robust state estimation

Abstract

State information of an object that is robust to different inputs or conditions can be determined. For drowsiness, facial landmarks can be determined from captured image data and used to determine a set of blink parameters. These parameters can be used, for example, in conjunction with a temporal network, to estimate the object's state (e.g., drowsiness). To improve robustness, an eye state determination network can determine eye state from image data without relying on intermediate landmarks, whose coordinates can be used (e.g., in conjunction with another temporal network) to estimate the object's state. A weighted combination of these values ​​can be used to determine the object's overall state. To improve accuracy, individual behavioral patterns and contextual information can be leveraged to account for data variations due to changes in the object or the current context rather than state.

Description

Background Technology

[0001] There has always been a desire to improve safety in various environments. For example, this could include accurately determining the drowsiness of a person who may be operating equipment (such as a vehicle or machine) and that insufficient attention or awareness could lead to damage or injury. While systems exist that attempt to determine states such as drowsiness or alertness, these systems are not accurate in all situations or sufficiently robust to changes in the user, the user's state, or environmental conditions. Attached Figure Description

[0002] Various embodiments according to this disclosure will be described with reference to the accompanying drawings, in which:

[0003] Figure 1A and 1B Examples of multiple components of a vehicle according to at least one embodiment are shown;

[0004] Figure 2A , 2B Figures 2C, 2D, 2E, and 2F illustrate feature data that can be used according to at least one embodiment;

[0005] Figure 3 A drowsiness estimation system that can be used according to at least one embodiment is shown;

[0006] Figure 4 An example process for estimating the state of an object, according to at least one embodiment, is shown;

[0007] Figure 5A and 5B A process for explaining changes or behaviors that are not caused by a change in the state of an object, according to at least one embodiment, is illustrated.

[0008] Figure 6 Components of a system for determining the state of a person according to at least one embodiment are shown;

[0009] Figure 7A The inference and / or training logic according to at least one embodiment is illustrated;

[0010] Figure 7B The inference and / or training logic according to at least one embodiment is illustrated;

[0011] Figure 8 An example data center system according to at least one embodiment is shown;

[0012] Figure 9 A computer system according to at least one embodiment is shown;

[0013] Figure 10A computer system according to at least one embodiment is shown;

[0014] Figure 11 At least a portion of a graphics processor according to one or more embodiments is shown;

[0015] Figure 12 At least a portion of a graphics processor according to one or more embodiments is shown;

[0016] Figure 13 This is an example data flow diagram of an advanced computing pipeline according to at least one embodiment;

[0017] Figure 14 This is a system diagram of an example system for training, adapting, instantiating, and deploying machine learning models in an advanced computing pipeline, according to at least one embodiment; and

[0018] Figure 15A and 15B A data flow diagram of a process for training a machine learning model according to at least one embodiment is shown, as well as a client-server architecture for enhancing annotation tools using a pre-trained annotation model;

[0019] Figure 16A and 16B Components that can be used with a vehicle system according to at least one embodiment are shown. Detailed Implementation

[0020] Methods according to various embodiments can provide for the determination of the state of a person or other such object. In particular, various embodiments provide for determining a person's drowsiness, fatigue, or alertness state based at least in part on observed blinking behavior over time. An end-to-end drowsiness estimation system comprising multiple neural networks can be used, thus being relatively robust to variations in the input data. One of these neural networks can be used to determine a set of facial landmarks in captured image data, which can be used to determine a set of blinking parameters of the object over a period of time. This set of blinking parameters can be used (e.g., in conjunction with a temporal network) to infer a state value of the object, such as the degree of drowsiness of the person of interest represented in the captured image data. A single neural network can determine eye states (e.g., open or closed) from the captured image data without relying on the accuracy of intermediate facial landmarks, which can improve the robustness of the entire process. Eye state information can be used, for example, in conjunction with another temporal network, to infer another state value of the object. The state values ​​from these temporal networks can then be used, for example, by weighted combination, to determine an overall state value estimate of the person if each infers with at least minimum confidence. This state value can be used to determine whether to take action based on the person's state, and to determine what type of action to take. To improve the accuracy of this estimation, the system can also attempt to account for behavioral variations between individual objects, as well as variations caused by changes in the current context or environment (e.g., changes in driving context). Object and / or context data can be provided as input to the temporal network, allowing the network to infer more accurate state data by comparing blink parameters or other observed behavioral data to a baseline that is more relevant to a specific object in the current context.

[0021] consider Figure 1A The autonomous vehicle 100 shown may be, for example, a semi-autonomous or computer-assisted vehicle that may include one or more drivers or passengers. In at least one embodiment, vehicle 100 may be, but is not limited to, a passenger vehicle, such as a car, truck, bus, and / or another type of vehicle that accommodates one or more passengers. In at least one embodiment, vehicle 100 may be a semi-trailer truck for hauling goods. In at least one embodiment, vehicle 100 may be an aircraft, a robotic vehicle, or another type of vehicle.

[0022] Autonomous vehicles can be described in terms of their level of automation, as defined by the National Highway Traffic Safety Administration (“NHTSA”), the U.S. Department of Transportation’s division, and the Society of Automotive Engineers (“SAE”) in its “Classification and Definition of Terms Related to Driving Automation Systems for Highway Motor Vehicles” (e.g., standard number J3016-201806, published June 15, 2018; standard number J3016-201609, published September 30, 2016; and previous and future versions of this standard). In one or more embodiments, vehicle 100 may be able to have one or more of the functions according to Level 1 through Level 5 of autonomous driving. For example, in at least one embodiment, depending on the embodiment, vehicle 100 may be able to perform conditional automation (Level 3), high automation (Level 4), and / or full automation (Level 5).

[0023] In at least one embodiment, vehicle 100 may include, but is not limited to, components such as chassis, body, wheels (e.g., 2, 4, 6, 8, 18, etc.), tires, axles, and other vehicle components. In at least one embodiment, vehicle 100 may include, but is not limited to, propulsion system 150, such as an internal combustion engine, a hybrid power station, an all-electric motor, and / or another type of propulsion system. In at least one embodiment, propulsion system 150 may be connected to the drivetrain of vehicle 100, which may include, but is not limited to, a transmission, to enable propulsion of vehicle 100. In at least one embodiment, propulsion system 150 may be controlled in response to receiving a signal from throttle / accelerator 152.

[0024] In at least one embodiment, a steering system 154, including but not limited to a steering wheel, is used to steer the vehicle 100 (e.g., along a desired path or route) when the propulsion system 150 is operating (e.g., when the vehicle is in motion). In at least one embodiment, the steering system 154 may receive signals from one or more steering actuators 156. The steering wheel may be optional for fully automated (level 5) functionality. In at least one embodiment, a brake sensor system 146 may be used to operate the vehicle brakes in response to receiving signals from one or more brake actuators 148 and / or brake sensors.

[0025] In at least one embodiment, there may be, but is not limited to, one or more system-on-chips (“SoCs”). Figure 1AA controller 136, comprising (not shown) and / or one or more graphics processing units (“(one or more) GPUs”), provides signals (e.g., signals indicating commands) to one or more components and / or systems of vehicle 100. For example, in at least one embodiment, controller 136 may send signals to operate vehicle braking via brake actuator 148, steering system 154 via steering actuator 156, and / or propulsion system 150 via throttle / accelerator 152. Controller 136 may include one or more onboard (e.g., integrated) computing devices (e.g., supercomputers) that process sensor signals and output operating commands (e.g., signals indicating commands) to enable autonomous driving and / or assisted human driving of vehicle 100. In at least one embodiment, controller 136 may include a first controller 136 for autonomous driving functions, a second controller 136 for functional safety functions, a third controller 136 for artificial intelligence functions (e.g., computer vision), a fourth controller 136 for infotainment functions, a redundant fifth controller 136 for emergency situations, and / or other controllers. In at least one embodiment, a single controller 136 may handle two or more of the above functions, and two or more controllers 136 may handle a single function, and / or any combination thereof.

[0026] In at least one embodiment, controller 136 provides signals for controlling one or more components and / or systems of vehicle 100 in response to sensor data (e.g., sensor inputs) received from one or more sensors. In at least one embodiment, sensor data may be received from, for example, but not limited to, the following devices: one or more Global Navigation Satellite System (“GNSS”) sensors 158 (e.g., one or more Global Positioning System sensors), one or more RADAR (radar) sensors 160, one or more ultrasonic sensors 162, one or more LiDAR sensors 164, one or more Inertial Measurement Unit (“IMU”) sensors 166 (e.g., one or more accelerometers, one or more gyroscopes, one or more magnetic compasses, one or more magnetometers, etc.), microphones 196, stereo cameras 168, wide-angle cameras 170 (e.g., fisheye cameras), one or more infrared cameras 172, one or more surround cameras 174 (e.g., 360-degree cameras), and remote cameras ( Figure 1A (not shown in the image), one or more medium-range cameras ( Figure 1A(not shown), one or more speed sensors 144 (e.g., for measuring the speed of vehicle 100), vibration sensors 142, steering sensors 140, brake sensors (e.g., as part of brake sensor system 146), and / or other sensor types.

[0027] In at least one embodiment, one or more controllers 136 may receive input (e.g., represented by input data) from the instrument panel 132 of the vehicle 100 and provide output (e.g., represented by output data, display data, etc.) via a human-machine interface (“HMI”) display 134, an audible signaling device, a speaker, and / or via other components of the vehicle 100. In at least one embodiment, the output may include information such as vehicle speed, velocity, time, map data (e.g., high-definition map). Figure 1A (not shown in the image)), location data (e.g., the location of vehicle 100, as on a map), direction, the location of other vehicles (e.g., occupied grid), information about objects as perceived by controller 136, and the state of those objects, etc. For example, in at least one embodiment, HMI display 134 may display information about the presence of one or more objects (e.g., street markers, attention markers, traffic light changes, etc.), and / or information about driving maneuvers that the vehicle has performed, is performing, or will perform (e.g., changing lanes now, exiting exit 34B within two miles, etc.).

[0028] In at least one embodiment, vehicle 100 also includes a network interface 124, which can communicate over one or more networks using wireless antenna 126 and / or a modem. For example, in at least one embodiment, network interface 124 may be able to communicate via Long Term Evolution (“LTE”), Wideband Code Division Multiple Access (“WCDMA”), Universal Mobile Telecommunications System (“UMTS”), Global System for Mobile Communications (“GSM”), IMT-CDMA Multicarrier (“CDMA2000”), etc. In at least one embodiment, wireless antenna 126 may also use one or more local area networks (such as Bluetooth, Bluetooth Low Energy (“LE”), Z-Wave, ZigBee, etc.) and / or one or more low-power wide area networks (“LPWAN”) (such as LoRaWAN, SigFox, etc.) for communication between objects in the environment (e.g., vehicles, mobile devices, etc.).

[0029] Figure 1B The illustration shows an embodiment according to at least one of the embodiments. Figure 1AExamples of camera positions and fields of view for the autonomous vehicle 100. In at least one embodiment, the camera and corresponding field of view are exemplary embodiments and are not intended to be limiting. For example, in at least one embodiment, additional and / or alternative cameras may be included and / or the cameras may be located at different positions on the vehicle 100.

[0030] In at least one embodiment, the camera type may include, but is not limited to, a digital camera suitable for use with components and / or systems of vehicle 100. In at least one embodiment, one or more cameras may operate at Vehicle Safety Integrity Level (“ASIL”) B and / or another ASIL. In at least one embodiment, depending on the embodiment, the camera type may have any image capture rate, such as 60 frames per second (fps), 120 fps, 240 fps, etc. In at least one embodiment, the camera may be able to use a rolling shutter, a global shutter, another type of shutter, or a combination thereof. In at least one embodiment, the color filter array may include a red transparent transparent transparent (“RCCC”) color filter array, a red transparent transparent blue (“RCCB”) color filter array, a red blue green transparent (“RBGC”) color filter array, a Foveon X3 color filter array, a Bayer sensor (“RGGB”) color filter array, a monochrome sensor color filter array, and / or another type of color filter array. In at least one embodiment, a transparent pixel camera (such as a camera with an array of RCCC, RCCB and / or RBGC color filters) may be used to attempt to increase photosensitivity.

[0031] In at least one embodiment, one or more cameras may be used to perform advanced driver assistance system (“ADAS”) functions (e.g., as part of a redundancy or fail-safe design). For example, in at least one embodiment, a multi-function single camera may be mounted to provide functions including lane departure warning, traffic sign assist, and intelligent headlight control. In at least one embodiment, one or more cameras (e.g., all cameras) may simultaneously record and provide image data (e.g., video).

[0032] In at least one embodiment, one or more cameras may be mounted in a mounting assembly, such as a custom-designed (3D-printed) assembly, to remove stray light and reflections from inside the vehicle (e.g., reflections from the dashboard in the windshield mirror), which may interfere with the camera's image data capture capabilities. Referring to a wing mirror mounting assembly, in at least one embodiment, the wing mirror assembly may be custom-3D printed such that the camera mounting plate matches the shape of the wing mirror. In at least one embodiment, one or more cameras may be integrated into the wing mirror. For side-view cameras, in at least one embodiment, one or more cameras may also be integrated into the four pillars at each corner.

[0033] In at least one embodiment, a camera having a field of view including a portion of the environment in front of vehicle 100 (e.g., a front-facing camera) can be used to surround the field of view to help identify forward-facing paths and obstacles, and, with the assistance of controller 136 and / or one or more control SoCs, to help provide information crucial for generating an occupancy grid and / or determining a preferred vehicle path. In at least one embodiment, the front-facing camera can be used to perform many of the same ADAS functions as LIDAR, including but not limited to emergency braking, pedestrian detection, and collision avoidance. In at least one embodiment, the front-facing camera can also be used for ADAS functions and systems, including but not limited to lane departure warning (“LDW”), autonomous cruise control (“ACC”), and / or other functions such as traffic sign recognition.

[0034] In at least one embodiment, multiple cameras can be used in a front-mounted configuration, including, for example, a monocular camera platform including a CMOS (“complementary metal-oxide-semiconductor”) color imager. In at least one embodiment, a wide-angle camera 170 can be used to perceive objects entering the field of view from the periphery (e.g., pedestrians, intersecting traffic, or bicycles). Although Figure 1B Only one wide-angle camera 170 is shown, but in other embodiments, any number (including zero) of wide-angle cameras 170 may be present on vehicle 100. In at least one embodiment, any number (one or more) of remote cameras 198 (e.g., a pair of long-view stereo cameras) may be used for depth-based object detection, especially for objects for which neural networks have not yet been trained. In at least one embodiment, the remote cameras 198 may also be used for object detection and classification, as well as basic object tracking.

[0035] In at least one embodiment, any number of stereo cameras 168 may be included in the front-mounted configuration. In at least one embodiment, one or more stereo cameras 168 may include an integrated control unit that includes a scalable processing unit that can provide programmable logic (“FPGA”) and a multi-core microprocessor with an integrated controller area network (“CAN”) or Ethernet interface on a single chip. In at least one embodiment, such a unit can be used to generate a 3D map of the environment of the vehicle 100, including distance estimates for all points in the image. In at least one embodiment, one or more of the stereo cameras 168 may include, but are not limited to, a compact stereo vision sensor, which may include, but is not limited to, two camera lenses (one on each side) and an image processing chip that can measure the distance from the vehicle 100 to a target object and use the generated information (e.g., metadata) to activate autonomous emergency braking and lane departure warning functions. In at least one embodiment, other types of stereo cameras 168 may be used in addition to those stereo cameras described herein or alternatively.

[0036] In at least one embodiment, a camera (e.g., a side-view camera) having a field of view including a portion of the environment on the side of the vehicle 100 can be used for surround view, providing information for creating and updating occupancy grids, and for generating side impact collision warnings. For example, in at least one embodiment, one or more surround cameras 174 (e.g., such as...) Figure 1B The four surround cameras 174 shown may be positioned on vehicle 100. In at least one embodiment, the surround cameras 174 may be any number and combination of, but not limited to, wide-angle cameras 170, fisheye cameras, 360-degree cameras, and / or the like. For example, in at least one embodiment, four fisheye cameras may be located at the front, rear, and sides of vehicle 100. In at least one embodiment, vehicle 100 may use three surround cameras 174 (e.g., left, right, and rear), and may use one or more other cameras (e.g., front-facing cameras) as a fourth surround-view camera.

[0037] In at least one embodiment, a camera (e.g., a rear-view camera) having a field of view including a portion of the rear environment of vehicle 100 can be used for parking assistance, surround view, rear collision warning, and creating and updating occupancy grids. In at least one embodiment, a wide variety of cameras can be used, including but not limited to cameras that are also suitable as front-facing cameras (e.g., one or more long-range cameras 198 and / or one or more mid-range cameras 176, one or more stereo cameras 168, one or more infrared cameras 172, etc.), as described herein.

[0038] In various situations, it may be desirable to determine the state of a person in or associated with such a vehicle. This may include, for example, determining the drowsy or alert state of the vehicle's driver. Methods according to various embodiments may utilize one or more cameras or imaging sensors, such as those previously discussed for such vehicles, capable of capturing image or video data of at least a portion of the person of interest. This may include, for example, a driver-facing camera capable of capturing at least the face of the driver or another person seated in the driver's seat, or other locations associated with at least a certain amount of vehicle control. Such a camera may be positioned in any suitable location, such as on or near the instrument cluster, rearview mirror, left pillar, or touch interface, among other such options. Such a camera may be a panchromatic or grayscale camera with any suitable resolution, and infrared (IR) or other sensors may also be included in various embodiments.

[0039] In at least one embodiment, video or images of such a person can be captured periodically or continuously at specific times. If captured at specific times, these times can be determined according to a selection algorithm, or can be determined at least in part based on one or more triggers, such as signals sent from the vehicle system in response to actions or behaviors that may be associated with driver drowsiness. In other embodiments, triggers can be sent in response to changes in the environment, such as moving to a congested urban area that may require more attention, or entering the evening or night when the driver may be more likely to be drowsy. This timing can also be configurable by the user, application, or device.

[0040] In at least one embodiment, one or more cameras may be used to capture a sequence of images or video frames (e.g., a stream). Typically, these images or video frames will include a representation of at least a portion of the face of a person of interest, such as... Figure 2AAs shown in image 200. Depending on factors such as the camera's position relative to the person and the field of view, the captured image may primarily represent the person's facial region, or it may include a larger view of parts such as the torso, arms, etc. In at least one embodiment, such an image may be passed to a face detection network or other face detector, which may attempt to determine whether a person's face is present in the image. For example, if the person is not currently in that position, has turned away from the camera, or is in another position such that a sufficient portion of the person's face is not displayed in the image, confident face detection can be enabled. It is also possible that some obstacle obstructs the view of the face, such as an arm or hand positioned between the camera and the face during vehicle movement.

[0041] If a face is detected in an image (or video frame, etc.), that image can be selected for analysis. For simplicity of explanation, the term "image" or "image data" will be used in many examples, but it should be understood that this can also refer to video frames, video data, sensor data, or any other type of data that can capture or represent information about one or more visual aspects of a person. Not every captured image can be analyzed; for example, if the person is in a normal or alert state, the system may analyze one-tenth of the images, but if the person is less alert or drowsy, the images can be analyzed more frequently. As discussed in more detail elsewhere herein, images can also be analyzed more frequently for certain environmental conditions or driving contexts. In at least one embodiment, data corresponding to facial regions of an image can be used to select a portion of the image to be analyzed, reducing the required storage and processing power, and focusing on more relevant parts of the image, which can help improve the accuracy of inference or determination for at least some systems.

[0042] For an image to be analyzed, a first neural network, such as a face landmark detection network, can be used to process at least the facial portion of the image. The facial portion can be identified using coordinates or bounding boxes provided by the face detection network. Other feature detection mechanisms can also be used within the scope of various embodiments. The face landmark detection network can be trained to infer the location of specific types of landmarks, reference points, or features in the image. This can include recognizing any one of, for example, 100 or more different features represented or detectable in the input image. Figure 2A As shown, this could include identifying landmarks 202, such as the top and bottom of a person's ear. Such landmarks are at least useful because they can help determine the head's pose or orientation relative to the camera that captured the image. Other landmarks 232 could also be useful, for example... Figure 2BThe landmarks shown in image region 230. These landmarks correspond to the extreme values ​​of each iris of a person (here, up, down, left, and right), and can then be used to determine information such as the number of times the person's eyes are open. Changes in the relative positions of these landmarks 232 between consecutive frames can be used to detect blinks and determine values ​​such as the amplitude, speed, or duration of a single blink. In at least one embodiment, information about any detected landmarks can be output by a facial landmark detection network, which may include, for example, the coordinates of a given landmark in the image, and an identifier of the type of landmark identified.

[0043] Data from at least some of these features or landmarks can also be provided as input to other neural networks, algorithms, or modules used to determine other aspects or behaviors. For example, facial landmarks related to a person's eyes can be provided to an eye state determination neural network along with at least a portion of the face in the input image to determine the region in the input image corresponding to a person's eyes. In other embodiments, some facial landmarks can be used to crop the input image to only the eye region, and this cropped image data can be provided as input to the eye state network. This allows the eye state neural network to focus on the portion of the input image corresponding to the eyes in order to provide more accurate inference about the eye state and simplify the corresponding network training process. In at least one embodiment, the eye state network can output the state of each eye, such as open or closed for a binary decision network, or other values, such as open, closed, or partially open (possibly with some open values). This can include some openness measurements for the partially open state, such as the distance of the inference or the percentage of the total blink amplitude, and a confidence value in the state determination.

[0044] Data from at least some of these landmarks can also be fed into neural networks, processes, or algorithms to determine a person's head pose, at least relative to the viewpoint of the camera used to capture the image. For example... Figure 2AAs shown, the relative spacing and position of at least some of these facial landmarks can be used to determine head pose, such as roll, pitch, and yaw of the head relative to a default orientation, axis, or coordinate system. This might correspond to a head centered in the image and positioned as if looking directly at the camera, or orthogonal to the plane of the 2D image (if the image data is 2D). Pose information can be used to determine differences between landmark positions due to head pose or orientation, rather than due to human action or behavior. Pose information can also be used to normalize the positions of these landmarks or eliminate the effects of pose. For example, pose information can be used to determine the transformation to be applied to the determined landmark positions to generate a landmark representation 260 with the effects of head pose removed, so that the features correspond to the face as if the face were in a default orientation or position. This approach can help to more accurately determine the distances between features or landmarks, and how these distances change over time. In at least one embodiment, facial landmark data can be compared to a three-dimensional (3D) ground-based head model to associate the landmarks with the model and determine the model's relative orientation in the image. In at least one embodiment, the solvePnP technique can be used to estimate head position and rotation in three dimensions.

[0045] In some cases, using a single network to determine blink-related information may be sufficient, rather than using both a facial landmark network and an eye state network simultaneously. For example, as... Figure 2D As shown in image 270, facial landmarks 272 can be used to determine when a person's eyes are open, and as shown in image 280, facial landmarks 282 can be used to determine when a person's eyes are closed, and the state in between. In addition to blink parameters (such as blink amplitude, duration, and speed), these landmarks can also be used to determine information such as blink frequency. However, it is possible that the user's face may be in a position such as an "extreme" position where these landmarks may not be recognizable, or at least difficult to recognize with sufficient confidence or accuracy. As mentioned earlier, this could occur when the user looks away from the camera, when the facial field of vision is partially obstructed, when the person is wearing reflective glasses, etc. Any uncertainty in these landmarks or intermediate features can lead to uncertainty in the determination of blink parameters.

[0046] Therefore, an eye state network can be used to determine eye states more accurately under at least these extreme conditions. The eye state network can be trained end-to-end so that it infers eye states directly from the input image data without requiring any intermediate features or values. As long as a sufficient number of at least one eye are represented in the input image data, the eye state network can infer eye states relatively accurately. For blink determination, the open and closed eye states can be determined relatively accurately, allowing for accurate determination of the overall blink frequency even if intermediate values ​​have some uncertainty regarding partially open or closed eye states. For example, Figure 290 shows a curve of eye states (e.g., aspect ratio) versus time (e.g., number of frames in a sequence). Figure 2F As shown in the example, many measurements correspond to the open-eye state, with values ​​close to the maximum open-eye state or blink amplitude (normalized to 1). The closed-eye state near the bottom of the curve roughly represents the middle of the blink action, or at least the point where the aspect ratio is at its lowest. Even if the measurements for partially open eyes are not very accurate, the overall shape of the curve does not change much, allowing for accurate determination of the duration between the open-eye states on both sides of the blink. Therefore, as long as at least a sufficient number of eyes are visible in the captured image data, the eye state network can determine the eye state accurately enough to generate accurate blink frequency determinations, even for extreme locations or conditions. In at least one embodiment, an algorithm for extracting blink features can receive the output from the eye state network, indicating when the eye is determined to be open or closed in the current frame. The most recent frames in the sequence can be analyzed to determine whether eye closure is detected in consecutive frames. If multiple closed-eye frames exist, the minimum eye aspect ratio (EAR) can be determined and designated as the bottom point, such as... Figure 2F As shown, it can be based at least in part on facial landmark data. The start and end frames of a blink can also be determined using EAR values ​​derived from facial landmark data.

[0047] As described above, in some embodiments, a binocular state network can be used in conjunction with a facial landmark network to extract blink features. The binocular state network can serve as a reliable binary classifier and can identify at least one frame in which the eyes are detected as closed for a given blink. Any of these identified frames, along with potentially nearby frames in the sequence, can be analyzed to determine or infer a bottom point in aspect ratio determination. The aspect ratio can be calculated at least in part based on the facial landmarks of these frames, and thus can be used to determine the minimum eye aspect ratio for that particular user, which may vary between individuals. Frames in the sequence can then be analyzed in each direction to identify blink state points and blink end points, where the eyes are fully open, close to fully open, or at least at or near their maximum value for a period of time. The sequence can be analyzed to determine a maximum aspect ratio, which can be set as the normal maximum aspect ratio for an open-eye state, at least under the current conditions of that particular subject. This value can be used to determine blink start and stop points, which helps generate more accurate frequency and duration calculations.

[0048] Figure 3 Components of an example drowsiness estimation system 300, which can be used according to various embodiments, are shown. In this example, one or more images 302 captured by one or more cameras (or sensors, etc.) at least partially oriented towards the person of interest can be provided as input to a drowsiness estimation module 304 (or system, application, service, or process, etc.). For vehicles, this module 304 can be on the vehicle itself or remotely, as discussed later herein, such as in the cloud or on a remote server accessible via at least one wireless network. In other examples, portions of this functionality, possibly related to face detection and / or facial landmark detection, can be performed on the vehicle to reduce the amount of data to be transmitted for analysis relative to the complete image data.

[0049] In this example, image data is passed to a face detection network 306. This network can be any suitable neural network, such as a convolutional neural network (CNN), trained to infer the presence of faces in the input image data. If no face is detected in the image with at least minimal confidence, the image data can be discarded, and no further analysis is performed until subsequent data is received. If a face is detected, at least a portion of the image data can be passed to at least a face landmark determination network 314 for analysis. In at least some embodiments, information about the location of the detected face in the image can also be passed, or the input image data can be cropped to a face region before being provided as input to the face landmark detection network 314. Obviously, there may be additional components, processes, or modules for at least some of this functionality, such as a module capable of cropping the input image to a face region given face region coordinates provided by the face detection network.

[0050] In at least one embodiment, information from the detected faces can also be used to attempt to identify the person corresponding to the detected face. This can be performed by a face detection network or by a separate face recognition module or network communicating with the face detection network. The input image, detected face data, or other information (including potential face landmarks determined by the face landmark detection network 314 in some embodiments) can be compared with face data in the personal database 308 or other such locations. If the person can be identified with sufficient confidence, such as at least meeting a minimum confidence threshold, another determination can be made regarding the existence of a profile of that person stored in the profile database 310 or otherwise accessible. As will be discussed in more detail later herein, such profile information can be used to determine a specific blinking behavior of a given user, which can be used to make a more accurate estimate of drowsiness by taking into account variations in blinking behavior between different individuals.

[0051] As shown in the figure, image data for at least one facial region, along with any output from the face detection network 306 and any personal profile data, can be passed to one or more neural networks for analysis. In this example, the data is passed to a facial landmark detection network 314, a head pose determination network 312, and an eye state determination network 316, although other networks, algorithms, or processes may be used within the scope of various embodiments. In this example, the facial landmark network 314 can analyze at least the facial portion of the input image to attempt to infer the location of as many facial landmarks as possible. The network can be trained to recognize any number of different landmarks, for example, more than 100 different landmarks in at least one embodiment, and can output the location of each detected landmark in the image, the type of the landmark, and the confidence level of the determination or inference.

[0052] In at least one embodiment, at least some facial landmark data may be provided to the head pose determination network 312 along with the input image data. The head pose determination network may be trained to infer head pose or orientation data, such as roll, pitch, and yaw, at least in part based on the relative positions of facial landmarks in the input image. In at least one embodiment, the head pose determination network may output inferred values ​​for each of roll, pitch, and yaw, or other such orientation determinations, and one or more corresponding confidence values. In some embodiments, the head pose determination network may be an end-to-end network that infers head pose from input image data without using facial landmark data, which would make the head pose determination network more robust; however, since the facial landmarks are determined in the system, these landmarks can be used to determine head pose more effectively anyway, with similar accuracy in most cases. If the condition of the head prevents the landmarks from being accurate, then the head pose information may not be used anyway, as discussed elsewhere herein.

[0053] Head pose information, along with facial landmark data, can be provided to the blink parameter determination module 318. In at least one embodiment, the module can use the head pose information to normalize the facial landmark data or remove variations generated due to the orientation of the face in the input image data and the relative distances between landmarks. The blink parameter determination module can then use data from the image and previous images in the sequence to determine values ​​for various blink parameters. This can include, for example, determining the amplitude, speed, and duration of blinks over a recent period, such as the last ten seconds, thirty seconds, or one minute. Values ​​for other blink or state parameters can also be determined within the range of various embodiments. Furthermore, while these blink parameters can be handcrafted and easily understood, at least some of these parameters may be previously undetermined and learned by the network during training. In this example, these blink parameter values ​​can then be fed into a temporal network, such as a Long Short-Term Memory (LSTM) network 322, a transducer or gated recurrent unit (GRU), or a support vector machine (SVM) for analysis. Blink parameter values ​​can be coupled with other drowsiness indicators, such as steering wheel patterns (e.g., the amplitude, frequency, or standard deviation of steering wheel movements, reversals, etc.), lane-keeping patterns (e.g., the number of lane crossings, the standard deviation of lane positions), EEG / ECG patterns, etc., as input to the (LSTM) network 322. The LSTM network can apply different weights to blink values ​​determined at different times, for example, by applying greater weights to recent events compared to events in the distant past, and this information can be used to infer the person's drowsiness level. Greater weighting of recent data helps the system become more robust to changes in environmental data or driving context, or to changes in the user's physiological state over time, while still taking into account patterns observed in a given person over time. As discussed later herein, this can include the determination of a first state value, for example, which may correspond to a Karolinska Sleepiness Scale (KSS) value used for determining drowsiness. Other state values ​​can also be determined, such as values ​​from any drowsiness scale (e.g., values ​​on the Stanford Drowsiness Scale or the Epworth Drowsiness Scale), or values ​​on any scale representing fatigue due to drowsiness, for the determination of drowsiness-related states. Such values ​​can also be generated relative to any measure representing a loss of performance or ability (e.g., a subjective or good-performing goal), such as a loss of driving performance due to drowsiness or fatigue (or other states of interest). In at least some embodiments, temporal networks such as LSTM can provide more accurate results than models or networks such as SVM, which can be used to attempt to determine drowsiness instantaneously, rather than analyzing one or more patterns over a period of time based on multiple blinks.

[0054] As mentioned above, drowsiness values ​​may not always be reliable, especially under extreme conditions, such as when the head is significantly turned away from the camera during image capture. To provide robustness for drowsiness estimation in such cases, an eye state network 316 can be used to perform a second estimation of drowsiness. In this example, the eye state network 316 may receive facial landmark data from a facial landmark network for landmarks (or bounding boxes, etc.) associated with a person's eyes. The eye state network can then use this information to focus only on one or more portions of the input image that represent one or more eyes of a person. In other embodiments, the eye state network may analyze the input image or at least the facial region of the image without receiving facial landmark data. The eye state network 316 can be trained to determine the state of the eyes in the image, such as whether the eye is fully open, fully closed, or partially open / closed. In at least some embodiments, the network can infer values ​​representing "open" or "closed," such as values ​​between 0 representing fully closed and 1 representing fully open. A "fully open" eye may correspond to an eye with the largest possible eyelid separation observed by the user or otherwise. The network can output such a value for each detected eye or both eyes together, along with a corresponding confidence value for each. In at least one embodiment, this information can be provided as another input to the blink parameter determination module 318 for more accurate blink parameter determination. In this example, eye state information, along with relevant information from a recent period, can be provided to the blink frequency determination module 320, the system, device, process, or service. The blink frequency determination module 320 can analyze changes in eye state over a recent period to determine the occurrence of blinking actions and can use it to calculate blink frequency values ​​over a recent period. This blink frequency information, along with blink frequency information from previous time periods in this example, can be provided to another LSTM network 324, which applies different weights to blink frequency data obtained from different recent past periods. The frequency information can be concatenated with other drowsiness indication signals, such as steering wheel patterns (e.g., the amplitude, frequency, or standard deviation of steering wheel movement, reversal, etc.), lane keeping patterns (e.g., the number of lane crossings or standard deviation of lane position), EEG / ECG data, etc., as input to the (LSTM) network 324. The LSTM network 324 can then infer a second drowsiness value for the person, which can correspond to the determination of a second KSS value. While these values ​​may be provided individually in some embodiments, in this example, they can be used to provide a single output drowsiness estimate.Furthermore, if the confidence value of the facial landmark data does not meet at least the minimum confidence threshold, such as in images with extreme head positions or partially occluded faces, the facial landmark data may not be provided to the first LSTM network, and only the second LSTM network can be used to predict drowsiness for the image based on one or more results from the eye state network.

[0055] If the drowsiness values ​​are consistent, at least within an acceptable range, the estimate can be provided as the output drowsiness value 330. If the values ​​are inconsistent, the individually determined relative confidence values ​​can be analyzed. If one determination has high confidence while the other does not, the determination with high confidence can be provided. In other embodiments, the value can be a mixture of two determinations weighted by confidence, such that if a score 8 has high confidence and a score 5 has low confidence, the final result 7 can be determined by applying a higher weight to score 8. Various other methods can also be used within the scope of the various embodiments.

[0056] As mentioned, values ​​that can provide a view of a person's state at a specific point in time or over a period of time can be inferred or generated. While values ​​such as KSS values ​​have been previously generated to attempt to provide a measure or indication of a specific state, previous methods have generally failed to provide sufficient accuracy and robustness due to factors such as inaccurate feature detection. Systems according to various embodiments can overcome these shortcomings by leveraging multiple networks, where these networks can utilize or rely on different information and are therefore not limited by a single set of inaccurate features or values. As previously described, this could include blink detection using an open-eye-closed network that can be used to derive blink frequency features (e.g., PerCLOS), and a facial landmark network for blink feature extraction, including blink amplitude, blink duration, and blink speed. Such a system could also include two temporal (e.g., LSTM) networks to associate blink events and features with KSS. Based at least in part on facial landmark confidence and head pose data, the drowsiness estimation system can select high-confidence features to train these temporal networks. If the facial landmark confidence is high, the temporal network can be trained using blink frequency features, as well as blink amplitude, blink duration, and blink speed features. These features can be frontalized using head pose data (or have their position affected by orientation removal). Otherwise, if the facial landmark confidence is low, the temporal network can be trained using only blink frequency data. This approach significantly improves the accuracy of drowsiness estimation due to the use of multiple networks and robust feature selection.

[0057] Figure 4An example process 400 for determining drowsiness, which may be used according to various embodiments, is illustrated. It should be understood that, for this process and other processes discussed herein, unless specifically stated otherwise, additional, fewer, or alternative steps may be performed in a similar or alternative order or at least partially in parallel within the scope of various embodiments. Furthermore, while this example is described in relation to drowsiness of a person driving a vehicle, the determination of a person's state can be used for other types of states of people or objects performing other types of activities, as within the scope of various embodiments of the invention. In this example, image data is received at 402, which includes a representation of at least a portion of the face of a person (or other object) of interest (e.g., the driver of a vehicle). The image data can be analyzed at 404 using a face detector network to determine the presence of a face and information about the face's location in the image. If no face is detected, or if a face cannot be determined with at least minimum confidence, the process may discard the image data and wait for subsequent image data in which a face can be detected. If a face is detected, at least a facial region of the image data can be analyzed at 406 to attempt to identify multiple facial landmarks that can be used to determine information about a person's state (e.g., drowsiness).

[0058] Once at least a determinable subset of facial landmarks has been identified, these landmarks can be used for a variety of different tasks. As one such task, at least some of these facial landmarks can be provided to a head pose network 408 to attempt to determine the head pose of a person of interest, at least as represented in the image data. In other embodiments, the head pose can be determined directly from the input image data. In this example, the facial landmark data can also be used 410 to crop the input image data, or at least identify a portion of the input image data to primarily contain one or more eye regions, such as a region for both eyes or a separate region for each eye (if represented in the image data). Image data of these one or more eye regions can be provided as input to an eye state determination network that can determine the state of a person's eyes, such as open or closed for a binary network, or partially open for a non-binary network. Any or all of the head pose, eye state, and facial landmark sets can also be used 412 to determine values ​​for a set of eye parameters, such as blink rate, duration, and amplitude. These eye parameter values, along with similar values ​​from a recent period, can be provided as input to a first-time network to attempt to infer the state value of the person of interest, such as a drowsy value. In some embodiments, this step can be performed only if the facial landmarks and / or the set of state parameters can be determined with at least a minimum confidence level or threshold. In parallel, eye state data from the eye state determination network, along with similar data from a recent period, can be provided to another time network to infer another drowsy value based on eye state data independent of intermediate facial landmarks, which can make the determination more robust to variations in the input image data. The overall drowsy value of this person can then be determined, at least in part, based on these inferred drowsy values ​​(if available). This can include, for example, performing a weighted average or selecting the most confident drowsy value, among other such options. Once the overall drowsy value is determined, the system, service, application, module, or process receiving that value can determine, at least in part, whether to take action, based on the overall drowsy (or other such state) value. For example, this could include providing notifications, generating alerts, or taking remedial or proactive actions, such as at least partially controlling a task that is currently being performed or will be performed.

[0059] This method can be very accurate in estimating a person's current state. However, different people often exhibit different behaviors, such as different blinking behaviors. To improve the accuracy of state estimation for different subjects, it may be beneficial to attempt cross-user normalization in some of the later embodiments. Certain characteristics or behaviors may exhibit different baseline levels or ranges across different individuals, which may be related to the individual's physiological state. Different individuals may also have different optometric operating patterns, such as different blinking patterns and rates. Determining drowsiness and fatigue can be very complex and based on many different factors. Good approximations of drowsiness and fatigue can be obtained by analyzing a set of blinking parameters, since at the onset of drowsiness, a person's blinking rate increases, blinking speed decreases accordingly, or blinking duration increases. The person's blinking amplitude may also decrease at the onset of drowsiness. Any of these blinking parameters, individually or in combination, can be used to estimate the drowsiness of a person or subject. However, to make this estimation accurate, it may be beneficial to determine how the values ​​of these parameters change for individual subjects in different states of drowsiness. There can be significant differences between individuals, as some people blink more frequently than others, and blinking speeds may vary, regardless of whether they are drowsy or not. Therefore, a global threshold or assessment may not provide accurate results for all observed users, as one person's normal blinking frequency may represent another person's drowsiness. Thus, methods according to various embodiments may attempt to learn or acquire information about an individual's actions or behaviors in order to make more accurate estimates or assessments for that particular individual.

[0060] As described above, various methods can be used to identify the person to whom state estimation will be performed. In some embodiments, this may include user login or selecting a profile from an interface within the vehicle. For some vehicles, there may be other ways to identify a person, such as through various biometrics, or the person may be set as the vehicle's default operator. In some cases, identity can be determined by using specific keys or input. As described above, facial (or other body part) recognition or identification systems can also be used, for example, in the case of capturing at least one image of a part of a person, which can then be analyzed to attempt to determine identity. This may include, for example, comparing facial features to a feature set stored in a user database, and other such options. Once a person is identified, that person's information can be used to improve state estimation. This may include, for example, extracting behavioral data from a user profile, or determining the person's behavioral category or type, and other such options.

[0061] User profiles (or other data repositories for one or more individuals) may include various types of data that may be associated with one or more types of state estimation. This may include data such as average or “normal” blink rate or blink amplitude, and typical ranges for such values. This allows estimations of states such as drowsiness to be performed relative to an accurate baseline for that particular individual. Other data on actions, characteristics, or patterns may also be stored, which may relate to different driving skills or behaviors, different reaction speeds, etc., for example, the frequency with which a person adjusts steering or the patterns a person uses to change lanes. At least in some cases, these values ​​may be vehicle-dependent, and a person may have different values ​​for different vehicles, such as a sports car versus an SUV, which may have very different handling or operating characteristics. In at least one embodiment, the robustness of the state estimation system or service can be improved by taking into account overall variation, for example, by considering individual details during model training.

[0062] In at least one embodiment, the individual's data can be used to train a drowsiness model for that person. This can include, for example, utilizing self-reported KSS or state data, as well as data from a specific subject profile. Data from the subject profile can include information such as driving experience level, age, sex, nationality, or any individual differences that may lead to or be associated with changes in state, such as drowsiness symptoms. The subject profile can also include baseline signal values ​​corresponding to when the subject is in a particular state, such as a specific level of drowsiness, which may be related to a specific blink rate or blink rate range, or to behavior related to drowsiness when in an alert state. The profile baseline signal can be used to normalize the data so that the results produced using the drowsiness estimation model are not significantly affected by individual differences. For example, two subjects may have different blink rates when in an alert state, and therefore different blink rates when drowsy or sleepy. Without a profile baseline or other such subject-specific data, the model may struggle to learn thresholds or ranges to distinguish states, such as whether an subject is drowsy based on absolute blink rate values. The profile baseline does not need to be derived from a specific state (e.g., an alarm state), but can or alternatively can be derived from any drowsiness level. In at least one embodiment, multiple drowsiness estimation models can be trained based on different profile baseline data for any or all drowsiness levels, such that the models can estimate the drowsiness level given a baseline profile for any drowsiness level. In at least one embodiment, feature vectors generated by the facial landmark network or including blink parameters determined from the output of the facial landmark network can be normalized before being passed to the LSTM network for analysis. This can include, for example, using the feature vector as the mean, or normalizing the feature range by subtracting the mean and then dividing by the standard deviation of the feature vector.

[0063] In one embodiment, when an object enters the vehicle or appears in a monitored location such as the driver's seat, the system may attempt to identify the person. As previously mentioned, this may include using facial recognition or biometric technology to identify the person. If identified, the system may attempt to determine whether the person or object has an available profile, whether it is stored in a non-transitory storage medium in the vehicle, or whether it is accessible via at least one network. If such a profile is available and accessible, the system may use the data in the profile to normalize data for the user and deploy an appropriate state estimation model. If the object does not have an existing and accessible profile, an attempt may be made to generate such a profile. In some embodiments, this may include monitoring or capturing information related to the user over a period of time to attempt to determine baseline information. In some embodiments, the person may have an option to indicate whether the person wishes to perform a user calibration process, thereby allowing the person to provide certain information and having additional information captured or acquired, which may be used to generate a state baseline for one or more user activities or behaviors.

[0064] To provide accurate estimates, the camera or sensor can also operate at a relatively high capture rate. A user's blink duration may be only a fraction of a second, so running the camera at a rate of at least 30Hz or 60Hz to obtain sufficient blink data may be beneficial. For example, if a person's blink duration is approximately 0.2 seconds, it must be run at a capture rate of at least 30Hz to obtain at least 5-6 blink data points, and fewer points at the start, middle, and end of a blink will lead to greater uncertainty in determining values ​​such as blink rate and duration. In at least some embodiments, it may be desirable to make this data collection as inconspicuous as possible, so that the user may not even be aware that data is being collected, and it will never compromise the safety of activities such as driving data collection.

[0065] If a person or object chooses to perform user calibration, they can be instructed to follow a specific data collection procedure to provide the system with one or more rounds of data for estimating a profile baseline specific to that object. The object may not need to provide the complete dataset in this data collection step, as the user may not be able to provide data for all possible user states. The system can acquire the data provided for certain states and can use that data to locate the nearest profile in the profile database, for example, using a nearest neighbor search process to locate the data used to complete the object's profile, or at least for inference of any missing data. As part of the calibration process, the system can allow user feedback or input. If the object finds that the drowsiness estimate deviates significantly from the self-reported KSS or current perceived drowsiness, the object can provide feedback that can be used to adjust and / or retrain the relevant model, or to adjust one or more baseline values ​​or the object's range.

[0066] If a person chooses not to perform user calibration, the system can attempt to identify profiles that approximate the behavior of that particular person. For example, this might involve analyzing captured image data to try to determine certain aspects of a person, such as age, sex, breathing pattern, or heart rate, and selecting profiles of people that best match at least some of these aspects.

[0067] Figure 5A An example process 500 for considering changes in user behavior data is shown. In this example, image data 502 (or otherwise obtained) is received, which includes a representation of at least a portion of the face of a person of interest. In other examples, additional information that may help identify the person may be received, such as information related to biometrics, identity, or other such information. In this example, the image data is analyzed 504 using a facial recognition process to determine the identity of the person of interest represented in the captured image data. A determination 506 can then be made regarding the existence of a relevant behavioral profile and its accessibility to the person. If identification is not possible, such a profile cannot be determined. If it is determined 508 that such a profile exists, relevant behavioral data of the person can be obtained 510 from that profile. If such a profile does not exist or is inaccessible, the user may be requested or prompted to undergo or participate in a calibration process to attempt to collect information for constructing such a profile for the person. If it is determined 512 that such a calibration process can proceed, a calibration process 514 can be performed to generate a behavioral profile for the person. As previously described, this could include collecting image and sensor data for the person, and potentially receiving user input about their state in order to generate calibration, pattern, or baseline data for that person under at least certain conditions or contexts. Similar profiles could be referenced to attempt to fill in any gaps in the profile or to provide a starting point for calibration. If calibration is not performed, or if the person is not identified, the closest or default profile can be selected based on any available and permissible data, which may relate to aspects of the person, location, or action to be performed. In some embodiments, if the user cannot be identified or any calibration is refused, such a process can determine to avoid using user behavior data in an attempt to improve the accuracy of state determination. If a profile is determined or generated, the state data can be normalized using 518 behavioral data from that profile to account for variations between individual users. This could include, for example, providing the behavioral data as an input feature vector to a temporal network that infers state values ​​based on observed user input, such as blink parameter values ​​determined over a recent period, where person-specific baselines, ranges, or behaviors can be used to more accurately infer the person's state.

[0068] As mentioned, a person's behavior or actions may also vary due to other factors that may be related to the environment or context in which the person is located or involved. For a person operating a vehicle, this can include various types of driving contextual information, as it can include a variety of environments and other such factors. For example, a person may blink or squint more frequently in a bright environment than in a dark environment. Furthermore, a driver in a congested urban location may tend to be more attentive and may tend to move his or her eyes more frequently in such an urban environment compared to a rural environment where there are few other vehicles or objects nearby. At least some of these environmental conditions can be analyzed by one or more cameras associated with the vehicle (e.g., Figure 1B The image or video data captured (as shown) is used to determine this. Environmental data can also come from other sources, such as external data sources accessible via at least one network (e.g., traffic, weather, or navigation services), internal clocks, or temperature sensors. Other data obtained by the vehicle's sensors, such as those mentioned above... Figure 1A Some of the data discussed can also be used to determine various environmental conditions or aspects of the current driving context, such as whether the road is curved or straight based on steering wheel movement, or whether there is heavy traffic or parking based on braking information. If GPS or navigation data is available, this information can also be used to provide at least some amount of contextual information for the current route or location. Brightness sensors can be used to determine lighting conditions, and vehicle control systems (such as steering and braking systems) can be used to infer aspects such as road or traffic conditions.

[0069] This driving context can be used to refine the baseline for reasoning or estimating the state of a person operating within that driving context. Any or all available contextual information (or other relevant information or inferences) can be analyzed to attempt to determine one or more state baselines for the person under the current conditions. This might include, for example, adjusting the range or baseline that can be used to infer different states of drowsiness based on these conditions. For instance, if a person blinks more frequently in a blizzard than under normal conditions, adjusting the baseline for this driving context could help prevent the increased blinking frequency from being interpreted as a change in drowsiness. Similarly, if a user typically behaves differently in the current driving context, what might normally be considered typical behavior could actually indicate that the user is beginning to feel drowsy, where failure to consider the driving context might lead to this increased drowsiness, which would otherwise remain undetected.

[0070] In some systems, driving contexts can be applied across all users in a similar manner. In other systems, personal profiles can be updated using information from different driving contexts. This could include, for example, monitoring user behavior over time in different driving contexts and updating the baseline based on observed behavior. In some systems, users can authorize the collection of information that can help calibrate the system, such as by responding to questions about drowsiness or other states when the vehicle is running in a specific set of driving conditions or contexts. Similar to personal profiles, there may not be enough information to fill in a complete profile for various driving contexts, so the system may attempt to fill in the missing information by extracting information from other objects with similar driving context changes from one or more profiles.

[0071] The use of driving context (or similar types of environmental data used for other activities) enables state estimation systems to generalize well when tested on different individuals in a variety of driving contexts. To further improve accuracy, such systems can leverage inputs from multiple sources to obtain a more accurate view of user behavior and the current driving context or environmental conditions. Many traditional systems attempting to determine drowsiness rely solely on data from a single source, such as a single sensor or method, and do not consider any variations in the driving context. These systems might look for user behavior, such as yawning or changes in steering wheel patterns in video data, as the sole indicator. Detection systems that use only one method without driving context risk low accuracy because these drowsiness signals are context-dependent, as drivers at the same drowsiness level exhibit different physiological behaviors and driving performance in different driving contexts. By fusing information from multiple sources and considering driving context beyond user variations and behavior, a robust drowsiness estimation system can be provided that is accurate across different objects and conditions.

[0072] As mentioned above, for vehicles, various cameras, sensors, or data sources can be used to obtain information about the current driving context. Similar sources can be used for other types of activities. For driving context, this data may include data such as road curvature, traffic volume or type, lane marking visibility, time of day, season, weather, lightning conditions, speed, construction, lane type, road surface type, wind speed, window status, radio status or volume, interior lighting, or any other environmental factors that may trigger detectable changes in object behavior, such as blinking. As noted, if a profile is not available for an object or the object cannot be identified, a generic driving context profile can be used, or a generic driving context profile can be selected at least in part based on determinable (and permissible) aspects of the object, such as age, gender, health status, or region that may influence driving behavior. At least in part because such data may be sensitive (or in some cases not permissible) to collect or use for decision-making, other methods can be used to attempt to predict a user's driving behavior, such as whether information about the driver's level of experience or familiarity with a particular vehicle is available. Any of this information can be used to improve the profile baseline used to normalize the data, minimizing the impact of variations between users or situations on the drowsiness or state estimation model. In at least some embodiments, multiple drowsiness estimation models can be trained on different profile baselines across all drowsiness levels, enabling the model to estimate drowsiness given a baseline profile at any drowsiness level. Robustness is achieved at least in part because driving context influences physiological behavior and driving performance, and these influences can vary further between subjects. For example, driving on congested roads may require more driver attention than driving on open roads, thus potentially increasing cognitive load, decreasing blink rate, increasing fixation / saccade fixation, and other potential variations. Factors such as road curvature, weather, route familiarity, and lighting conditions also influence physiological behavior, as well as driving patterns, such as how the driver adjusts the steering wheel and stays within the lane. For example, even for the same route under the same conditions, a user may exhibit different behavior if it is the first time driving the route compared to if the user frequently takes the route and is familiar with it, and may therefore tend to give less attention or be less alert.

[0073] In at least one embodiment, the context monitor 334 can be used to analyze available or received data 332 related to the driving context or other set of environmental conditions, such as Figure 3As shown. This can include, for example, analyzing input data to determine or infer the current driving context from a set of possible driving contexts. In other embodiments, this can include determining a set of contextual inputs or features that can be used to select an appropriate baseline from an appropriate model. This context monitor can run continuously, periodically, or when a significant change is detected in at least one contextual input, among other such options. In some embodiments, the context monitor can include a neural network trained to determine the driving context for a given set of inputs. In other embodiments, one or more algorithms or processes can be used to determine one or more contextual factors or values ​​from the obtained inputs. The driving context can then be used to determine, set, select, or compute an appropriate baseline or range for one or more behaviors or states to be monitored under the current conditions.

[0074] Similar to the user profiles discussed above, the system can attempt to identify an individual when they enter a vehicle or appear in a monitored location such as the driver's seat. If identified, the system can attempt to determine if the individual or object has an available profile, and if so, the system can utilize the data in that profile to normalize the user's current driving context and deploy an appropriate state estimation model. If the object does not have an existing and accessible profile, the system can attempt to generate or acquire one. In some embodiments, this may include monitoring or capturing information related to the user over a period of time to attempt to determine baseline information and to extract missing information from similar profiles.

[0075] In some embodiments, blink parameters can be provided in time increments, such as for the most recent minute. For example, this might include the number of blinks determined within that minute, along with individual or aggregated information about those blinks. The history of the determined numbers can be maintained in a history buffer, such as the last sixty minutes or the last sixty blink data periods, and then fed into the LSTM network as a feature vector of length 60 features. Any driving context or user profile information can also be provided to at least one LSTM network as a vector of similar length or otherwise. Maintaining a history of driving context or user physiological state over time can help make more accurate determinations based on blink or state behavior within the same time period. In at least some embodiments, different vectors can be provided for different types of contextual information. In at least some embodiments, the feature vector (or the composition of a given feature vector) can vary over time, at least in part, based on the type or amount of context or conditional data available at the time. These feature vectors used for user profile and driving context data can then be used to adjust thresholds or otherwise interpret expected changes (unrelated to drowsiness) to attempt to normalize the blink parameter data and detect blink behavior changes caused solely by changes in drowsiness.

[0076] Figure 5BAn example process 550 for improving the accuracy of state estimation by taking into account the current action context or other environmental or conditional information is illustrated. In this example, action-related contextual data 552 may be received from multiple sources. For driving behavior, this may include any data related to the driving context, such as image data captured from cameras on the vehicle, sensor data of the vehicle, vehicle operation information, environmental or location data from network connectivity services, and other options discussed and suggested elsewhere herein. In some embodiments, a superset of information may be received or obtained, and a relevant subset of that data may be determined or selected. The received data may be used to generate 554 one or more content feature vectors indicating the current action context. For example, the received data may be used to determine the values ​​of specific context parameters, such as location type, weather, brightness, congestion, etc., which may be used to construct the context feature vector. Any generated context feature vector, along with any user profile vector (if available) and a set of behavioral parameters measured by any appropriate sensor (e.g., a camera), and possibly including information such as steering wheel pattern, lane-keeping pattern, or EEG / ECG data, may be provided as input 556 to a time network or other state determination network or module. This temporal network can be used, at least in part, to estimate state values ​​based on this input, such as a person's level of drowsiness. Contextual feature vectors and / or user profile data (which may also be provided as one or more feature vectors) can be used to attempt to normalize behavioral parameters to address behavioral changes that may not be due to changes in the person's state, but may be due to changes in the current action context or person-specific behavioral patterns. The estimated state values ​​generated by this network can then be provided as a measure of the person's current state.

[0077] Once a state estimate is generated, information about that estimate can be used for various purposes. For example, for a vehicle driver's drowsy state, there may be a value or range of values ​​at the onset of drowsiness that would lead to certain actions, such as notifying the user, issuing an alarm, or displaying an icon indicating that drowsiness has been detected. In some embodiments, messages or alarms can be tailored to the user or driving context, as actions associated with someone driving on a city highway on a sunny day may differ from those associated with someone driving on a rural road in a snowstorm. Furthermore, different users may be more likely to take different actions or may dislike certain suggestions (e.g., drinking coffee or caffeine). In at least some embodiments, recommendations may also be made at least in part based on the user's history or preference data, such as the user having previously stopped at a coffee shop during a long drive or indicating that they do not drink caffeine. Other levels or ranges of drowsiness may exist that would lead the vehicle to take specific actions. This could include, for example, activating driver assistance processes or changing the amount of driver assistance provided. For example, if a particular state of drowsiness is determined to be the driver, lane maintenance and automatic braking could be increased. In some cases, the vehicle's control system 336 can be programmed to take drastic action in response to a high level of drowsiness indicated by the output drowsiness estimate 330, such as entering fully autonomous mode or pulling the vehicle over to the side of the road until the driver is no longer in a state of high drowsiness. In some situations, when a certain state of drowsiness is determined, it may be necessary to issue alerts periodically or take specific actions. These actions may vary depending on location, jurisdiction, vehicle, type of object, type of activity, or other such factors.

[0078] The different methods presented in this paper are lightweight enough to be executed in real time on different types of devices, such as personal computers, smart vehicles, or game consoles. Such processing can be performed using data captured or generated on that device or received from an external source, such as streaming data received over at least one network. This source can be any suitable source, such as a standalone client device, a streaming data provider, or a third-party data provider, among other such options. In some instances, the processing and / or use of this data can be performed by one of these other devices, systems, or entities and then provided to the client device (or another such receiver) for presentation or another such use.

[0079] As an example, Figure 6An example network configuration 600 is shown that can be used to provide, generate, modify, encode, and / or transmit data. In at least one embodiment, client device 602 can generate or receive data for a session using components of a state monitoring application 604 on client device 602 and data locally stored on the client device. In at least one embodiment, a state monitoring application 624 executing on a data or content server 620 (e.g., a cloud server or edge server) can initiate a session associated with at least client device 602, such as by utilizing a session manager and user data stored in a user database 634, and content can be determined or managed by a content manager 626. An estimator module 628 can attempt to estimate state data for one or more objects based on received data and can work with a context module 630 to receive context data determined based on the received data. This data or at least a portion of the state estimate can then be transmitted to client device 602 using an appropriate transmission manager 622 for transmission via download, streaming, or another such transmission channel. An encoder can be used to encode and / or compress this data before transmission to client device 602. In at least one embodiment, the data 632 may include any data related to state estimation, user behavior, or action context. In at least one embodiment, the client device 602 receiving the data may provide the data to a corresponding state monitor 604, which may also or alternatively include a state estimator 612 or a context determination module 614 for analyzing data received from the client device 602 or captured by the client. The decoder may also be used to decode the data received via network 640 for presentation or via actions of the client device 602, such as audio (e.g., alarms or sound notifications) notification content via display 606 or via at least one audio playback device 608 (e.g., speaker or headphones). In at least one embodiment, at least some of the data may already be stored on, generated on, or accessible by the client device 602, such that at least that portion of the data does not need to be transmitted via network 640, such as in cases where the data may have been previously downloaded or stored locally on a hard drive or optical disc. In at least one embodiment, a transport mechanism such as data streaming can be used to transmit the data from server 620, such as from profile database 632 to client device 602. In at least one embodiment, at least a portion of the data can be obtained, determined, or streamed from another source, such as a separate client device 650 or third-party service 660 that may also include functions for estimating state, determining user behavior patterns, or determining action context.In at least one embodiment, a portion of the function may be performed using multiple computing devices or multiple processors within one or more computing devices (such as a combination of CPU and GPU).

[0080] In this example, the client device may include any suitable computing device, such as a desktop computer, laptop computer, set-top box, streaming device, game console, smartphone, tablet computer, smart vehicle, robotic-assisted machine, VR headset, AR goggles, wearable computer, or smart TV. Each client device may be able to submit requests across at least one wired or wireless network (such as the Internet, Ethernet, Local Area Network (LAN), or cellular network, and other such options). In this example, these requests can be submitted to or received from an address associated with a cloud provider that can operate or control one or more electronic resources in the cloud provider environment, such as data centers or server clusters. In at least one embodiment, requests may be received or processed by at least one edge server located at the network edge and outside at least one security layer associated with the cloud provider environment. In this way, latency can be reduced by enabling client devices to interact with servers closer to the network, while also improving the security of resources in the cloud provider environment.

[0081] In at least one embodiment, such a system can be used to perform graphics rendering operations. In other embodiments, such a system can be used for other purposes, such as providing image or video content to test or validate autonomous machine applications, or for performing deep learning operations. In at least one embodiment, such a system can be implemented using edge devices, or it can be combined with one or more virtual machines (VMs). In at least one embodiment, such a system can be implemented at least partially in a data center or at least partially using cloud computing resources.

[0082] Reasoning and training logic

[0083] Figure 7A Inference and / or training logic 715 is shown for performing inference and / or training operations associated with one or more embodiments. The following is in conjunction with... Figure 7A and / or Figure 7B Provide details about reasoning and / or training logic 715.

[0084] In at least one embodiment, inference and / or training logic 715 may include, but is not limited to, code and / or data storage 701 for storing forward and / or output weights and / or input / output data, and / or other parameters configuring neurons or layers of a neural network trained for and / or used for inference in one or more embodiments. In at least one embodiment, training logic 715 may include or be coupled to code and / or data storage 701 for storing graph code or other software to control timing and / or sequence, wherein weight and / or other parameter information is loaded to configure logic, including integer and / or floating-point units (collectively referred to as Arithmetic Logic Units (ALUs)). In at least one embodiment, code (such as graph code) loads weight or other parameter information into the processor ALU based on the architecture of the neural network to which the code corresponds. In at least one embodiment, code and / or data storage 701 stores weight parameters and / or input / output data of each layer of a neural network trained or used in one or more embodiments during forward propagation of input / output data and / or weight parameters during training and / or inference using one or more embodiments. In at least one embodiment, any portion of the code and / or data storage 701 may be included within other on-chip or off-chip data storage, including the processor's L1, L2, or L3 cache or system memory.

[0085] In at least one embodiment, any portion of the code and / or data storage 701 may be internal or external to one or more processors or other hardware logic devices or circuits. In at least one embodiment, the code and / or data storage 701 may be a cache memory, dynamic random-addressable memory (“DRAM”), static random-addressable memory (“SRAM”), non-volatile memory (e.g., flash memory), or other storage. In at least one embodiment, the choice of whether the code and / or data storage 701 is internal or external to the processor, for example, or composed of DRAM, SRAM, flash memory, or some other storage type, may depend on the available on-chip or off-chip storage space, the latency requirements of the training and / or inference functions being performed, the batch size of the data used in the inference and / or training of the neural network, or some combination of these factors.

[0086] In at least one embodiment, the inference and / or training logic 715 may include, but is not limited to, code and / or data storage 705 to store backpropagation and / or output weights and / or input / output data neural networks corresponding to neurons or layers of a neural network trained and / or used for inference in one or more embodiments. In at least one embodiment, during training and / or inference using one or more embodiments, the code and / or data storage 705 stores weight parameters and / or input / output data for each layer of a neural network trained or used in one or more embodiments during backpropagation of input / output data and / or weight parameters. In at least one embodiment, the training logic 715 may include or be coupled to code and / or data storage 705 for storing graph code or other software to control timing and / or sequence, wherein weight and / or other parameter information is loaded to configure logic including integer and / or floating-point units (collectively referred to as Arithmetic Logic Units (ALUs)). In at least one embodiment, code (such as graph code) causes weight or other parameter information to be loaded into the processor ALU based on the architecture of the neural network corresponding to the code. In at least one embodiment, any portion of the code and / or data storage 705 may be included together with other on-chip or off-chip data storage, including the processor's L1, L2, or L3 cache or system memory. In at least one embodiment, any portion of the code and / or data storage 705 may be internal or external to one or more processors or other hardware logic devices or circuits. In at least one embodiment, the code and / or data storage 705 may be cache memory, DRAM, SRAM, non-volatile memory (e.g., flash memory), or other storage. In at least one embodiment, the choice between the code and / or data storage 705 being internal or external to the processor, for example, whether it consists of DRAM, SRAM, flash memory, or some other type of storage, depends on whether the available storage is on-chip or off-chip, the latency requirements of the training and / or inference functions being performed, the data batch size used in the inference and / or training of the neural network, or some combination of these factors.

[0087] In at least one embodiment, code and / or data storage 701 and code and / or data storage 705 may be separate storage structures. In at least one embodiment, code and / or data storage 701 and code and / or data storage 705 may be the same storage structure. In at least one embodiment, code and / or data storage 701 and code and / or data storage 705 may have partially identical storage structures and partially separate storage structures. In at least one embodiment, any portion of code and / or data storage 701 and code and / or data storage 705 may be included with other on-chip or off-chip data storage, including the processor's L1, L2, or L3 cache or system memory.

[0088] In at least one embodiment, the inference and / or training logic 715 may include, but is not limited to, one or more arithmetic logic units (“ALUs”) 710 (including integer and / or floating-point units) for performing logical and / or mathematical operations at least in part based on or instructed by training and / or inference code (e.g., graph code), the results of which may produce activations (e.g., output values ​​from layers or neurons within a neural network) stored in activation storage 720, which are functions of input / output and / or weight parameter data stored in code and / or data storage 701 and / or code and / or data storage 705. In at least one embodiment, activation is activated in response to execution instructions or other code, and linear algebraic and / or matrix-based mathematical generation performed by ALU 710 is stored in activation storage 720. The weight values ​​stored in code and / or data storage 705 and / or code and / or data storage 701 are used as operands with other values, such as bias values, gradient information, momentum values, or other parameters or hyperparameters. Any or all of these can be stored in code and / or data storage 705 or code and / or data storage 701 or other on-chip or off-chip storage.

[0089] In at least one embodiment, one or more processors or other hardware logic devices or circuits include one or more ALUs 710, while in another embodiment, one or more ALUs 710 may be located outside the processor or other hardware logic device or the circuitry using them (e.g., a coprocessor). In at least one embodiment, one or more ALUs 710 may be included within an execution unit of a processor, or otherwise included in a group of ALUs accessible by the execution unit of the processor, which may be within the same processor or distributed among different processors of different types (e.g., a central processing unit, a graphics processing unit, a fixed-function unit, etc.). In at least one embodiment, code and / or data storage 701, code and / or data storage 705, and activation storage 720 may be the same processor or other hardware logic device or circuitry, while in another embodiment, they may be in different processors or other hardware logic devices or circuitry, or some combination of the same and different processors or other hardware logic devices or circuitry. In at least one embodiment, any portion of activation storage 720 may be included together with other on-chip or off-chip data storage, including the processor's L1, L2, or L3 cache or system memory. Furthermore, inference and / or training code may be stored together with other code accessible to the processor or other hardware logic or circuitry, and may be retrieved and / or processed using the processor’s fetch, decode, schedule, execute, exit, and / or other logic circuitry.

[0090] In at least one embodiment, the active memory 720 may be a cache memory, DRAM, SRAM, non-volatile memory (e.g., flash memory), or other memory. In at least one embodiment, the active memory 720 may be wholly or partially located inside or outside one or more processors or other logic circuits. In at least one embodiment, the choice of whether the active memory 720 is internal to or external to the processor may depend on the available on-chip or off-chip storage, the latency requirements for training and / or inference functions, the batch size of data used in inference and / or training the neural network, or some combination of these factors. For example, it may include DRAM, SRAM, flash memory, or other memory types. In at least one embodiment, Figure 7A The inference and / or training logic 715 shown can be used in conjunction with an application-specific integrated circuit (“ASIC”), such as those from Google. Processing unit, from Graphcore TM Inference processing units (IPUs) or from Intel Corp. (e.g., "Lake Crest") processor. In at least one embodiment, Figure 7AThe inference and / or training logic 715 shown can be used in conjunction with central processing unit (“CPU”) hardware, graphics processing unit (“GPU”) hardware, or other hardware such as field programmable gate array (“FPGA”)).

[0091] Figure 7B Inference and / or training logic 715 according to at least one or more embodiments is illustrated. In at least one embodiment, the inference and / or training logic 715 may include, but is not limited to, hardware logic, wherein computational resources are dedicated or otherwise uniquely used in conjunction with weight values ​​or other information corresponding to one or more layers of neurons within a neural network. In at least one embodiment, Figure 7B The inference and / or training logic 715 shown can be used in conjunction with an application-specific integrated circuit (ASIC), such as those from Google. Processing unit, from Graphcore TM Inference processing units (IPUs) or from Intel Corp. (e.g., "Lake Crest") processor. In at least one embodiment, Figure 7B The inference and / or training logic 715 shown can be used in conjunction with central processing unit (CPU) hardware, graphics processing unit (GPU) hardware, or other hardware (e.g., field-programmable gate array (FPGA)). In at least one embodiment, the inference and / or training logic 715 includes, but is not limited to, code and / or data storage 701 and code and / or data storage 705, which can be used to store code (e.g., graph code), weight values, and / or other information, including bias values, gradient information, momentum values, and / or other parameter or hyperparameter information. Figure 7B In at least one embodiment shown, each of code and / or data storage 701 and code and / or data storage 705 is associated with dedicated computing resources (e.g., computing hardware 702 and computing hardware 706), respectively. In at least one embodiment, each of computing hardware 702 and computing hardware 706 includes one or more ALUs that perform mathematical functions (e.g., linear algebraic functions) only on the information stored in code and / or data storage 701 and code and / or data storage 705, respectively, and the results of the function execution are stored in activation storage 720.

[0092] In at least one embodiment, each of the code and / or data storage 701 and 705 and the corresponding computing hardware 702 and 706 corresponds to a different layer of the neural network, such that activation obtained from one “store / computation pair 701 / 702” of the code and / or data storage 701 and computing hardware 702 provides input as input to the next “store / computation pair 705 / 706” of the code and / or data storage 705 and computing hardware 706, in order to reflect the conceptual organization of the neural network. In at least one embodiment, each store / computation pair 701 / 702 and 705 / 706 may correspond to more than one neural network layer. In at least one embodiment, additional store / computation pairs (not shown) may be included in the inference and / or training logic 715 after or in parallel with the store / computation pairs 701 / 702 and 705 / 706.

[0093] Data Center

[0094] Figure 8 An example data center 800 that can be used with at least one embodiment is shown. In at least one embodiment, the data center 800 includes a data center infrastructure layer 810, a framework layer 820, a software layer 830, and an application layer 840.

[0095] In at least one embodiment, such as Figure 8 As shown, the data center infrastructure layer 810 may include a resource coordinator 812, packet computing resources 814, and node computing resources (“nodes CR”) 816 (1)-816 (N), where “N” represents any positive integer. In at least one embodiment, nodes CR 816 (1)-816 (N) may include, but are not limited to, any number of central processing units (“CPUs”) or other processors (including accelerators, field-programmable gate arrays (FPGAs), graphics processors, etc.), memory devices (e.g., dynamic read-only memory), storage devices (e.g., solid-state drives or disk drives), network input / output (“NW I / O”) devices, network switches, virtual machines (“VMs”), power modules, and cooling modules, etc. In at least one embodiment, one or more nodes CR 816 (1)-816 (N) may be servers having one or more of the aforementioned computing resources.

[0096] In at least one embodiment, the grouped computing resource 814 may include individual groups (not shown) of node CRs housed within one or more racks, or a plurality of racks (also not shown) housed within data centers in various geographic locations. The individual groups of node CRs within the grouped computing resource 814 may include computing, networking, memory, or storage resources that can be configured or allocated to support groups of one or more workloads. In at least one embodiment, several node CRs, including CPUs or processors, may be grouped within one or more racks to provide computing resources to support one or more workloads. In at least one embodiment, the one or more racks may also include any number of power modules, cooling modules, and network switches, in any combination.

[0097] In at least one embodiment, resource coordinator 812 may configure or otherwise control one or more nodes CR816(1)-816(N) and / or grouped computing resources 814. In at least one embodiment, resource coordinator 812 may include a software design infrastructure (“SDI”) management entity for data center 800. In at least one embodiment, resource coordinator may include hardware, software, or some combination thereof.

[0098] In at least one embodiment, such as Figure 8 As shown, framework layer 820 includes a job scheduler 822, a configuration manager 824, a resource manager 826, and a distributed file system 828. In at least one embodiment, framework layer 820 may include a framework of software 832 supporting software layer 830 and / or one or more applications 842 supporting application layer 840. In at least one embodiment, software 832 or application 842 may respectively include web-based service software or applications, such as services or applications provided by Amazon Web Services, Google Cloud, and Microsoft Azure. In at least one embodiment, framework layer 820 may be, but is not limited to, a free and open-source software web application framework, such as Apache Spark, which can utilize distributed file system 828 for large-scale data processing (e.g., "big data"). TM(Hereinafter referred to as "Spark"). In at least one embodiment, the job scheduler 832 may include a Spark driver to facilitate the scheduling of workloads supported by various layers of the data center 800. In at least one embodiment, the configuration manager 824 may be able to configure different layers, such as the software layer 830 and the framework layer 820, which includes Spark and a distributed file system 828 for supporting large-scale data processing. In at least one embodiment, the resource manager 826 is able to manage cluster or group computing resources mapped to or allocated to support the distributed file system 828 and the job scheduler 822. In at least one embodiment, the cluster or group computing resources may include group computing resources 814 on the data center infrastructure layer 810. In at least one embodiment, the resource manager 826 may coordinate with the resource coordinator 812 to manage these mapped or allocated computing resources.

[0099] In at least one embodiment, the software 832 included in the software layer 830 may include software used by at least a portion of the nodes CR816(1)-816(N), the grouped computing resources 814, and / or the distributed file system 828 of the framework layer 820. One or more types of software may include, but are not limited to, Internet web page search software, email virus scanning software, database software, and streaming video content software.

[0100] In at least one embodiment, one or more applications 842 included in application layer 840 may include one or more types of applications used by at least a portion of nodes CR816(1)-816(N), grouped computing resources 814, and / or the distributed file system 828 of framework layer 820. One or more types of applications may include, but are not limited to, any number of genomics applications, cognitive computing and machine learning applications, including training or inference software, machine learning framework software (e.g., PyTorch, TensorFlow, Caffe, etc.), or other machine learning applications used in conjunction with one or more embodiments.

[0101] In at least one embodiment, any of the configuration manager 824, resource manager 826, and resource coordinator 812 can perform any number and type of self-modification actions based on any amount and type of data acquired in any technically feasible manner. In at least one embodiment, self-modification actions can mitigate potentially poor configuration decisions by data center operators of data center 800 and can prevent underutilization and / or poor performance of the data center.

[0102] In at least one embodiment, data center 800 may include tools, services, software, or other resources to train one or more machine learning models or to use one or more machine learning models to predict or infer information according to one or more embodiments described herein. For example, in at least one embodiment, a machine learning model can be trained by calculating weight parameters based on a neural network architecture using the software and computing resources described above with respect to data center 800. In at least one embodiment, information can be inferred or predicted using trained machine learning models corresponding to one or more neural networks using the resources described above with respect to data center 800 by using weight parameters calculated through one or more training techniques described herein.

[0103] In at least one embodiment, the data center may use a CPU, application-specific integrated circuit (ASIC), GPU, FPGA, or other hardware to utilize the aforementioned resources to perform training and / or inference. Furthermore, one or more of the aforementioned software and / or hardware resources may be configured as a service to allow a user to train or perform information inference, such as image recognition, speech recognition, or other artificial intelligence services.

[0104] Inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. The following is combined with... Figure 7A and / or Figure 7B Details regarding inference and / or training logic 715 are provided. In at least one embodiment, inference and / or training logic 715 may be used in System Figure 8 for inference or prediction operations based at least in part on weight parameters computed using neural network training operations, neural network functions and / or architectures, or neural network use cases described herein.

[0105] These components can be used to synthesize a compositional image into a single representation using parameters determined from one or more quality assessment values.

[0106] Computer System

[0107] Figure 9This is a block diagram illustrating an exemplary computer system according to at least one embodiment. The exemplary computer system may be a system of interconnected devices and components, a system-on-a-chip (SoC), or some combination thereof formed with a processor, which may include an execution unit to execute instructions. In at least one embodiment, according to this disclosure, such as the embodiments described herein, computer system 900 may include, but is not limited to, components such as processor 902, whose execution unit includes logic to execute algorithms for process data. In at least one embodiment, computer system 900 may include a processor, such as one available from Intel Corporation of Santa Clara, California. Processor family, Xeon TM , XScale TM and / or StrongARM TM , Core TM or Nervana TM A microprocessor may be used, although other systems (including PCs, engineering workstations, set-top boxes, etc.) with other microprocessors may also be used. In at least one embodiment, computer system 900 may execute a version of the Windows operating system available from Microsoft Corporation of Redmond, Washington, although other operating systems (such as UNIX and Linux), embedded software, and / or graphical user interfaces may also be used.

[0108] The embodiments can be used in other devices, such as handheld devices and embedded applications. Some examples of handheld devices include cellular phones, Internet Protocol (IP) devices, digital cameras, personal digital assistants (“PDAs”), and handheld PCs. In at least one embodiment, the embedded application may include a microcontroller, a digital signal processor (“DSP”), a system-on-a-chip (SoC), a network computer (“NetPC”), a set-top box, a network hub, a wide area network (“WAN”) switch, or any other system that can execute one or more instructions according to at least one embodiment.

[0109] In at least one embodiment, the computer system 900 may include, but is not limited to, a processor 902, which may include, but is not limited to, one or more execution units 908, to perform machine learning model training and / or inference according to the techniques described herein. In at least one embodiment, the computer system 900 is a single-processor desktop or server system, but in another embodiment, the computer system 900 may be a multiprocessor system. In at least one embodiment, the processor 902 may include, but is not limited to, a Complex Instruction Set Computer (“CISC”) microprocessor, a Reduced Instruction Set Computing (“RISC”) microprocessor, a Very Long Instruction Word (“VLIW”) microprocessor, a processor implementing instruction set combination, or any other processor device, such as a digital signal processor. In at least one embodiment, the processor 902 may be coupled to a processor bus 910, which can transmit data signals between the processor 902 and other components in the computer system 900.

[0110] In at least one embodiment, processor 902 may include, but is not limited to, a Level 1 (“L1”) internal cache memory (“cache”) 904. In at least one embodiment, processor 902 may have a single internal cache or multiple levels of internal cache. In at least one embodiment, the cache memory may reside externally to processor 902. Depending on specific implementation and requirements, other embodiments may also include a combination of internal and external caches. In at least one embodiment, register file 906 may store different types of data in various registers, including but not limited to integer registers, floating-point registers, status registers, and instruction pointer registers.

[0111] In at least one embodiment, an execution unit 908, including but not limited to logic for performing integer and floating-point operations, is also located within the processor 902. In at least one embodiment, the processor 902 may further include a microcode (“ucode”) read-only memory (“ROM”) for storing microcode of certain macro instructions. In at least one embodiment, the execution unit 908 may include logic for processing a packaged instruction set 909. In at least one embodiment, by including the packaged instruction set 909 in the instruction set of the general-purpose processor 902, along with the associated circuitry for executing the instructions, packaged data in the general-purpose processor 902 can be used to perform operations used by many multimedia applications. In one or more embodiments, many multimedia applications can be executed more quickly and efficiently by using the full width of the processor's data bus to perform operations on the packaged data, which may eliminate the need to transfer smaller data units on the processor's data bus to perform one or more operations on one data element at a time.

[0112] In at least one embodiment, execution unit 908 may also be used in a microcontroller, embedded processor, graphics device, DSP, and other types of logic circuitry. In at least one embodiment, computer system 900 may include, but is not limited to, memory 920. In at least one embodiment, memory 920 may be implemented as a dynamic random access memory (“DRAM”) device, a static random access memory (“SRAM”) device, a flash memory device, or another storage device. In at least one embodiment, memory 920 may store instructions 919 and / or data 921 represented by data signals that can be executed by processor 902.

[0113] In at least one embodiment, the system logic chip may be coupled to a processor bus 910 and a memory 920. In at least one embodiment, the system logic chip may include, but is not limited to, a memory controller hub (“MCH”) 916, and the processor 902 may communicate with the MCH 916 via the processor bus 910. In at least one embodiment, the MCH 916 may provide a high-bandwidth memory path 918 to the memory 920 for instruction and data storage, as well as for storage of graphics commands, data, and textures. In at least one embodiment, the MCH 916 may initiate data signals between the processor 902, the memory 920, and other components in the computer system 900, and bridge data signals between the processor bus 910, the memory 920, and the system I / O interface 922. In at least one embodiment, the system logic chip may provide a graphics port for coupling to a graphics controller. In at least one embodiment, MCH 916 can be coupled to memory 920 via high-bandwidth memory path 918, and graphics / video card 912 can be coupled to MCH 916 via Accelerated Graphics Port (“AGP”) interconnect 914.

[0114] In at least one embodiment, computer system 900 may use system I / O interface 922, i.e., a proprietary hub interface bus, to couple MCH 916 to I / O controller hub (“ICH”) 930. In at least one embodiment, ICH 930 may provide direct connectivity to certain I / O devices via a local I / O bus. In at least one embodiment, the local I / O bus may include, but is not limited to, a high-speed I / O bus for connecting peripheral devices to memory 920, chipset, and processor 902. Examples may include, but are not limited to, audio controller 929, firmware hub (“Flash BIOS”) 928, wireless transceiver 926, data storage 924, a conventional I / O controller 923 including user input and keyboard interfaces, serial expansion port 927 (e.g., a Universal Serial Bus (USB) port), and network controller 934. Data storage 924 may include hard disk drives, floppy disk drives, CD-ROM devices, flash memory devices, or other mass storage devices.

[0115] In at least one embodiment, Figure 9 A system including interconnected hardware devices or "chips" is shown, while in other embodiments, Figure 9 A system-on-a-chip (“SoC”) may be shown. In at least one embodiment, Figure 9 The devices shown can be interconnected with proprietary interconnects, standardized interconnects (e.g., PCIe), or some combination thereof. In at least one embodiment, one or more components of the computer system 900 are interconnected using a Compute Fast Link (CXL) interconnect.

[0116] The inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. The following is in conjunction with... Figure 7A 7B provides details regarding the inference and / or training logic 715. In at least one embodiment, the inference and / or training logic 715 can be configured in the system. Figure 9 The operation is used to infer or predict based at least in part on weight parameters calculated using the neural network training operations, neural network functions and / or architecture or neural network usage described herein.

[0117] These components can be used to synthesize a compositional image into a single representation using parameters determined from one or more quality assessment values.

[0118] Figure 10This is a block diagram illustrating an electronic device 1000 utilizing a processor 1010 according to at least one embodiment. In at least one embodiment, the electronic device 1000 may be, for example, but not limited to, a laptop, tower server, rack server, blade server, laptop computer, desktop computer, tablet computer, mobile device, telephone, embedded computer, or any other suitable electronic device.

[0119] In at least one embodiment, system 1000 may include, but is not limited to, processor 1010, which is communicatively coupled to any suitable number or type of components, peripherals, modules, or devices. In at least one embodiment, processor 1010 is coupled using a bus or interface (such as an I2C bus), system management bus (“SMBus”), low pin count (LPC) bus, serial peripheral interface (“SPI”), high definition audio (“HDA”) bus, serial advanced technology accessory (“SATA”) bus, universal serial bus (“USB”) (versions 1, 2, 3), or universal asynchronous receiver / transmitter (“UART”) bus. In at least one embodiment, Figure 10 One embodiment is shown that includes interconnected hardware devices or "chips," while in other embodiments, Figure 10 An exemplary system-on-a-chip (“SoC”) may be illustrated. In at least one embodiment, Figure 10 The devices shown can be interconnected with dedicated interconnects, standardized interconnects (e.g., PCIe), or some combination thereof. In at least one embodiment, a compute fast link (CXL) interconnect is used for interconnection. Figure 10 One or more components.

[0120] In at least one embodiment, Figure 10It may include a display 1024, a touch screen 1025, a touchpad 1030, a near field communication unit (“NFC”) 1045, a sensor hub 1040, a thermal sensor 1046, a fast chipset (“EC”) 1035, a trusted platform module (“TPM”) 1038, a BIOS / firmware / flash memory (“BIOS, FW flash”) 1022, a DSP 1060, a drive 1020 (such as a solid-state drive (“SSD”) or a hard disk drive (“HDD”)), a wireless local area network unit (“WLAN”) 1050, a Bluetooth unit 1052, a wireless wide area network unit (“WWAN”) 1056, a global positioning system (GPS) 1055, a camera (“USB 3.0 camera”) 1054 (e.g., a USB 3.0 camera), and / or a low-power double data rate (“LPDDR”) memory unit (“LPDDR3”) 1015 implemented therein, such as the LPDDR3 standard. These components can each be implemented in any suitable manner.

[0121] In at least one embodiment, other components may be communicatively coupled to processor 1010 via the components discussed above. In at least one embodiment, accelerometer 1041, ambient light sensor (“ALS”) 1042, compass 1043, and gyroscope 1044 may be communicatively coupled to sensor hub 1040. In at least one embodiment, thermal sensor 1039, fan 1037, keyboard 1046, and touchpad 1030 may be communicatively coupled to EC 1035. In at least one embodiment, speaker 1063, headset 1064, and microphone (“mic”) 1065 may be communicatively coupled to audio unit (“audio codec and Class D amplifier”) 1062, which in turn may be communicatively coupled to DSP 1060. In at least one embodiment, audio unit 1064 may include (e.g., but not limited to) an audio encoder / decoder (“codec”) and a Class D amplifier. In at least one embodiment, SIM card (“SIM”) 1057 may be communicatively coupled to WWAN unit 1056. In at least one embodiment, components such as WLAN unit 1050, Bluetooth unit 1052, and WWAN unit 1056 may be implemented in a next-generation form factor (“NGFF”).

[0122] The inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. The following is in conjunction with... Figure 7A and / or Figure 7B Details are provided regarding the inference and / or training logic 715. In at least one embodiment, the inference and / or training logic 715 may be... Figure 10The system is used to infer or predict operations based at least in part on weight parameters calculated using neural network training operations, neural network functions and / or architecture or neural network usage as described herein.

[0123] These components can be used to synthesize a compositional image into a single representation using parameters determined from one or more quality assessment values.

[0124] Figure 11 This is a block diagram of a processing system according to at least one embodiment. In at least one embodiment, system 1100 includes one or more processors 1102 and one or more graphics processors 1108, and may be a single-processor desktop system, a multi-processor workstation system, or a server system having a large number of processors 1102 or processor cores 1107. In at least one embodiment, system 1100 is a processing platform incorporated within a system-on-a-chip (SoC) integrated circuit for use in mobile, handheld, or embedded devices.

[0125] In at least one embodiment, system 1100 may include or be integrated into a game console (including game and media consoles), mobile game console, handheld game console, or online game console in a server-based gaming platform. In at least one embodiment, system 1100 is a mobile phone, smartphone, tablet computing device, or mobile internet device. In at least one embodiment, processing system 1100 may also include a wearable device (such as a smartwatch, smart glasses, augmented reality, or virtual reality device), coupled to or integrated within the wearable device. In at least one embodiment, processing system 1100 is a television or set-top box device having one or more processors 1102 and a graphical interface generated by one or more graphics processors 1108.

[0126] In at least one embodiment, one or more processors 1102 each include one or more processor cores 1107 for processing instructions that, when executed, perform operations for system and user software. In at least one embodiment, each of the one or more processor cores 1107 is configured to process a particular instruction set 1109. In at least one embodiment, the instruction set 1109 may facilitate Complex Instruction Set Computing (CISC), Reduced Instruction Set Computing (RISC), or computation via Very Long Instruction Word (VLIW). In at least one embodiment, the processor cores 1107 may each process a different instruction set 1109, which may include instructions that facilitate the emulation of other instruction sets. In at least one embodiment, the processor cores 1107 may also include other processing devices, such as digital signal processors (DSPs).

[0127] In at least one embodiment, processor 1102 includes cache memory 1104. In at least one embodiment, processor 1102 may have a single internal cache or multi-level internal caches. In at least one embodiment, the cache memory is shared among different components of processor 1102. In at least one embodiment, processor 1102 also uses an external cache (e.g., a Level 3 (L3) cache or a last-level cache (LLC)) (not shown), which can be shared among processor cores 1107 using known cache coherence techniques. In at least one embodiment, register file 1106 is additionally included in processor 1102, which may include different types of registers (e.g., integer registers, floating-point registers, status registers, and instruction pointer registers) for storing different types of data. In at least one embodiment, register file 1106 may include general-purpose registers or other registers.

[0128] In at least one embodiment, one or more processors 1102 are coupled to one or more interface buses 1110 to transmit communication signals, such as address, data, or control signals, between the processors 1102 and other components in the system 1100. In at least one embodiment, the interface bus 1110 may be a processor bus, such as a version of the Direct Media Interface (DMI) bus. In at least one embodiment, the interface 1110 is not limited to the DMI bus and may include one or more peripheral component interconnect buses (e.g., PCI, PCI Express), memory buses, or other types of interface buses. In at least one embodiment, the processor 1102 includes an integrated memory controller 1116 and a platform controller hub 1130. In at least one embodiment, the memory controller 1116 facilitates communication between memory devices and other components of the system 1100, while the platform controller hub (PCH) 1130 provides connectivity to I / O devices via a local I / O bus.

[0129] In at least one embodiment, memory device 1120 may be a dynamic random access memory (DRAM) device, a static random access memory (SRAM) device, a flash memory device, a phase-change memory device, or some other memory device with performance suitable for use as process memory. In at least one embodiment, memory device 1120 may operate as system memory of system 1100 to store data 1122 and instructions 1121 for use when one or more processors 1102 execute an application or process. In at least one embodiment, memory controller 1116 is also coupled to an optional external graphics processor 1112, which may communicate with one or more graphics processors 1108 of processor 1102 to perform graphics and media operations. In at least one embodiment, display device 1111 may be connected to (one or more) processors 1102. In at least one embodiment, display device 1111 may include one or more internal display devices, such as in a mobile electronic device or laptop device attached via a display interface (e.g., DisplayPort, etc.) or an external display device. In at least one embodiment, the display device 1111 may include a head-mounted display (HMD), such as a stereoscopic display device for virtual reality (VR) applications or augmented reality (AR) applications.

[0130] In at least one embodiment, the platform controller hub 1130 enables peripheral devices to connect to the memory device 1120 and the processor 1102 via a high-speed I / O bus. In at least one embodiment, the I / O peripheral devices include, but are not limited to, an audio controller 1146, a network controller 1134, a firmware interface 1128, a wireless transceiver 1126, a touch sensor 1125, and a data storage device 1124 (e.g., a hard disk drive, flash memory, etc.). In at least one embodiment, the data storage device 1124 may be connected via a storage interface (e.g., SATA) or via a peripheral bus (such as a peripheral component interconnect bus (e.g., PCI, PCI Express)). In at least one embodiment, the touch sensor 1125 may include a touchscreen sensor, a pressure sensor, or a fingerprint sensor. In at least one embodiment, the wireless transceiver 1126 may be a Wi-Fi transceiver, a Bluetooth transceiver, or a mobile network transceiver, such as a 3G, 4G, or LTE transceiver. In at least one embodiment, the firmware interface 1128 enables communication with the system firmware and may be, for example, a Unified Extensible Firmware Interface (UEFI). In at least one embodiment, the network controller 1134 can implement a network connection to a wired network. In at least one embodiment, a high-performance network controller (not shown) is coupled to an interface bus 1110.

[0131] In at least one embodiment, the audio controller 1146 is a multi-channel high-definition audio controller. In at least one embodiment, the system 1100 includes an optional legacy I / O controller 1140 for coupling legacy (e.g., Personal System 2 (PS / 2)) devices to the system. In at least one embodiment, the platform controller hub 1130 may also be connected to one or more Universal Serial Bus (USB) controllers 1142 to connect input devices, such as a keyboard and mouse combination 1143, a camera 1144, or other USB input devices.

[0132] In at least one embodiment, instances of the memory controller 1116 and platform controller hub 1130 may be integrated into a discrete external graphics processor (such as external graphics processor 1112). In at least one embodiment, the platform controller hub 1130 and / or the memory controller 1116 may be external to one or more processors 1102. For example, in at least one embodiment, system 1100 may include an external memory controller 1116 and platform controller hub 1130, which may be configured as a system chipset-based memory controller hub and peripheral controller hub to communicate with processor 1102.

[0133] The inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. The following is in conjunction with... Figure 7A 7B and / or 7B provide details regarding the inference and / or training logic 715. In at least one embodiment, some or all of the inference and / or training logic 715 may be incorporated into the graphics processor 1500. For example, in at least one embodiment, the training and / or inference techniques described herein may use one or more ALUs implemented in the graphics processor. Furthermore, in at least one embodiment, the inference and / or training operations described herein may use, in addition to Figure 7A Alternatively, it may be accomplished using logic other than that shown in 7B. In at least one embodiment, the weight parameters may be stored in on-chip or off-chip memory and / or registers (shown or not shown), which configure the graphics processor's ALU for executing one or more machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0134] These components can be used to synthesize a compositional image into a single representation using parameters determined from one or more quality assessment values.

[0135] Figure 12This is a block diagram of a processor 1200 according to at least one embodiment, the processor having one or more processor cores 1202A-1202N, an integrated memory controller 1214, and an integrated graphics processor 1208. In at least one embodiment, the processor 1200 may include up to and including additional cores 1202N, indicated by dashed boxes. In at least one embodiment, each of the processor cores 1202A-1202N includes one or more internal cache units 1204A-1204N. In at least one embodiment, each processor core may also access one or more shared cache units 1206.

[0136] In at least one embodiment, internal cache units 1204A-1204N and shared cache unit 1206 represent a cache memory hierarchy within processor 1200. In at least one embodiment, cache memory units 1204A-1204N may include at least one level of instruction and data cache memory within each processor core, and one or more levels of shared intermediate cache memory, such as Level 2 (L2), Level 3 (L3), Level 4 (L4), or other levels of cache, wherein the highest level of cache preceding external memory is classified as LLC. In at least one embodiment, cache coherence logic maintains coherence between different cache units 1206 and 1204A-1204N.

[0137] In at least one embodiment, the processor 1200 may further include a collection of one or more bus controller units 1216 and system agent cores 1210. In at least one embodiment, one or more bus controller units 1216 manage a set of peripheral buses, such as one or more PCI or PCI Fast buses. In at least one embodiment, the system agent core 1210 provides management functions for different processor components. In at least one embodiment, the system agent core 1210 includes one or more integrated memory controllers 1214 for managing access to different external memory devices (not shown).

[0138] In at least one embodiment, one or more of the processor cores 1202A-1202N include support for simultaneous multithreading. In at least one embodiment, the system agent core 1210 includes components for coordinating and operating the cores 1202A-1202N during multithreaded processing. In at least one embodiment, the system agent core 1210 may additionally include a power control unit (PCU) including logic and components for regulating one or more power states of the processor cores 1202A-1202N and the graphics processor 1208.

[0139] In at least one embodiment, processor 1200 further includes a graphics processor 1208 for performing graphics processing operations. In at least one embodiment, graphics processor 1208 is coupled to a shared cache unit 1206 and a system proxy core 1210 (including one or more integrated memory controllers 1214). In at least one embodiment, system proxy core 1210 further includes a display controller 1211 for driving graphics processor output to one or more coupled displays. In at least one embodiment, display controller 1211 may also be a separate module coupled to graphics processor 1208 via at least one interconnect or may be integrated within graphics processor 1208.

[0140] In at least one embodiment, the ring-based interconnect unit 1212 is used to couple internal components of the processor 1200. In at least one embodiment, alternative interconnect units, such as point-to-point interconnects, switched interconnects, or other technologies, may be used. In at least one embodiment, the graphics processor 1208 is coupled to the ring interconnect 1212 via I / O link 1213.

[0141] In at least one embodiment, I / O link 1213 represents at least one of a variety of I / O interconnects, including on-package I / O interconnects that facilitate communication between different processor components and high-performance embedded memory modules 1218 (such as eDRAM modules). In at least one embodiment, each of the processor cores 1202A-1202N and the graphics processor 1208 uses the embedded memory module 1218 as a shared final-level cache.

[0142] In at least one embodiment, processor cores 1202A-1202N are homogeneous cores executing a common instruction set architecture. In at least one embodiment, processor cores 1202A-1202N are heterogeneous in terms of instruction set architecture (ISA), wherein one or more processor cores 1202A-1202N execute a common instruction set, while one or more other cores of processor cores 1202A-1202N execute a common instruction set or a subset of a different instruction set. In at least one embodiment, processor cores 1202A-1202N are heterogeneous in terms of microarchitecture, wherein one or more cores with relatively high power consumption are coupled to one or more power cores with lower power consumption. In at least one embodiment, processor 1200 can be implemented on one or more chips or as a SoC integrated circuit.

[0143] The inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. The following is in conjunction with... Figure 7A and / or Figure 7B Details regarding the inference and / or training logic 715 are provided. In at least one embodiment, some or all of the inference and / or training logic 715 may be incorporated into the processor 1200. For example, in at least one embodiment, the training and / or inference techniques described herein may be used in the graphics processor 1512, (one or more) graphics cores 1202A-1202N, or... Figure 12 One or more ALUs embodied in other components of the graphics processor 1200. Furthermore, in at least one embodiment, the inference and / or training operations described herein can be performed using logic other than that shown in Figures 7A or 7B. In at least one embodiment, weight parameters can be stored in on-chip or off-chip memory and / or registers (shown or not shown), which configure the ALUs of the graphics processor 1200 to execute one or more machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0144] These components can be used to synthesize a compositional image into a single representation using parameters determined from one or more quality assessment values.

[0145] Virtualization computing platform

[0146] Figure 13 This is an example data flow diagram of process 1300 for generating and deploying an image processing and inference pipeline according to at least one embodiment. In at least one embodiment, process 1300 can be deployed for use with imaging devices, processing devices, and / or other device types at one or more facilities 1302. Process 1300 can be executed within training system 1304 and / or deployment system 1306. In at least one embodiment, training system 1304 can be used to train, deploy, and implement machine learning models (e.g., neural networks, object detection algorithms, computer vision algorithms, etc.) for use in deployment system 1306. In at least one embodiment, deployment system 1306 can be configured to offload processing and computing resources between distributed computing environments to reduce infrastructure requirements at facility 1302. In at least one embodiment, one or more applications in the pipeline can use or invoke services of deployment system 1306 (e.g., inference, visualization, computation, AI, etc.) during application execution.

[0147] In at least one embodiment, some applications in the advanced processing and inference pipeline may use machine learning models or other AI to perform one or more processing steps. In at least one embodiment, the machine learning model may be trained at facility 1302 using data 1308 (such as imaging data) generated at facility 1302 (and stored on one or more Picture Archiving and Communication System (PACS) servers at facility 1302), or may be trained using imaging or sorting data 1308 or a combination thereof from another (one or more) facility. In at least one embodiment, training system 1304 may be used to provide applications, services, and / or other resources for generating jobs, deployable machine learning models, for deployment system 1306.

[0148] In at least one embodiment, the model registry 1324 may be supported by an object storage that supports versioning and object metadata. In at least one embodiment, the object storage may be, for example, cloud storage (e.g., Figure 14 The cloud platform (1426)-compatible application programming interface (API) is accessed from within the cloud platform. In at least one embodiment, machine learning models in the model registry 1324 can be uploaded, listed, modified, or deleted by the developer or partner of the system interacting with the API. In at least one embodiment, the API can provide access to methods that allow a user with appropriate credentials to associate a model with an application, enabling the model to be executed as part of the containerized instantiation of the application.

[0149] In at least one embodiment, training pipeline 1404 ( Figure 14The scenario may include facility 1302 training its own machine learning model or having an existing machine learning model that needs to be optimized or updated. In at least one embodiment, imaging data 1308 generated by one or more imaging devices, sequencing devices, and / or other device types may be received. In at least one embodiment, once the imaging data 1308 is received, AI-assisted annotation 1310 may be used to help generate annotations corresponding to the imaging data 1308 for use as ground-based data for machine learning models. In at least one embodiment, AI-assisted annotation 1310 may include one or more machine learning models (e.g., convolutional neural networks (CNNs)) that can be trained to generate annotations corresponding to certain types of imaging data 1308 (e.g., from certain devices). In at least one embodiment, AI-assisted annotation 1310 may then be used directly or may be adjusted or fine-tuned using annotation tools to generate ground-based data. In at least one embodiment, AI-assisted annotation 1310, labeled clinic data 1312, or a combination thereof may be used as ground-based data for training machine learning models. In at least one embodiment, the trained machine learning model may be referred to as output model 1316 and may be used by deployment system 1306 as described herein.

[0150] In at least one embodiment, training pipeline 1404 ( Figure 14This may include scenarios where facility 1302 requires a machine learning model to perform one or more processing tasks of one or more applications in deployment system 1306, but facility 1302 may not currently have such a machine learning model (or may not have an optimized, efficient, or effective model for such a purpose). In at least one embodiment, an existing machine learning model may be selected from model registry 1324. In at least one embodiment, model registry 1324 may include machine learning models trained to perform various inference tasks on imaging data. In at least one embodiment, the machine learning model in model registry 1324 may have already been trained on imaging data from a facility different from facility 1302 (e.g., a remote facility). In at least one embodiment, the machine learning model may have already been trained on imaging data from one location, two locations, or any number of locations. In at least one embodiment, when training on imaging data from a particular location, training may occur at that location, or at least in a manner that protects the confidentiality of the imaging data or restricts the imaging data from being transmitted in the field. In at least one embodiment, once the model has been trained or partially trained at a location, the machine learning model may be added to model registry 1324. In at least one embodiment, the machine learning model can then be retrained or updated at any number of other facilities, and the retrained or updated model can be made available in model registry 1324. In at least one embodiment, the machine learning model can then be selected from model registry 1324—and referred to as output model 1316—and can be used in deployment system 1306 to perform one or more processing tasks for one or more applications of the deployment system.

[0151] In at least one embodiment, training pipeline 1404 ( Figure 14The scenario may include facility 1302, which requires a machine learning model to perform one or more processing tasks for one or more applications in deployment system 1306, but facility 1302 may not currently have such a machine learning model (or may not have an optimized, efficient, or effective model for such purposes). In at least one embodiment, the machine learning model selected from model registry 1324 may not be fine-tuned or optimized for the imaging data 1308 generated at facility 1302 due to population differences, robustness of training data used to train the machine learning model, anomalous diversity of training data, and / or other problems with the training data. In at least one embodiment, AI-assisted annotation 1310 may be used to help generate annotations corresponding to imaging data 1308, which is used as ground-based data for retraining or updating the machine learning model. In at least one embodiment, labeled data 1312 may be used as ground-based data for training the machine learning model. In at least one embodiment, retraining or updating the machine learning model may be referred to as model training 1314. In at least one embodiment, model training 1314 (e.g., AI-assisted annotation 1310, labeled clinic data 1312, or a combination thereof) can be used as ground-based real-world data for retraining or updating the machine learning model. In at least one embodiment, the trained machine learning model may be referred to as output model 1316 and may be used by deployment system 1306 as described herein.

[0152] In at least one embodiment, deployment system 1306 may include software 1318, service 1320, hardware 1322, and / or other components, features, and functions. In at least one embodiment, deployment system 1306 may include a software "stack" such that software 1318 can be built on top of service 1320 and can use service 1320 to perform some or all of the processing tasks, service 1320 and software 1318 can be built on top of hardware 1322 and use hardware 1322 to perform processing, storage, and / or other computational tasks of deployment system 1306. In at least one embodiment, software 1318 may include any number of different containers, each of which can perform application instantiation. In at least one embodiment, each application can perform one or more processing tasks (e.g., inference, object detection, feature detection, segmentation, image enhancement, calibration, etc.) in high-level processing and inference pipelines. In at least one embodiment, the high-level processing and inference pipeline may be defined based on the selection of different containers desired or required for processing imaging data 1308, in addition to containers that receive and configure imaging data for use by each container and / or for use by facility 1302 after processing through the pipeline (e.g., converting the output back to a usable data type). In at least one embodiment, a combination of containers within software 1318 (e.g., a combination of containers that make up the pipeline) may be referred to as a virtual tool (as described in more detail herein), and the virtual tool may utilize service 1320 and hardware 1322 to perform some or all of the processing tasks of an application instantiated in a container.

[0153] In at least one embodiment, the data processing pipeline may receive input data (e.g., imaging data 1308) in a specific format in response to an inference request (e.g., a request from a user of deployment system 1306). In at least one embodiment, the input data may represent one or more images, videos, and / or other data representations generated by one or more imaging devices. In at least one embodiment, the data may undergo preprocessing as part of the data processing pipeline to prepare the data for processing by one or more applications. In at least one embodiment, postprocessing may be performed on the outputs of one or more inference tasks or other processing tasks of the pipeline to prepare output data for the next application and / or to prepare output data for user transmission and / or use (e.g., in response to an inference request). In at least one embodiment, the inference task may be performed by one or more machine learning models, such as trained or deployed neural networks, which may include the output model 1316 of training system 1304.

[0154] In at least one embodiment, the tasks of the data processing pipeline can be encapsulated in containers, each representing a discrete, fully functional instantiation of an application capable of referencing a machine learning model and a virtualized computing environment. In at least one embodiment, containers or applications can be published to a private (e.g., restricted access) area of ​​a container registry (described in more detail herein), and trained or deployed models can be stored in model registry 1324 and associated with one or more applications. In at least one embodiment, an image of the application (e.g., a container image) can be available in the container registry, and once selected by a user from the container registry for deployment in the pipeline, the image can be used to generate containers to provide instantiations of the application for use by the user's system.

[0155] In at least one embodiment, a developer (e.g., a software developer, clinician, physician, etc.) may develop, publish, and store applications (e.g., as containers) for performing image processing and / or inference on the provided data. In at least one embodiment, development, publication, and / or storage may be performed using a software development kit (SDK) associated with the system (e.g., to ensure that the developed applications and / or containers are compatible with the system). In at least one embodiment, at least some of the services 1320 may be utilized as a system (e.g., Figure 14 The system 1400's SDK is used to test the developed application locally (e.g., at the first facility, on data from the first facility). In at least one embodiment, because DICOM objects can contain anywhere from one to hundreds of images or other data types, and due to variations in data, the developer can be responsible for managing (e.g., setting up construction, incorporating preprocessing into the application, etc.) the extraction and preparation of input data. In at least one embodiment, once verified by the system 1400 (e.g., for accuracy), the application can be made available in the container registry for user selection and / or implementation to perform one or more processing tasks on data at the user's facility (e.g., the second facility).

[0156] In at least one embodiment, the developer can then share the application or container over the network for the system (e.g., Figure 14The system 1400 allows for user access and use. In at least one embodiment, completed and validated applications or containers may be stored in a container registry, and associated machine learning models may be stored in a model registry 1324. In at least one embodiment, a requesting entity providing an inference or image processing request may browse the container registry and / or model registry 1324 for applications, containers, datasets, machine learning models, etc., select desired combinations of elements to include in the data processing pipeline, and submit an imaging processing request. In at least one embodiment, the request may include input data necessary to perform the request (and, in some examples, associated patient data), and / or may include the selection of one or more applications and / or machine learning models to be performed in the processing request. In at least one embodiment, the request may then be passed to one or more components of the deployment system 1306 (e.g., the cloud) to perform processing in the data processing pipeline. In at least one embodiment, the processing performed by the deployment system 1306 may include referencing the selected elements (e.g., applications, containers, models, etc.) from the container registry and / or model registry 1324. In at least one embodiment, once the results are generated by the pipeline, the results can be returned to the user for reference (e.g., for viewing in a viewing application suite executed locally, on a field workstation, or on a terminal).

[0157] In at least one embodiment, service 1320 may be utilized to assist in processing or executing applications or containers in the pipeline. In at least one embodiment, service 1320 may include computing services, artificial intelligence (AI) services, visualization services, and / or other service types. In at least one embodiment, service 1320 may provide functionality shared by one or more applications in software 1318, thus the functionality may be abstracted into services that can be invoked or utilized by applications. In at least one embodiment, the functionality provided by service 1320 can operate dynamically and more efficiently, while also allowing applications to process data in parallel (e.g., using parallel computing platform 1430). Figure 14To scale well. In at least one embodiment, service 1320 can be shared between and among different applications, rather than requiring each application sharing the same functionality provided by service 1320 to have a corresponding instance of service 1320. In at least one embodiment, as a non-limiting example, the service may include an inference server or engine that can be used to perform detection or segmentation tasks. In at least one embodiment, a model training service may be included, which can provide machine learning model training and / or retraining capabilities. In at least one embodiment, a data augmentation service may also be included, which can provide GPU-accelerated data (e.g., DICOM, RIS, CIS, REST-compatible, RPC, raw, etc.) extraction, resizing, scaling, and / or other enhancements. In at least one embodiment, a visualization service may be used, which can add image rendering effects—such as ray tracing, rasterization, denoising, sharpening, etc.—to add realism to two-dimensional (2D) and / or three-dimensional (3D) models. In at least one embodiment, a virtual instrument service may be included that provides beamforming, segmentation, inference, imaging, and / or support for other applications within the virtual instrument pipeline.

[0158] In at least one embodiment, where service 1320 includes an AI service (e.g., an inference service), one or more machine learning models can be executed by invoking (e.g., as an API call) the inference service (e.g., an inference server) to perform the machine learning models or their processing as part of application execution. In at least one embodiment, where another application includes one or more machine learning models for segmentation tasks, the application can execute one or more machine learning models for performing processing operations associated with the segmentation tasks based on inference service invoking. In at least one embodiment, the software 1318 implementing the high-level processing and inference pipelines including the segmentation application and the anomaly detection application can be streamlined because each application can invoke the same inference service to perform one or more inference tasks.

[0159] In at least one embodiment, hardware 1322 may include a GPU, CPU, graphics card, AI / deep learning system (e.g., an AI supercomputer, such as NVIDIA's DGX), cloud platform, or a combination thereof. In at least one embodiment, different types of hardware 1322 may be used to provide efficient, specifically designed support for software 1318 and services 1320 in deployment system 1306. In at least one embodiment, the use of GPU processing may be implemented for processing locally (e.g., at facility 1302), within an AI / deep learning system, in a cloud system, and / or in other processing components of deployment system 1306 to improve the efficiency, accuracy, and power of image processing and generation. In at least one embodiment, as a non-limiting example, software 1318 and / or services 1320 may be optimized for GPU processing related to deep learning, machine learning, and / or high-performance computing. In at least one embodiment, at least some of the computing environments of deployment system 1306 and / or training system 1304 may execute one or more supercomputers or high-performance computing systems in a data center, wherein GPU-optimized software (e.g., the hardware and software combination of NVIDIA's DGX system) may be used. In at least one embodiment, hardware 1322 may include any number of GPUs, as described herein, that can be invoked to perform data processing in parallel. In at least one embodiment, the cloud platform may also include GPU processing for GPU-optimized execution of deep learning tasks, machine learning tasks, or other computational tasks. In at least one embodiment, the cloud platform (e.g., NVIDIA's NGC) may be executed using an AI / deep learning supercomputer and / or GPU-optimized software (e.g., provided on NVIDIA's DGX systems) as a hardware abstraction and scaling platform. In at least one embodiment, the cloud platform may integrate application container cluster systems or orchestration systems (e.g., Kubernetes) across multiple GPUs to achieve seamless scaling and load balancing.

[0160] Figure 14 This is a system diagram of an example system 1400 for generating and deploying an imaging deployment pipeline according to at least one embodiment. In at least one embodiment, system 1400 can be used to implement... Figure 13 The process 1300 and / or other processes including advanced processing and inference pipelines. In at least one embodiment, system 1400 may include training system 1304 and deployment system 1306. In at least one embodiment, training system 1304 and deployment system 1306 may be implemented using software 1318, service 1320 and / or hardware 1322, as described herein.

[0161] In at least one embodiment, system 1400 (e.g., training system 1304 and / or deployment system 1306) may be implemented in a cloud computing environment (e.g., using cloud 1426). In at least one embodiment, system 1400 may be implemented locally relative to a healthcare service facility, or as a combination of both cloud computing resources and local computing resources. In at least one embodiment, access to APIs in cloud 1426 may be restricted to authorized users through established security measures or protocols. In at least one embodiment, the security protocol may include a web token that can be signed by an authentication service (e.g., AuthN, AuthZ, Gluecon, etc.) and carries appropriate authorization. In at least one embodiment, the API of the virtual tool (described herein) or other instantiations of system 1400 may be restricted to a set of public IPs that have been reviewed or authorized for interaction.

[0162] In at least one embodiment, the various components of system 1400 may communicate with each other and with each other using any of a variety of different network types, including but not limited to local area networks (LANs) and / or wide area networks (WANs) via wired and / or wireless communication protocols. In at least one embodiment, communication between facilities and components of system 1400 (e.g., for transmitting inference requests, for receiving the results of inference requests, etc.) may be transmitted via a data bus, a wireless data protocol (Wi-Fi), a wired data protocol (e.g., Ethernet), etc.

[0163] In at least one embodiment, the training system 1304 may execute the training pipeline 1404, similar to that described herein. Figure 13 The described ones. In at least one embodiment, wherein one or more machine learning models will be used by deployment system 1306 in deployment pipeline 1410, training pipeline 1404 can be used to train or retrain one or more (e.g., pre-trained) models, and / or implement one or more pre-trained models 1406 (e.g., without retraining or updating). In at least one embodiment, as a result of training pipeline 1404, one or more output models 1316 may be generated. In at least one embodiment, training pipeline 1404 may include any number of processing steps, such as, but not limited to, imaging data (or other input data) transformation or adaptation. In at least one embodiment, different training pipelines 1404 may be used for different machine learning models used by deployment system 1306. In at least one embodiment, similar to the description of... Figure 13 The training pipeline 1404 of the first example described can be used for a first machine learning model, similar to that described above. Figure 13 The training pipeline 1404 of the second example described can be used for a second machine learning model, and is similar to that described above. Figure 13 The training pipeline 1404 of the third example described can be used for a third machine learning model. In at least one embodiment, any combination of tasks within the training system 1304 can be used depending on what each corresponding machine learning model requires. In at least one embodiment, one or more machine learning models may have already been trained and are ready for deployment, so the machine learning models may not undergo any processing by the training system 1304 and can be implemented by the deployment system 1306.

[0164] In at least one embodiment, depending on the implementation or embodiment, one or more output models 1316 and / or one or more pre-trained models 1406 may include any type of machine learning model. In at least one embodiment, but not limited to, the machine learning model used by system 1400 may include one or more machine learning models using linear regression, logistic regression, decision trees, support vector machines (SVM), primitive Bayes, k-nearest neighbors (Knn), K-means clustering, random forests, dimensionality reduction algorithms, gradient boosting algorithms, neural networks (e.g., autoencoders, convolutions, recursion, perceptrons, long / short-term memory (LSTM), Hopfield, Boltzmann, deep belief, deconvolution, adversarial generation, liquid machines, etc.), and / or other types of machine learning models.

[0165] In at least one embodiment, the training pipeline 1404 may include AI-assisted annotations, such as those provided herein in relation to at least... Figure 15BDescribed in more detail. In at least one embodiment, the labeled data 1312 can be generated using any number of techniques (e.g., conventional annotations). In at least one embodiment, labels or other annotations may be generated within a drawing program (e.g., annotating program), a computer-aided design (CAD) program, a labeling program, another type of program suitable for generating annotations or labels for ground reality, and / or may be hand-drawn in some examples. In at least one embodiment, the ground reality data may be synthetically generated (e.g., generated from a computer model or rendering), realistically generated (e.g., designed and generated from real-world data), machine-automated (e.g., extracting features from the data using feature analysis and learning and then generating labels), manually annotated (e.g., labelers or annotation experts defining the placement of labels), and / or a combination thereof. In at least one embodiment, for each instance of imaging data 1308 (or other data types used by a machine learning model), there may be corresponding ground reality data generated by the training system 1304. In at least one embodiment, AI-assisted annotation may be performed as part of the deployment pipeline 1410; as a supplement to or alternative to AI-assisted annotation included in the training pipeline 1404. In at least one embodiment, system 1400 may include a multi-layer platform that may include a software layer (e.g., software 1318) capable of performing one or more medical imaging and diagnostic functions. In at least one embodiment, system 1400 may be communicatively coupled to (e.g., via an encrypted link) a network of PACS servers in one or more facilities. In at least one embodiment, system 1400 may be configured to access and reference data from PACS servers to perform operations such as training machine learning models, deploying machine learning models, image processing, inference, and / or other operations.

[0166] In at least one embodiment, the software layer may be implemented as a secure, encrypted, and / or certified API through which an application or container can be invoked (e.g., called) from one or more external environments (e.g., facility 1302). In at least one embodiment, the application may then invoke or execute one or more services 1320 to perform computational, AI, or visualization tasks associated with the respective application, and the software 1318 and / or service 1320 may utilize the hardware 1322 to perform processing tasks in an efficient and effective manner.

[0167] In at least one embodiment, deployment system 1306 may execute deployment pipeline 1410. In at least one embodiment, deployment pipeline 1410 may include any number of applications that may be applied sequentially, non-sequentially, or otherwise to imaging data (and / or other data types) generated by imaging devices, sequencing devices, genomics devices, etc., including AI-assisted annotation as described above. In at least one embodiment, as described herein, deployment pipeline 1410 for an individual device may be referred to as a virtual instrument for the device (e.g., a virtual ultrasound instrument, a virtual CT scanner, a virtual sequencing instrument, etc.). In at least one embodiment, for a single device, more than one deployment pipeline 1410 may exist depending on the information required from the data generated by the device. In at least one embodiment, a first deployment pipeline 1410 may exist when it is desired to detect an abnormality from an MRI machine, and a second deployment pipeline 1410 may exist when it is desired to perform image enhancement from the output of the MRI machine.

[0168] In at least one embodiment, the image generation application may include processing tasks that include using a machine learning model. In at least one embodiment, a user may expect to use their own machine learning model or select a machine learning model from the model registry 1324. In at least one embodiment, a user may implement their own machine learning model or select a machine learning model to include in the application used to perform the processing task. In at least one embodiment, the application may be optional and customizable, and by defining the construction of the application, the deployment and implementation of the application for a particular user is presented as a more seamless user experience. In at least one embodiment, by leveraging other features of system 1400—such as service 1320 and hardware 1322—the deployment pipeline 1410 can be even more user-friendly, providing easier integration and producing more accurate, efficient, and timely results.

[0169] In at least one embodiment, deployment system 1306 may include user interface 1414 (e.g., graphical user interface, web interface, etc.) which can be used to select applications to be included in deployment pipeline 1410, schedule applications during setup and / or deployment, modify or change applications or their parameters or configurations, use deployment pipeline 1410 and interact with deployment pipeline 1410, and / or otherwise interact with deployment system 1306. In at least one embodiment, although not shown relative to training system 1304, user interface 1414 (or different user interfaces) may be used to select models to be used in deployment system 1306, to select models to be used for training or retraining in training system 1304, and / or to otherwise interact with training system 1304.

[0170] In at least one embodiment, in addition to the application orchestration system 1428, a pipeline manager 1412 may be used to manage interactions between applications or containers deployed through the deployment pipeline 1410 and services 1320 and / or hardware 1322. In at least one embodiment, the pipeline manager 1412 may be configured to facilitate interactions from application to application, from application to service 1320, and / or from application or service to hardware 1322. In at least one embodiment, although shown as included in software 1318, this is not intended to be limiting, and in some examples, the pipeline manager 1412 may be included in service 1320. In at least one embodiment, the application orchestration system 1428 (e.g., Kubernetes, DOCKER, etc.) may include a container orchestration system that can group applications into containers as logical units for coordination, management, scaling, and deployment. In at least one embodiment, by associating applications from the deployment pipeline 1410 (e.g., refactoring applications, splitting applications, etc.) with separate containers, each application can execute in a self-contained environment (e.g., at the kernel level) to improve speed and efficiency.

[0171] In at least one embodiment, each application and / or container (or its image) can be developed, modified, and deployed independently (e.g., a first user or developer can develop, modify, and deploy a first application, while a second user or developer can develop, modify, and deploy a second application separate from the first user or developer). This allows focus on and attention to the tasks of individual applications and / or containers without being hindered by the tasks of other applications or containers. In at least one embodiment, communication and collaboration between different containers or applications can be facilitated by the pipeline manager 1412 and the application orchestration system 1428. In at least one embodiment, as long as the system (e.g., based on the application or container's architecture) knows the expected inputs and / or outputs of each container or application, the application orchestration system 1428 and / or the pipeline manager 1412 can facilitate communication between and between them, as well as resource sharing between and between each application or container. In at least one embodiment, because one or more applications or containers in the deployment pipeline 1410 can share the same services and resources, the application orchestration system 1428 can orchestrate, load balance, and determine the sharing of services or resources between and among different applications or containers. In at least one embodiment, the scheduler can be used to track the resource requirements of applications or containers, the current or planned use of these resources, and resource availability. In at least one embodiment, the scheduler can therefore allocate resources to different applications and distribute resources among and between applications based on the system's needs and availability. In some instances, the scheduler (and / or other components of the application orchestration system 1428) can determine resource availability and distribution based on constraints imposed on the system (e.g., user constraints), such as Quality of Service (QoS), the urgency of data output requirements (e.g., determining whether to perform real-time processing or delayed processing), etc.

[0172] In at least one embodiment, services 1320 utilized and shared by applications or containers in deployment system 1306 may include computing services 1416, AI services 1418, visualization services 1420, and / or other service types. In at least one embodiment, an application may invoke (e.g., execute) one or more of services 1320 to perform processing operations of the application. In at least one embodiment, computing service 1416 may be utilized by an application to perform supercomputing or other high-performance computing (HPC) tasks. In at least one embodiment, computing services 1416 may be fully utilized to perform parallel processing (e.g., using parallel computing platform 1430) for processing data substantially simultaneously through one or more tasks of an application and / or one or more tasks of a single application. In at least one embodiment, parallel computing platform 1430 (e.g., NVIDIA's CUDA) may enable general-purpose computing on a GPU (GPGPU) (e.g., GPU 1422). In at least one embodiment, the software layer of parallel computing platform 1430 may provide access to the GPU's virtual instruction set and parallel computing elements to execute computing kernels. In at least one embodiment, the parallel computing platform 1430 may include memory, and in some embodiments, memory may be shared between and within multiple containers and / or between and within different processing tasks within a single container. In at least one embodiment, inter-process communication (IPC) calls may be generated for multiple containers and / or for multiple processes within a container to use the same data from a shared segment of memory from the parallel computing platform 1430 (e.g., in cases where multiple applications are processing the same information at multiple different stages of an application). In at least one embodiment, instead of copying data and moving it to different locations in memory (e.g., read / write operations), the same data in the same location of memory is used for any number of processing tasks (e.g., simultaneously, at different times, etc.). In at least one embodiment, since new data is generated using data as a result of processing, this information about the new location of the data can be stored and shared between different applications. In at least one embodiment, the location of the data and the location of updated or modified data may be part of the definition of how the payload is understood within the container.

[0173] In at least one embodiment, AI service 1418 may be used to perform inference services for executing machine learning models associated with an application (e.g., tasks assigned to perform one or more processing tasks of the application). In at least one embodiment, AI service 1418 may utilize AI system 1424 to execute machine learning models (e.g., neural networks, such as CNNs) for segmentation, reconstruction, object detection, feature detection, classification, and / or other inference tasks. In at least one embodiment, applications of deployment pipeline 1410 may use one or more of the output models 1316 from training system 1304 and / or other models of the application to perform inference on imaging data. In at least one embodiment, two or more examples of inference using application orchestration system 1428 (e.g., scheduler) may be available. In at least one embodiment, a first category may include high-priority / low-waittime paths that implement higher service level agreements, such as for performing inference on urgent requests during emergencies or on radiologists during diagnosis. In at least one embodiment, a second category may include standard priority paths that may be used for requests that are not urgent or where analysis can be performed later. In at least one embodiment, the application orchestration system 1428 may allocate resources (e.g., service 1320 and / or hardware 1322) based on priority paths for different inference tasks for the AI ​​service 1418.

[0174] In at least one embodiment, shared storage may be installed within AI service 1418 of system 1400. In at least one embodiment, shared storage may operate as a cache (or other storage device type) and may be used to process inference requests from applications. In at least one embodiment, when an inference request is submitted, the request may be received by a set of API instances deployed in system 1306, and one or more instances may be selected (e.g., for best fit, for load balancing, etc.) to process the request. In at least one embodiment, to process the request, the request may be fed into a database, and if not already in the cache, a machine learning model may be located from model registry 1324. A verification step may ensure that an appropriate machine learning model is loaded into the cache (e.g., shared storage), and / or a copy of the model may be saved to the cache. In at least one embodiment, a scheduler (e.g., of pipeline manager 1412) may be used to launch the application referenced in the request if the application is not yet running or if there are not enough instances of the application. In at least one embodiment, an inference server may be launched if an inference server has not yet been started to execute the model. Any number of inference servers may be launched for each model. In at least one embodiment, in a clustered pull model where the inference server is located, the model can be cached whenever load balancing is favorable. In at least one embodiment, the inference server can be statically loaded into the corresponding distributed server.

[0175] In at least one embodiment, an inference server running in a container can be used to perform inference. In at least one embodiment, an instance of the inference server can be associated with a model (and optionally multiple versions of the model). In at least one embodiment, if an instance of the inference server does not exist when a request to perform inference on the model is received, a new instance can be loaded. In at least one embodiment, when the inference server is started, a model can be passed to the inference server so that the same container can be used to serve different models as long as the inference server runs as different instances.

[0176] In at least one embodiment, during application execution, an inference request for a given application may be received, and a container (e.g., an instance of a hosted inference server) may be loaded (if not already loaded), and a start procedure may be invoked. In at least one embodiment, preprocessing logic within the container may load, decode incoming data, and / or perform any additional preprocessing on the incoming data (e.g., using a CPU and / or GPU). In at least one embodiment, once the data is ready for inference, the container may perform inference on the data as needed. In at least one embodiment, this may include a single inference call for an image (e.g., a hand X-ray) or may request inference for hundreds of images (e.g., a chest CT scan). In at least one embodiment, the application may summarize the results before completion, which may include, but is not limited to, a single confidence score, pixel-level segmentation, voxel-level segmentation, generating visualizations, or generating text to summarize the findings. In at least one embodiment, different models or applications may be assigned different priorities. For example, some models may have a real-time (TAT < 1 minute) priority, while others may have a lower priority (e.g., TAT < 10 minutes). In at least one embodiment, model execution time can be measured from the requesting agency or entity, and model execution time can include partner network traversal time, as well as execution on the inference service.

[0177] In at least one embodiment, the transmission of requests between service 1320 and the inference application can be hidden behind a software development kit (SDK) and robust transmission can be provided via queues. In at least one embodiment, requests are placed in a queue via an API with a separate application / tenant ID combination, and the SDK pulls requests from the queue and delivers them to the application. In at least one embodiment, the name of the queue can be provided in the environment from which the SDK will pick up the queue. In at least one embodiment, asynchronous communication via queues can be useful because it allows any instance of the application to pick up work as it becomes available. Results can be transmitted back via queues to ensure no data loss. In at least one embodiment, queues can also provide the ability to partition work, as the highest priority work can be sent to a queue with a majority of instances of the application connected to it, while the lowest priority work can be sent to a queue with a single instance connected to it, which processes tasks in the order they are received. In at least one embodiment, the application can run on a GPU-accelerated instance generated in cloud 1426, and the inference service can perform inference on the GPU.

[0178] In at least one embodiment, visualization service 1420 may be used to generate visualizations for viewing the output of application and / or deployment pipeline 1410. In at least one embodiment, GPU 1422 may be utilized by visualization service 1420 to generate visualizations. In at least one embodiment, rendering effects (such as ray tracing) may be implemented by visualization service 1420 to generate higher quality visualizations. In at least one embodiment, visualizations may include, but are not limited to, 2D image rendering, 3D volumetric rendering, 3D volumetric reconstruction, 2D tomographic slicing, virtual reality displays, augmented reality displays, etc. In at least one embodiment, a virtualized environment may be used to generate a virtual interactive display or environment (e.g., a virtual environment) for interaction by users of the system (e.g., doctors, nurses, radiologists, etc.). In at least one embodiment, visualization service 1420 may include an internal visualizer, dynamic images and / or other rendering or image processing capabilities or functions (e.g., ray tracing, rasterization, internal optics, etc.).

[0179] In at least one embodiment, hardware 1322 may include GPU 1422, AI system 1424, cloud 1426, and / or any other hardware for performing training system 1304 and / or deployment system 1306. In at least one embodiment, GPU 1422 (e.g., NVIDIA's TESLA and / or QUADRO GPUs) may include any number of GPUs that can be used to perform processing tasks of any of the features or functions of computing service 1416, AI service 1418, visualization service 1420, other services, and / or software 1318. For example, with respect to AI service 1418, GPU 1422 may be used to perform preprocessing on imaging data (or other data types used by machine learning models), postprocessing on the output of machine learning models, and / or to perform inference (e.g., for executing machine learning models). In at least one embodiment, cloud 1426, AI system 1424, and / or other components of system 1400 may use GPU 1422. In at least one embodiment, cloud 1426 may include a GPU-optimized platform for deep learning tasks. In at least one embodiment, AI system 1424 may use a GPU, and one or more AI systems 1424 may be used to perform cloud 1426—or a task that is at least part of deep learning or inference. Accordingly, although hardware 1322 is shown as discrete components, this is not intended to be limiting, and any component of hardware 1322 may be combined with or utilized by any other component of hardware 1322.

[0180] In at least one embodiment, AI system 1424 may include a dedicated computing system (e.g., a supercomputer or HPC) configured for inference, deep learning, machine learning, and / or other artificial intelligence tasks. In at least one embodiment, AI system 1424 (e.g., NVIDIA's DGX) may include GPU-optimized software (e.g., a software stack) that can be executed using multiple GPUs 1422, in addition to CPUs, RAM, storage devices, and / or other components, features, or functionalities. In at least one embodiment, one or more AI systems 1424 may be implemented in a cloud 1426 (e.g., in a data center) to perform some or all of the AI-based processing tasks of system 1400.

[0181] In at least one embodiment, cloud 1426 may include GPU-accelerated infrastructure (e.g., NVIDIA's NGC) that provides a GPU-optimized platform for performing processing tasks of system 1400. In at least one embodiment, cloud 1426 may include AI system 1424 for performing one or more AI-based tasks of system 1400 (e.g., as a hardware abstraction and scaling platform). In at least one embodiment, cloud 1426 may be integrated with application orchestration system 1428 that utilizes multiple GPUs to enable seamless scaling and load balancing between and within applications and services 1320. In at least one embodiment, the tasks of cloud 1426 may be performing at least some of the services 1320 of system 1400, including computing service 1416, AI service 1418, and / or visualization service 1420, as described herein. In at least one embodiment, cloud 1426 may perform mini-batch inference and mass inference (e.g., perform NVIDIA's TENSORRT), provide accelerated parallel computing APIs and platform 1430 (e.g., NVIDIA's CUDA), perform application orchestration system 1428 (e.g., KUBERNETES), provide graphics rendering APIs and platform (e.g., for ray tracing, 2D graphics, 3D graphics, and / or other rendering techniques to produce higher quality cinematography), and / or may provide other functionalities for system 1400.

[0182] Figure 15A A data flow diagram of a process 1500 for training, retraining, or updating a machine learning model according to at least one embodiment is shown. In at least one embodiment, as a non-limiting example, the following can be used: Figure 14 System 1400 performs processing 1500. In at least one embodiment, process 1500 may utilize services 1320 and / or hardware 1322 of system 1400, as described herein.

[0183] In at least one embodiment, the refined model 1512 generated by process 1500 can be executed by deployment system 1306 for one or more containerized applications in deployment pipeline 1410.

[0184] In at least one embodiment, model training 1314 may include retraining or updating the initial model 1504 (e.g., a pre-trained model) using new training data (e.g., new input data, such as customer dataset 1506 and / or new ground reality data associated with the input data).

[0185] In at least one embodiment, to retrain or update the initial model 1504, the output or lost layer of the initial model 1504 may be reset, deleted, and / or replaced with an updated or new output or lost layer. In at least one embodiment, the initial model 1504 may have previously fine-tuned parameters (e.g., weights and / or biases) that remain from previous training, so training or retraining 1314 may not take as long as training the model from scratch or require as much processing. In at least one embodiment, during model training 1314, by resetting or replacing the output or lost layer of the initial model 1504, when generating new predictions, the parameters may be updated and retuned for the new dataset 1506 (e.g., customer dataset 1506) based on loss calculations associated with the accuracy of the output or (one or more) lost layers. Figure 13 Image data 1308).

[0186] In at least one embodiment, the pre-trained model 1406 may be stored in a data storage or registry (e.g., Figure 13The model registry 1324 is used for training. In at least one embodiment, the pre-trained model 1406 may have been trained at least partially at one or more facilities other than the facility executing process 1500. In at least one embodiment, to protect the privacy and permissions of patients, objects, or clients at different facilities, the pre-trained model 1406 may be trained on-site using customer or patient data generated within the facility. In at least one embodiment, the pre-trained model 1406 may be trained using cloud 1426 and / or other hardware 1322, but confidential, privacy-protected patient data may not be transferred to any component of cloud 1426 (or other off-site hardware), used by any component of cloud 1426, or accessed by any component of cloud 1426 (or other off-site hardware). In at least one embodiment, when training the pre-trained model 1406 using patient data from more than one facility, the pre-trained model 1406 may be trained separately for each facility before training on patient or customer data from another facility. In at least one embodiment, such as where customer or patient data has been published for privacy reasons (e.g., by waiting, for experimental use, etc.), or where customer or patient data is included in a public dataset, customer or patient data from any number of facilities can be used to train pre-trained models 1406 on-site and / or off-site, such as in data centers or other cloud computing infrastructures.

[0187] In at least one embodiment, when selecting an application to use in deployment pipeline 1410, the user can also select the machine learning model to be used for the specific application. In at least one embodiment, the user may not have a model available for use, so the user can select a pre-trained model 1406 to use with the application. In at least one embodiment, the pre-trained model 1406 may not be optimized to generate accurate results on the user's facility's customer dataset 1506 (e.g., based on patient diversity, demographics, type of medical imaging equipment used, etc.). In at least one embodiment, the pre-trained model 1406 may be updated, retrained, and / or fine-tuned for use at the appropriate facility before being deployed to deployment pipeline 1410 for use with the application.

[0188] In at least one embodiment, the user can select a pre-trained model 1406 to be updated, retrained, and / or fine-tuned, and the pre-trained model 1406 can be referred to as the initial model 1504 of the training system 1304 within process 1500. In at least one embodiment, the customer dataset 1506 (e.g., imaging data, genomics data, sequencing data, or other data types generated by facilities) can be used to perform model training 1314 (which may include, but is not limited to, transfer learning) on ​​the initial model 1504 to generate a refined model 1512. In at least one embodiment, ground-based data corresponding to the customer dataset 1506 can be generated by the training system 1304. In at least one embodiment, the ground-based data can be generated at least in part by clinicians, scientists, physicians, or practicing physicians at the facility (e.g., such as...). Figure 13 Clinical data marked with markers (1312).

[0189] In at least one embodiment, AI-assisted annotation 1310 may be used in some examples to generate ground condition data. In at least one embodiment, AI-assisted annotation 1310 (e.g., implemented using an AI-assisted annotation SDK) may leverage machine learning models (e.g., neural networks) to generate suggested or predicted ground condition data for a customer dataset. In at least one embodiment, user 1510 may use annotation tools within a user interface (graphical user interface (GUI)) on computing device 1508.

[0190] In at least one embodiment, user 1510 can interact with the GUI via computing device 1508 to edit or fine-tune (automatic) annotations. In at least one embodiment, polygon editing features can be used to move the vertices of a polygon to more accurate or finely adjusted positions.

[0191] In at least one embodiment, once the customer dataset 1506 has associated ground-based data, the ground-based data (e.g., annotations from AI-assisted sources, manual labeling, etc.) can be used to generate a refined model 1512 during model training 1314. In at least one embodiment, the customer dataset 1506 can be applied to the initial model 1504 an arbitrary number of times, and the ground-based data can be used to update the parameters of the initial model 1504 until an acceptable level of accuracy is achieved for the refined model 1512. In at least one embodiment, once the refined model 1512 is generated, it can be deployed within one or more deployment pipelines 1410 at a facility for performing one or more processing tasks related to medical imaging data.

[0192] In at least one embodiment, the refined model 1512 can be uploaded to the pre-trained model 1406 in the model registry 1324 for selection by another facility. In at least one embodiment, this process can be performed at any number of facilities, allowing the refined model 1512 to be further refined any number of times on new datasets to generate a more general model.

[0193] Figure 15B This is an example illustration of a client-server architecture 1532 for enhancing annotation tools using a pre-trained annotation model, according to at least one embodiment. In at least one embodiment, an AI-assisted annotation tool 1536 can be instantiated based on the client-server architecture 1532. In at least one embodiment, the annotation tool 1536 in an imaging application can help radiologists, for example, identify organs and abnormalities. In at least one embodiment, the imaging application may include software tools that help user 1510 identify (as a non-limiting example) several extreme points on a specific organ of interest in an original image 1534 (e.g., in a 3D MRI or CT scan) and receive automatic annotation results of all 2D slices of the specific organ. In at least one embodiment, the results can be stored in a data store as training data 1538 and used (e.g., but not limited to) ground-based data for training. In at least one embodiment, when computing device 1508 sends extreme points for AI-assisted annotation 1310, a deep learning model can, for example, receive this data as input and return inference results for segmented organs or abnormalities. In at least one embodiment, a pre-instantiated annotation tool (such as...) Figure 15B The AI-assisted annotation tool 1536B can be enhanced by making API calls (e.g., API call 1544) to a server (such as an annotation assistant server 1540, which may, for example, include a set of pre-trained models 1542 stored in an annotation model registry). In at least one embodiment, the annotation model registry may store pre-trained models 1542 (e.g., machine learning models, such as deep learning models) that have been pre-trained to perform AI-assisted annotation on specific organs or abnormalities. These models can be further updated using the training pipeline 1404. In at least one embodiment, the pre-installed annotation tool can be improved over time as new tagged clinic data 1312 is added.

[0194] These components can be used to synthesize a compositional image into a single representation using parameters determined from one or more quality assessment values.

[0195] Automation technology

[0196] Figure 16A The illustration shows an embodiment according to at least one of the embodiments. Figure 16AA block diagram of an example system architecture for an autonomous vehicle 1600. In at least one embodiment, Figure 16A Each of one or more components, one or more features, and one or more systems of vehicle 1600 is shown as connected via bus 1602. In at least one embodiment, bus 1602 may include, but is not limited to, a CAN data interface (which may alternatively be referred to herein as “CAN bus”). In at least one embodiment, the CAN bus may be a network within vehicle 1600 used to help control various features and functions of vehicle 1600, such as brake actuation, acceleration, braking, steering, windshield wipers, etc. In one embodiment, bus 1602 may be configured to have dozens or even hundreds of nodes, each node having its own unique identifier (e.g., CAN ID). In at least one embodiment, bus 1602 can be read to find steering wheel angle, ground speed, engine revolutions per minute (“RPM”), button positions, and / or other vehicle status indicators. In at least one embodiment, bus 1602 may be an ASIL B compliant CAN bus.

[0197] In at least one embodiment, FlexRay and / or Ethernet may be used in addition to or from CAN. In at least one embodiment, there may be any number of buses 1602, which may include, but are not limited to, zero or more CAN buses, zero or more FlexRay buses, zero or more Ethernet buses, and / or zero or more other types of buses using other protocols. In at least one embodiment, two or more buses may be used to perform different functions and / or may be used for redundancy. For example, a first bus may be used for a collision avoidance function, and a second bus may be used for actuation control. In at least one embodiment, each bus 1602 may communicate with any component of vehicle 1600, and two or more buses 1602 may communicate with the same component. In at least one embodiment, each of any number of system-on-chip (“SoC”) 1604, each of one or more controllers 1636, and / or each computer within the vehicle may access the same input data (e.g., input from sensors of vehicle 1600) and may be connected to a common bus, such as a CAN bus.

[0198] In at least one embodiment, vehicle 1600 may include one or more controllers 1636, such as those described herein. Figure 1AThe controller 1636 can be used for a variety of functions. In at least one embodiment, the controller 1636 can be coupled to any of the various other components and systems of the vehicle 1600 and can be used to control the vehicle 1600, the artificial intelligence of the vehicle 1600, the infotainment and / or other functions of the vehicle 1600.

[0199] In at least one embodiment, vehicle 1600 may include any number of SoCs 1604. Each of the SoCs 1604 may include, but is not limited to, a central processing unit (“one or more CPUs”) 1606, a graphics processing unit (“one or more GPUs”) 1608, one or more processors 1610, one or more caches 1612, one or more accelerators 1614, one or more data storage 1616, and / or other components and features not shown. In at least one embodiment, one or more SoCs 1604 may be used to control vehicle 1600 on various platforms and systems. For example, in at least one embodiment, one or more SoCs 1604 may be combined with a high-definition (“HD”) map 1622 in a system (e.g., the system of vehicle 1600), which may be transmitted via a network interface 1624 from one or more servers ( Figure 16A (Not shown in the image) Get map refresh and / or update.

[0200] In at least one embodiment, one or more CPUs 1606 may include CPU clusters or CPU complexes (which may alternatively be referred to herein as “CCPLEX”). In at least one embodiment, one or more CPUs 1606 may include multiple cores and / or a secondary (“L2”) cache. For example, in at least one embodiment, one or more CPUs 1606 may include eight cores in an intercoupled multiprocessor configuration. In at least one embodiment, one or more CPUs 1606 may include four dual-core clusters, each cluster having a dedicated L2 cache (e.g., 2MB L2 cache). In at least one embodiment, one or more CPUs 1606 (e.g., CCPLEX) may be configured to support simultaneous cluster operation, such that any combination of clusters of one or more CPUs 1606 can be active at any given time.

[0201] In at least one embodiment, one or more CPUs 1606 may implement power management functions, including but not limited to one or more of the following features: automatic clock gating of individual hardware modules to conserve dynamic power when idle; clock gating of each core when the core is not actively executing instructions due to executing Wait for Interrupt (“WFI”) / Event Wait (“WFE”) instructions; independent power supply for each core; independent clock gating for each core cluster when all cores are clock-gated or power-gated; and / or independent power gating for each core cluster when all cores are power-gated. In at least one embodiment, one or more CPUs 1606 may further implement an enhanced algorithm for managing power states, wherein allowed power states and expected wake-up times are specified, and the hardware / microcode determines the optimal power state for the core, cluster, and CCPLEX inputs. In at least one embodiment, the processing core may support a simplified power state input sequence in software, wherein the work is offloaded to the microcode.

[0202] In at least one embodiment, one or more GPUs 1608 may include integrated GPUs (or “iGPUs” herein). In at least one embodiment, one or more GPUs 1608 may be programmable and efficient for parallel workloads. In at least one embodiment, one or more GPUs 1608 may use an enhanced tensor instruction set. In at least one embodiment, one or more GPUs 1608 may include one or more streaming microprocessors, wherein each streaming microprocessor may include a Level 1 (“L1”) cache (e.g., an L1 cache with at least 96KB of storage capacity), and two or more streaming microprocessors may share an L2 cache (e.g., an L2 cache with 512KB of storage capacity). In at least one embodiment, one or more GPUs 1608 may include at least eight streaming microprocessors. In at least one embodiment, one or more GPUs 1608 may use a computational application programming interface (API). In at least one embodiment, one or more GPUs 1608 may use one or more parallel computing platforms and / or programming models (e.g., NVIDIA’s CUDA).

[0203] In at least one embodiment, one or more GPU 1608s may be power-optimized for optimal performance in automotive and embedded use cases. For example, in one embodiment, one or more GPU 1608s may be fabricated on a FinFET (“FinFET”). In at least one embodiment, each streaming microprocessor may include multiple mixed-precision processing cores divided into multiple blocks. For example, but not limited to, 64 PF32 cores and 32 PF64 cores may be divided into four processing blocks. In at least one embodiment, each processing block may be allocated 16 FP32 cores, 8 FP64 cores, 16 INT32 cores, two mixed-precision NVIDIA Tensor cores for deep learning matrix arithmetic, a level-zero (“L0”) instruction cache, a thread bundle scheduler, a dispatch unit, and / or a 64KB register file. In at least one embodiment, the streaming microprocessor may include independent parallel integer and floating-point data paths to provide efficient execution of workloads that mix computation and addressing operations. In at least one embodiment, the streaming microprocessor may include independent thread scheduling capabilities to enable finer-grained synchronization and cooperation between parallel threads. In at least one embodiment, the streaming microprocessor may include a combined L1 data cache and shared memory unit to improve performance while simplifying programming.

[0204] In at least one embodiment, one or more GPUs 1608 may include high-bandwidth memory (“HBM”) and / or a 16GB HBM2 memory subsystem to provide a peak storage bandwidth of approximately 900GB / s in some examples. In at least one embodiment, in addition to or instead of HBM memory, synchronous graphics random access memory (“SGRAM”) may be used, such as graphics double data rate type five synchronous random access memory (“GDDR5”).

[0205] In at least one embodiment, one or more GPUs 1608 may include unified memory technology. In at least one embodiment, address translation service (“ATS”) support can be used to allow one or more GPUs 1608 to directly access the page tables of one or more CPUs 1606. In at least one embodiment, when one or more GPUs 1608 memory management units (“MMU”) experience a miss, an address translation request can be sent to one or more CPUs 1606. In response, in at least one embodiment, two of the one or more CPUs 1606 can look up the virtual-physical mapping of the address in their page tables and transfer the translation back to one or more GPUs 1608. In at least one embodiment, unified memory technology can allow a single unified virtual address space to be used for the memory of both one or more CPUs 1606 and one or more GPUs 1608, thereby simplifying the programming of one or more GPUs 1608 and the porting of applications to one or more GPUs 1608.

[0206] In at least one embodiment, one or more GPUs 1608 may include any number of access counters that can track the frequency of memory accesses by one or more GPUs 1608 to other processors. In at least one embodiment, one or more access counters can help ensure that memory pages are moved to the physical memory of the processor that accesses the pages most frequently, thereby improving the efficiency of shared memory ranges between processors.

[0207] In at least one embodiment, one or more SoCs 1604 may include any number of caches 1612, including those described herein. For example, in at least one embodiment, one or more caches 1612 may include a Level 3 (“L3”) cache available for one or more CPUs 1606 and one or more GPUs 1608 (e.g., connected to CPUs 1606 and GPUs 1608). In at least one embodiment, one or more caches 1612 may include a write-back cache that can, for example, track the state of a line using a cache coherence protocol (e.g., MEI, MESI, MSI, etc.). In at least one embodiment, although a smaller cache size may be used, the L3 cache may include 4 MB or more, depending on the embodiment.

[0208] In at least one embodiment, one or more SoCs 1604 may include one or more accelerators 1614 (e.g., hardware accelerators, software accelerators, or combinations thereof). In at least one embodiment, one or more SoCs 1604 may include a hardware acceleration cluster, which may include optimized hardware accelerators and / or large on-chip memory. In at least one embodiment, large on-chip memory (e.g., 4MB of SRAM) enables the hardware acceleration cluster to accelerate neural networks and other computations. In at least one embodiment, the hardware acceleration cluster may be used to supplement one or more GPUs 1608 and offload some tasks from one or more GPUs 1608 (e.g., freeing up more cycles from one or more GPUs 1608 to perform other tasks). In at least one embodiment, one or more accelerators 1614 may be used for a target workload (e.g., perceptual, convolutional neural network (“CNN”), recurrent neural network (“RNN”), etc.) that is sufficiently stable to withstand acceleration testing. In at least one embodiment, the CNN may include region-based or region convolutional neural networks (“RCNN”) and fast RCNN (e.g., for object detection) or other types of CNNs.

[0209] In at least one embodiment, one or more accelerators 1614 (e.g., a hardware acceleration cluster) may include one or more deep learning accelerators (“DLAs”). One or more DLAs may include, but are not limited to, one or more Tensor Processing Units (“TPUs”), which may be configured to provide an additional 10 trillion operations per second for deep learning applications and inference. In at least one embodiment, the TPU may be an accelerator configured and optimized for performing image processing functions (e.g., for CNNs, RCNNs, etc.). One or more DLAs may be further optimized for specific sets of neural network types and floating-point operations and inference. In at least one embodiment, one or more DLAs are designed to provide higher performance per millimeter than typical general-purpose GPUs and typically significantly outperform CPUs. In at least one embodiment, one or more TPUs may perform several functions, including single-instance convolution functions supporting, for example, INT8, INT16, and FP16 data types for features and weights, as well as post-processor functions. In at least one embodiment, one or more DLAs can execute neural networks, particularly CNNs, quickly and efficiently on processed or unprocessed data for any of the various functions, including, but not limited to: CNNs for object recognition and detection using data from camera sensors; CNNs for distance estimation using data from camera sensors; CNNs for emergency vehicle detection, recognition, and identification using data from microphone 1696; CNNs for face recognition and vehicle owner recognition using data from camera sensors; and / or CNNs for safety and / or safety-related events.

[0210] In at least one embodiment, the DLA can perform any function of one or more GPUs 1608, and by using inference accelerators, for example, the designer can target one or more DLAs or one or more GPUs 1608 for any function. For example, in at least one embodiment, the designer can concentrate the CNN processing and floating-point operations on one or more DLAs, leaving other functions to one or more GPUs 1608 and / or one or more accelerators 1614.

[0211] In at least one embodiment, one or more accelerators 1614 (e.g., hardware acceleration clusters) may include one or more programmable vision accelerators (“PVAs”), which may alternatively be referred to herein as computer vision accelerators. In at least one embodiment, one or more PVAs may be designed and configured to accelerate computer vision algorithms for advanced driver assistance systems (“ADAS”) 1638, autonomous driving, augmented reality (“AR”) applications, and / or virtual reality (“VR”) applications. One or more PVAs may strike a balance between performance and flexibility. For example, in at least one embodiment, each of one or more PVAs may include, for example, but not limited to, any number of reduced instruction set computer (“RISC”) cores, direct memory access (“DMA”), and / or any number of vector processors.

[0212] In at least one embodiment, the RISC core can interact with an image sensor (e.g., the image sensor of any camera described herein), an image signal processor, and / or other processors. In at least one embodiment, each RISC core may include any number of memories. In at least one embodiment, the RISC core may use any of a variety of protocols, depending on the embodiment. In at least one embodiment, the RISC core may execute a real-time operating system (“RTOS”). In at least one embodiment, the RISC core may be implemented using one or more integrated circuit devices, application-specific integrated circuits (“ASICs”), and / or storage devices. For example, in at least one embodiment, the RISC core may include an instruction cache and / or tightly coupled RAM.

[0213] In at least one embodiment, DMA enables components of (one or more) PVAs to access system memory independently of one or more CPUs 1606. In at least one embodiment, DMA can support any number of features for providing optimization to the PVA, including but not limited to, support for multidimensional addressing and / or circular addressing. In at least one embodiment, DMA can support up to six or more addressing dimensions, which may include, but are not limited to, block width, block height, block depth, horizontal block step, vertical block step, and / or depth step.

[0214] In at least one embodiment, the vector processor may be a programmable processor designed to efficiently and flexibly execute programming for computer vision algorithms and provide signal processing capabilities. In at least one embodiment, the PVA may include a PVA core and two vector processing subsystem partitions. In at least one embodiment, the PVA core may include a processor subsystem, a DMA engine (e.g., two DMA engines), and / or other peripherals. In at least one embodiment, the vector processing subsystem may serve as the main processing engine of the PVA and may include a vector processing unit (“VPU”), an instruction cache, and / or a vector memory (e.g., “VMEM”). In at least one embodiment, the VPU core may include a digital signal processor, such as a Single Instruction Multiple Data (“SIMD”) or Very Long Instruction Word (“VLIW”) digital signal processor. In at least one embodiment, the combination of SIMD and VLIW can improve throughput and speed.

[0215] In at least one embodiment, each vector processor may include an instruction cache and may be coupled to dedicated memory. As a result, in at least one embodiment, each vector processor may be configured to execute independently of other vector processors. In at least one embodiment, vector processors included in a particular PVA may be configured to employ data parallelism. For example, in at least one embodiment, multiple vector processors included in a single PVA may execute the same computer vision algorithm, except on different regions of an image. In at least one embodiment, vector processors included in a particular PVA may execute different computer vision algorithms simultaneously on the same image, or even execute different algorithms on a sequence of images or portions of images. In at least one embodiment, among others, any number of PVAs may be included in the hardware-accelerated cluster, and any number of vector processors may be included in each PVA. In at least one embodiment, (one or more) PVAs may include additional error-correcting code (“ECC”) memory to enhance overall system security.

[0216] In at least one embodiment, one or more accelerators 1614 (e.g., a hardware acceleration cluster) may include an on-chip computer vision network and static random access memory (“SRAM”) for providing high-bandwidth, low-latency SRAM to one or more accelerators 1614. In at least one embodiment, the on-chip memory may include at least 4 MB of SRAM, comprising, for example, but not limited to, eight field-configurable memory blocks accessible to both the PVA and DLA. In at least one embodiment, each pair of memory blocks may include an Advanced Peripheral Bus (“APB”) interface, configuration circuitry, a controller, and a multiplexer. In at least one embodiment, any type of memory may be used. In at least one embodiment, the PVA and DLA may access the memory via a backbone providing high-speed access to the memory for both the PVA and DLA. In at least one embodiment, the backbone may include an on-chip computer vision network that interconnects the PVA and DLA to the memory (e.g., using an APB).

[0217] In at least one embodiment, the on-chip computer vision network may include an interface that determines that both the PVA and DLA provide ready and valid signals before transmitting any control signals / addresses / data. In at least one embodiment, the interface may provide separate phases and separate channels for transmitting control signals / addresses / data, as well as bursty communication for continuous data transmission. In at least one embodiment, although other standards and protocols may be used, the interface may conform to the International Organization for Standardization (“ISO”) 26262 or the International Electrotechnical Commission (“IEC”) 61508 standard.

[0218] In at least one embodiment, one or more SoCs 1604 may include a real-time eye-tracking hardware accelerator. In at least one embodiment, the real-time eye-tracking hardware accelerator may be used to quickly and efficiently determine the location and extent of an object (e.g., within a world model) to generate real-time visualization simulations for RADAR signal interpretation, for sound propagation synthesis and / or analysis, for simulation of SONAR systems, for general wave propagation simulation, for comparison with LIDAR data for localization and / or other functions, and / or for other purposes.

[0219] In at least one embodiment, one or more accelerators 1614 (e.g., hardware acceleration clusters) have broad applications for autonomous driving. In at least one embodiment, the PVA can be a programmable vision accelerator, which can be used in critical processing stages in ADAS and autonomous vehicles. In at least one embodiment, the capabilities of the PVA at low power and low latency are well-matched to algorithmic domains requiring predictable processing. In other words, the PVA performs well in semi-intensive or intensive conventional computations, even on small datasets that may require predictable runtimes with low latency and low power consumption. In at least one embodiment, for autonomous vehicles, such as vehicle 1600, the PVA is designed to run classical computer vision algorithms because they are efficient in object detection and integer mathematical operations.

[0220] For example, according to at least one embodiment of the technology, PVA is used to perform computer stereo vision. In at least one embodiment, a semi-global matching-based algorithm may be used in some examples, although this is not intended to be limiting. In at least one embodiment, applications for Level 3-5 autonomous driving use dynamic estimation / stereo matching during operation (e.g., structure recovery from motion, pedestrian recognition, lane detection, etc.). In at least one embodiment, PVA can perform computer stereo vision functions on input from two monocular cameras.

[0221] In at least one embodiment, the PVA can be used to perform intensive optical flow. For example, in at least one embodiment, the PVA can process raw RADAR data (e.g., using 4D Fast Fourier Transform) to provide processed RADAR data. In at least one embodiment, the PVA is used for time-of-flight depth processing, for example, by processing raw time-of-flight data to provide processed time-of-flight data.

[0222] In at least one embodiment, the DLA can be used to run any type of network to enhance control and driving safety, including, but not limited to, neural networks whose output is used for a confidence score for each object detection. In at least one embodiment, the confidence score can be represented or interpreted as a probability, or as providing a relative “weight” for each detection relative to other detections. In at least one embodiment, the confidence score enables the system to make further decisions about which detections should be considered true positives rather than false positives. For example, in at least one embodiment, the system can set a threshold for the confidence score and only consider detections exceeding the threshold as true positives. In embodiments using an Automatic Emergency Braking (“AEB”) system, false positives would cause the vehicle to automatically perform emergency braking, which is obviously undesirable. In at least one embodiment, a highly confident detection can be considered a trigger for AEB. In at least one embodiment, the DLA can run a neural network for regressing the confidence score value. In at least one embodiment, the neural network may take at least a subset of parameters as its input, such as bounding box size, obtained ground plane estimate (e.g., from another subsystem), and outputs of one or more IMU sensors 1666 related to the vehicle 1600 orientation, distance, and 3D position estimate of the object obtained from the neural network and / or other sensors (e.g., one or more LiDAR sensors 1664 or one or more RADAR sensors 1660).

[0223] In at least one embodiment, one or more SoCs 1604 may include one or more data storage devices 1616 (e.g., memory). In at least one embodiment, one or more data storage devices 1616 may be on-chip memory of one or more SoCs 1604, which may store neural networks to be executed on one or more GPUs 1608 and / or DLAs. In at least one embodiment, one or more data storage devices 1616 may have a sufficiently large capacity to store multiple instances of the neural network for redundancy and security. In at least one embodiment, one or more data storage devices 1616 may include L2 or L3 caches.

[0224] In at least one embodiment, one or more SoCs 1604 may include any number of processors 1610 (e.g., embedded processors). In at least one embodiment, one or more processors 1610 may include a boot and power management processor, which may be a dedicated processor and subsystem for handling boot power and management functions, as well as associated security implementations. In at least one embodiment, the boot and power management processor may be part of a boot sequence of one or more SoCs 1604 and may provide runtime power management services. In at least one embodiment, the boot power and management processor may provide clock and voltage programming, assist system low-power state transitions, thermal and temperature sensor management of one or more SoCs 1604s, and / or power state management of one or more SoCs 1604s. In at least one embodiment, each temperature sensor may be implemented with its output frequency proportional to temperature, and one or more SoCs 1604s may use the ring oscillator to detect the temperature of one or more CPUs 1606s, one or more GPUs 1608s, and / or one or more accelerators 1614s. In at least one embodiment, if it is determined that the temperature exceeds a threshold, the startup and power management processor may enter a temperature fault routine and place one or more SoCs 1604s into a lower power state and / or place the vehicle 1600 into a safe stopping pattern for the driver (e.g., bring the vehicle 1600 to a safe stop).

[0225] In at least one embodiment, one or more processors 1610 may further include a set of embedded processors that can be used as an audio processing engine. In at least one embodiment, the audio processing engine may be an audio subsystem capable of providing full hardware support for multi-channel audio through multiple interfaces and a wide and flexible range of audio I / O interfaces. In at least one embodiment, the audio processing engine is a dedicated processor core with a digital signal processor with dedicated RAM.

[0226] In at least one embodiment, one or more processors 1610 may also include an always-on processor engine that can provide the necessary hardware features to support low-power sensor management and wake-up use cases. In at least one embodiment, the processor on the always-on processor engine may include, but is not limited to, a processor core, tightly coupled RAM, peripheral support (e.g., timers and interrupt controllers), various I / O controller peripherals, and routing logic.

[0227] In at least one embodiment, one or more processors 1610 may further include a secure clustering engine, which includes, but is not limited to, a dedicated processor subsystem for handling security management of automotive applications. In at least one embodiment, the secure clustering engine may include, but is not limited to, two or more processor cores, tightly coupled RAM, supporting peripheral devices (e.g., timers, interrupt controllers, etc.) and / or routing logic. In secure mode, in at least one embodiment, the two or more cores may operate in lockstep mode and may be used as a single core with comparison logic for detecting any differences between their operations. In at least one embodiment, one or more processors 1610 may further include a real-time camera engine, which may include, but is not limited to, a dedicated processor subsystem for handling real-time camera management. In at least one embodiment, one or more processors 1610 may further include a high dynamic range signal processor, which may include, but is not limited to, an image signal processor, which is a hardware engine as part of the camera processing pipeline.

[0228] In at least one embodiment, one or more processors 1610 may include a video image synthesizer, which may be a processing block (e.g., implemented on a microprocessor) that implements video post-processing functions required by the video playback application to produce the final image for the player window. In at least one embodiment, the video image synthesizer may perform lens distortion correction on one or more wide-angle cameras 1670, one or more surround cameras 1674, and / or one or more cabin monitoring camera sensors. In at least one embodiment, preferably, the cabin monitoring camera sensors are monitored by a neural network running on another instance of the SoC 1604, the neural network being configured to recognize cabin events and respond accordingly. In at least one embodiment, the cabin system may perform, but is not limited to, lip reading to activate cellular service and make phone calls, instruct emails, change the vehicle's destination, activate or change the vehicle's infotainment system and settings, or provide voice-activated web browsing. In at least one embodiment, certain functions are available to the driver when the vehicle is operating in autonomous mode, and are otherwise disabled.

[0229] In at least one embodiment, the video image synthesizer may include enhanced temporal denoising for simultaneous spatial and temporal denoising. For example, in at least one embodiment, when motion occurs in the video, denoising appropriately weights spatial information, thereby reducing the weight of information provided by adjacent frames. In at least one embodiment, when the image or a portion of the image does not contain motion, temporal denoising performed by the video image synthesizer may use information from previous images to reduce noise in the current image.

[0230] In at least one embodiment, the video image compositor can also be configured to perform stereoscopic correction on the input stereo lens frames. In at least one embodiment, when using an operating system desktop, the video image compositor can also be used for user interface compositing and does not require one or more GPUs 1608 to continuously render new surfaces. In at least one embodiment, when one or more GPUs 1608 are powered and actively performing 3D rendering, the video image compositor can be used to offload one or more GPUs 1608 to improve performance and responsiveness.

[0231] In at least one embodiment, one or more SoCs of SoC 1604 may also include a Mobile Industrial Processor Interface (“MIPI”) camera serial interface, a high-speed interface, and / or a video input block that can be used for receiving video and input from a camera and associated pixel input functions. In at least one embodiment, one or more SoCs of SoC 1604 may also include an input / output controller that can be software controlled and can be used to receive I / O signals not assigned to a specific role.

[0232] In at least one embodiment, one or more SoCs of SoC 1604 may also include extensive peripheral interfaces to enable communication with peripheral devices, audio encoders / decoders (“codecs”), power management and / or other devices. One or more SoCs of SoC 1604 may be used to process data from (e.g., connected via gigabit multimedia serial links and Ethernet channels) cameras, sensors (e.g., one or more LiDAR sensors 1664, one or more RADAR sensors 1660, etc., which may be connected via Ethernet), data from bus 1602 (e.g., vehicle 1600 speed, steering wheel position, etc.), data from one or more GNSS sensors 1658 (e.g., connected via Ethernet bus or CAN bus), etc. In at least one embodiment, one or more SoCs of SoC 1604 may also include a dedicated high-performance mass storage controller, which may include its own DMA engine and may be used to free one or more CPUs 1606 from routine data management tasks.

[0233] In at least one embodiment, one or more SoCs 1604 can be an end-to-end platform with a flexible architecture spanning automation levels 3-5, providing a comprehensive functional safety architecture that leverages and effectively utilizes computer vision and ADAS technologies to achieve diversity and redundancy. This provides a platform offering a flexible and reliable driving software stack as well as deep learning tools. In at least one embodiment, one or more SoCs 1604 can be faster, more reliable, and even more energy and space efficient than conventional systems. For example, in at least one embodiment, one or more accelerators 1614, when combined with one or more CPUs 1606, one or more GPUs 1608, and one or more data storage devices 1616, can provide a fast and efficient platform for Level 3-5 autonomous vehicles.

[0234] In at least one embodiment, the computer vision algorithm can be executed on a CPU, which can be configured using a high-level programming language (e.g., C) to execute multiple processing algorithms on a variety of visual data. However, in at least one embodiment, the CPU typically cannot meet the performance requirements of many computer vision applications, such as performance requirements related to execution time and power consumption. In at least one embodiment, many CPUs cannot execute complex object detection algorithms in real time, algorithms used in automotive ADAS applications and practical Level 3-5 autonomous vehicles.

[0235] The embodiments described herein allow multiple neural networks to be executed simultaneously and / or sequentially, and allow the results to be combined to achieve Level 3-5 autonomous driving capabilities. For example, in at least one embodiment, a CNN executed on a DLA or discrete GPU (e.g., one or more GPU 1620s) may include text and word recognition, thereby allowing a supercomputer to read and understand traffic signs, including signs for which the neural network has not yet been specifically trained. In at least one embodiment, the DLA may also include a neural network capable of recognizing, interpreting, and providing semantic understanding of symbols, and passing this semantic understanding to a path planning module running on a CPU Complex.

[0236] In at least one embodiment, for drives of levels 3, 4, or 5, multiple neural networks can run simultaneously. For example, in at least one embodiment, a warning sign consisting of a light along with the warning sign “Caution: flashing lights indicate icy conditions” can be interpreted independently or jointly by multiple neural networks. In at least one embodiment, the warning sign itself can be identified as a traffic sign by a first deployed neural network (e.g., a trained neural network), and the text “flashing lights indicate icy conditions” can be interpreted by a second deployed neural network, which informs the vehicle’s path planning software (preferably executed on a CPU Complex) that icing conditions exist when flashing lights are detected. In at least one embodiment, flashing lights can be identified by operating a third deployed neural network across multiple frames, informing the vehicle’s path planning software of the presence (or absence) of flashing lights. In at least one embodiment, all three neural networks can run simultaneously, for example within a DLA and / or on one or more GPUs 1608.

[0237] In at least one embodiment, the CNN for facial recognition and vehicle owner identification can use data from camera sensors to identify the presence of an authorized driver and / or the owner of vehicle 1600. In at least one embodiment, a normally open sensor processor engine can be used to unlock the vehicle when the owner approaches the driver's door and turns on the lights, and, in security mode, can be used to disable the vehicle when the owner leaves it. In this way, one or more SoCs 1604 provide protection against theft and / or carjacking.

[0238] In at least one embodiment, the CNN for emergency vehicle detection and identification can use data from microphone 1696 to detect and identify emergency vehicle sirens. In at least one embodiment, one or more SoCs 1604 use the CNN to classify environmental and urban sounds, as well as visual data. In at least one embodiment, the CNN running on DLA is trained to identify the relative approach speed of emergency vehicles (e.g., by using the Doppler effect). In at least one embodiment, the CNN can also be trained to identify emergency vehicles in the area where the vehicle is operating, as identified by one or more GNSS sensors 1658. In at least one embodiment, when operating in Europe, the CNN will seek to detect European sirens, while in the United States the CNN will seek to identify only North American sirens. In at least one embodiment, once an emergency vehicle is detected, a control program can be used, with the assistance of one or more ultrasonic sensors 1662, to execute emergency vehicle safety routines, slow down the vehicle, pull the vehicle to the side of the road, stop, and / or leave the vehicle idle until (one or more) emergency vehicles have passed.

[0239] In at least one embodiment, vehicle 1600 may include one or more CPUs 1618 (e.g., one or more discrete CPUs or one or more dCPUs) that may be coupled to one or more SoCs 1604 via high-speed interconnects (e.g., PCIe). In at least one embodiment, one or more CPUs 1618 may include x86 processors. For example, one or more CPUs 1618 may be used to perform any of the various functions, such as arbitrating the results of potential inconsistencies between ADAS sensors and one or more SoCs 1604, and / or monitoring the status and health of one or more monitoring controllers 1636 and / or on-chip information systems (“information SoCs”) 1630.

[0240] In at least one embodiment, vehicle 1600 may include one or more GPUs 1620 (e.g., one or more discrete GPUs or one or more dGPUs) that may be coupled to one or more SoCs 1604 via a high-speed interconnect (e.g., NVIDIA's NVLINK). In at least one embodiment, one or more GPUs 1620 may provide additional artificial intelligence capabilities, such as by executing redundant and / or different neural networks, and may be used to train and / or update the neural networks based at least in part on inputs from sensors of vehicle 1600 (e.g., sensor data).

[0241] In at least one embodiment, vehicle 1600 may also include a network interface 1624, which may include, but is not limited to, one or more wireless antennas 1626 (e.g., one or more wireless antennas for different communication protocols, such as cellular antennas, Bluetooth antennas, etc.). In at least one embodiment, network interface 1624 may be used to enable wireless connectivity with other vehicles and / or computing devices (e.g., passenger client devices) via an internet cloud (e.g., employing servers and / or other network devices). In at least one embodiment, for communication with other vehicles, a direct link and / or an indirect link (e.g., via a network and the internet) may be established between vehicle 1600 and other vehicles. In at least one embodiment, a vehicle-to-vehicle communication link may be used to provide a direct link. The vehicle-to-vehicle communication link may provide vehicle 1600 with information about vehicles near vehicle 1600 (e.g., vehicles in front, to the side, and / or behind vehicle 1600). In at least one embodiment, the foregoing functionality may be part of a cooperative adaptive cruise control function of vehicle 1600.

[0242] In at least one embodiment, network interface 1624 may include a System-on-Chip (SoC) that provides modulation and demodulation functions and enables one or more controllers 1636 to communicate over a wireless network. In at least one embodiment, network interface 1624 may include a radio frequency (RF) front-end for up-conversion from baseband to RF and down-conversion from RF to baseband. In at least one embodiment, frequency conversion may be performed in any technically feasible manner. For example, frequency conversion may be performed using known processes and / or using a superheterodyne process. In at least one embodiment, the RF front-end functionality may be provided by a separate chip. In at least one embodiment, the network interface may include wireless functions for communication via LTE, WCDMA, UMTS, GSM, CDMA2000, Bluetooth, Bluetooth LE, Wi-Fi, Z-Wave, ZigBee, LoRaWAN, and / or other wireless protocols.

[0243] In at least one embodiment, vehicle 1600 may also include one or more data storage units 1628, which may include, but are not limited to, off-chip (e.g., one or more SoC 1604) storage. In at least one embodiment, one or more data storage units 1628 may include, but are not limited to, one or more storage elements, including RAM, SRAM, dynamic random access memory (“DRAM”), video random access memory (“VRAM”), flash memory, hard disk and / or other components and / or devices capable of storing at least one bit of data.

[0244] In at least one embodiment, the vehicle 1600 may also include one or more GNSS sensors 1658 (e.g., GPS and / or auxiliary GPS sensors) to assist in map creation, perception, occupancy raster generation, and / or path planning functions. In at least one embodiment, any number of GNSS sensors 1658 may be used, including, for example, but not limited to, GPS sensors connected to a serial interface (e.g., RS-232) bridge using a USB connector with Ethernet.

[0245] In at least one embodiment, vehicle 1600 may also include one or more RADAR sensors 1660. The one or more RADAR sensors 1660 can be used by vehicle 1600 for remote vehicle detection, even in dark and / or inclement weather conditions. In at least one embodiment, the RADAR functional safety level may be ASIL B. The one or more RADAR sensors 1660 can use a CAN bus and / or bus 1602 (e.g., to transmit data generated by the one or more RADAR sensors 1660) for control and access to object tracking data, and in some examples, Ethernet may be accessible to access the raw data. In at least one embodiment, a wide variety of RADAR sensor types can be used. For example, but not limited to, one or more RADAR sensors 1660 may be suitable for front, rear, and side RADAR use. In at least one embodiment, one or more RADAR sensors 1660 are pulse Doppler RADAR sensors.

[0246] In at least one embodiment, one or more RADAR sensors 1660 may include different configurations, such as long-range with a narrow field of view, short-range with a wide field of view, short-range side coverage, etc. In at least one embodiment, the long-range RADAR can be used for adaptive cruise control functions. In at least one embodiment, the long-range RADAR system can provide a wide field of view achieved through two or more independent scans (e.g., within a 250m range). In at least one embodiment, one or more RADAR sensors 1660 can help distinguish between stationary and moving objects and can be used by the ADAS system 1638 for emergency braking assistance and forward collision warning. One or more sensors 1660 included in the long-range RADAR system may include, but are not limited to, a monostatic multimode RADAR with multiple (e.g., six or more) fixed RADAR antennas and high-speed CAN and FlexRay interfaces. In at least one embodiment, having six antennas, with the four central antennas, can create a focused beammap designed to record the surrounding environment of the vehicle 1600 at a high speed while minimizing traffic interference from adjacent lanes. In at least one embodiment, the other two antennas can expand the field of view, thereby enabling rapid detection of vehicles entering or leaving the lane 1600.

[0247] In at least one embodiment, as an example, a mid-range RADAR system may include, for example, a range of up to 160m (front) or 80m (rear), and a field of view of up to 42 degrees (front) or 150 degrees (rear). In at least one embodiment, a short-range RADAR system may include, but is not limited to, any number of RADAR sensors 1660 designed to be mounted at both ends of the rear bumper. When mounted at both ends of the rear bumper, in at least one embodiment, the RADAR sensor system may generate two beams that continuously monitor the blind spots at and near the rear of the vehicle. In at least one embodiment, the short-range RADAR system may be used in ADAS system 1638 for blind spot detection and / or lane change assistance.

[0248] In at least one embodiment, the vehicle 1600 may also include one or more ultrasonic sensors 1662. One or more ultrasonic sensors 1662, which may be positioned at the front, rear, and / or sides of the vehicle 1600, can be used for parking assistance and / or creating and updating occupancy detectors. In at least one embodiment, a wide variety of ultrasonic sensors 1662 can be used, and different ultrasonic sensors 1662 can be used for different detection ranges (e.g., 2.5m, 4m). In at least one embodiment, the ultrasonic sensors 1662 can operate at the ASIL B functional safety level.

[0249] In at least one embodiment, vehicle 1600 may include one or more LiDAR sensors 1664. The one or more LiDAR sensors 1664 may be used for object and pedestrian detection, emergency braking, collision avoidance, and / or other functions. In at least one embodiment, the one or more LiDAR sensors 1664 may be of functional safety level ASIL B. In at least one embodiment, vehicle 1600 may include multiple (e.g., two, four, six, etc.) LiDAR sensors 1664 that can use Ethernet (e.g., providing data to a Gigabit Ethernet switch).

[0250] In at least one embodiment, one or more LiDAR sensors 1664 may be able to provide a list of objects and their distances for a 360-degree field of view. In at least one embodiment, one or more commercially available LiDAR sensors 1664 may, for example, have an advertising range of approximately 100m, an accuracy of 2cm-3cm, and support a 100Mbps Ethernet connection. In at least one embodiment, one or more non-protruding LiDAR sensors may be used. In such embodiments, one or more LiDAR sensors 1664 may be implemented as small devices embedded in the front, rear, sides, and / or corners of a vehicle 1600. In at least one embodiment, one or more LiDAR sensors 1664, in such embodiments, can provide a horizontal field of view of up to 120 degrees and a vertical field of view of 35 degrees, even for objects with low reflectivity, and have a range of 200m. In at least one embodiment, one or more forward-facing LiDAR sensors 1664 may be configured for a horizontal field of view between 45 degrees and 135 degrees.

[0251] In at least one embodiment, LIDAR technology (such as 3D flash LIDAR) may also be used. 3D flash LIDAR uses a laser flash as a transmission source to illuminate approximately 200m around the vehicle 1600. In at least one embodiment, the flash LIDAR unit includes, but is not limited to, a receiver that records the laser pulse propagation time and reflected light on each pixel, which in turn corresponds to the range from the vehicle 1600 to the object. In at least one embodiment, flash LIDAR can allow the generation of highly accurate and distortion-free images of the surrounding environment using each laser flash. In at least one embodiment, four flash LIDAR sensors may be deployed, one on each side of the vehicle 1600. In at least one embodiment, the 3D flash LIDAR system includes, but is not limited to, a solid-state 3D line-of-sight array LIDAR camera with no moving parts other than a fan (e.g., a non-scanning LIDAR device). In at least one embodiment, the flash LIDAR device can use a 5-nanosecond Class I (eye-safe) laser pulse per frame and can capture reflected laser light in the form of a 3D ranging point cloud and co-registered intensity data.

[0252] In at least one embodiment, vehicle 1600 may further include one or more IMU sensors 1666. In at least one embodiment, one or more IMU sensors 1666 may be located at the center of the rear axle of vehicle 1600. In at least one embodiment, one or more IMU sensors 1666 may include, for example, but not limited to, one or more accelerometers, one or more magnetometers, one or more gyroscopes, a magnetic compass, multiple magnetic compasses, and / or other sensor types. In at least one embodiment, for example in a six-axis application, one or more IMU sensors 1666 may include, but are not limited to, accelerometers and gyroscopes. In at least one embodiment, for example in a nine-axis application, one or more IMU sensors 1666 may include, but are not limited to, accelerometers, gyroscopes, and magnetometers.

[0253] In at least one embodiment, one or more IMU sensors 1666 may be implemented as a miniature, high-performance GPS-assisted inertial navigation system (“GPS / INS”) combining a microelectromechanical system (“MEMS”) inertial sensor, a high-sensitivity GPS receiver, and an advanced Kalman filtering algorithm to provide position, velocity, and attitude estimations; in at least one embodiment, one or more IMU sensors 1666 may enable vehicle 1600 to estimate heading without input from a magnetic sensor obtained by directly observing and correlating velocity changes from GPS to one or more IMU sensors 1666. In at least one embodiment, one or more IMU sensors 1666 and one or more GNSS sensors 1658 may be combined in a single integrated unit.

[0254] In at least one embodiment, vehicle 1600 may include one or more microphones 1696 placed inside and / or around vehicle 1600. In at least one embodiment, in addition, one or more microphones 1696 may be used for emergency vehicle detection and identification.

[0255] In at least one embodiment, vehicle 1600 may also include any number of camera types, including one or more stereo cameras 1668, one or more wide-angle cameras 1670, one or more infrared cameras 1672, one or more surround cameras 1674, one or more long-range cameras 1698, one or more mid-range cameras 1676, and / or other camera types. In at least one embodiment, the cameras can be used to capture image data around the entire perimeter of vehicle 1600. In at least one embodiment, the type of camera used depends on vehicle 1600. In at least one embodiment, any combination of camera types can be used to provide the necessary coverage around vehicle 1600. In at least one embodiment, the number of cameras deployed may vary depending on the embodiment. For example, in at least one embodiment, vehicle 1600 may include six cameras, seven cameras, ten cameras, twelve cameras, or other numbers of cameras. The cameras may be examples, but are not limited to, supporting Gigabit Multimedia Serial Link (“GMSL”) and / or Gigabit Ethernet. In at least one embodiment, references previously made herein... Figure 16A and Figure 16B Each camera can be described in more detail.

[0256] In at least one embodiment, the vehicle 1600 may also include one or more vibration sensors 1642. In at least one embodiment, the one or more vibration sensors 1642 can measure vibrations of components of the vehicle 1600 (e.g., axles). For example, in at least one embodiment, changes in vibration can indicate changes in road surface conditions. In at least one embodiment, when two or more vibration sensors 1642 are used, differences between vibrations can be used to determine road surface friction or slippage (e.g., when there is a vibration difference between a power drive axle and a free-rotating axle).

[0257] In at least one embodiment, vehicle 1600 may include ADAS system 1638. ADAS system 1638 may include, but is not limited to, SoC. In at least one embodiment, ADAS system 1638 may include, but is not limited to, any number of autonomous / adaptive / automatic cruise control (“ACC”) systems, cooperative adaptive cruise control (“CACC”) systems, forward collision warning (“FCW”) systems, automatic emergency braking (“AEB”) systems, lane departure warning (“LDW”) systems, lane keeping assist (“LKA”) systems, blind spot warning (“BSW”) systems, rear cross traffic warning (“RCTW”) systems, collision warning (“CW”) systems, lane centering (“LC”) systems, and / or other systems, features, and / or functions, and combinations thereof.

[0258] In at least one embodiment, the ACC system may use one or more RADAR sensors 1660, one or more LIDAR sensors 1664, and / or any number of cameras. In at least one embodiment, the ACC system may include a longitudinal ACC system and / or a lateral ACC system. In at least one embodiment, the longitudinal ACC system monitors and controls the distance to vehicles adjacent to vehicle 1600 and automatically adjusts the speed of vehicle 1600 to maintain a safe distance from the vehicle ahead. In at least one embodiment, the lateral ACC system performs distance holding and suggests that vehicle 1600 change lanes when necessary. In at least one embodiment, lateral ACC is associated with other ADAS applications, such as LC and CW.

[0259] In at least one embodiment, the CACC system uses information from other vehicles, which may be received from other vehicles via network interface 1624 and / or one or more wireless antennas 1626 via a wireless link or indirectly via a network connection (e.g., via the Internet). In at least one embodiment, the direct link may be provided by a vehicle-to-vehicle (“V2V”) communication link, while the indirect link may be provided by an infrastructure-to-vehicle (“I2V”) communication link. Typically, the V2V communication concept provides information about the vehicle immediately preceding it (e.g., a vehicle immediately in front of vehicle 1600 and in the same lane as it), while the I2V communication concept provides information about traffic further ahead. In at least one embodiment, the CACC system may include one or both of the I2V and V2V information sources. In at least one embodiment, given information about vehicles preceding vehicle 1600, the CACC system can be more reliable and has the potential to improve traffic flow smoothness and reduce road congestion.

[0260] In at least one embodiment, the FCW system is designed to warn the driver of danger so that the driver can take corrective action. In at least one embodiment, the FCW system uses a forward-facing camera and / or one or more RADAR sensors 1660, coupled to a dedicated processor, DSP, FPGA, and / or ASIC, electrically coupled to driver feedback, such as a display, speaker, and / or vibration components. In at least one embodiment, the FCW system can provide warnings, for example, in the form of audible, visual, haptic, and / or rapid braking pulses.

[0261] In at least one embodiment, the AEB system detects an impending forward collision with another vehicle or other object and can automatically apply brakes if the driver does not take corrective action within a specified time or distance parameter. In at least one embodiment, the AEB system may use one or more forward-facing cameras and / or one or more RADAR sensors 1660 coupled to a dedicated processor, DSP, FPGA, and / or ASIC. In at least one embodiment, when the AEB system detects a hazard, it typically first warns the driver to take corrective action to avoid a collision, and if the driver does not take corrective action, the AEB system can automatically apply brakes to attempt to prevent or at least mitigate the effects of the predicted collision. In at least one embodiment, the AEB system may include techniques such as dynamic braking to support and / or brakes for impending collisions.

[0262] In at least one embodiment, when vehicle 1600 crosses lane markings, the LDW system provides visual, auditory, and / or tactile warnings, such as steering wheel or seat vibrations, to alert the driver. In at least one embodiment, the LDW system is inactive when the driver indicates intentional lane departure, such as by activating turn signals. In at least one embodiment, the LDW system may use a front-facing camera coupled to a dedicated processor, DSP, FPGA, and / or ASIC, which is electrically coupled to provide driver feedback such as a display, speaker, and / or vibration components. The LKA system is a variant of the LDW system. In at least one embodiment, if vehicle 1600 begins to leave the lane, the LKA system provides steering input or braking to correct vehicle 1600.

[0263] In at least one embodiment, the BSW system detects and warns the driver of a vehicle in the blind spot. In at least one embodiment, the BSW system can provide visual, auditory, and / or tactile alerts to indicate that merging or changing lanes is unsafe. In at least one embodiment, the BSW system can provide additional warnings when the driver uses the turn signal. In at least one embodiment, the BSW system can use one or more rear-facing cameras and / or one or more RADAR sensors 1660 coupled to a dedicated processor, DSP, FPGA, and / or ASIC, electrically coupled to driver feedback, such as a display, speaker, and / or vibration assembly.

[0264] In at least one embodiment, the RCTW system can provide visual, auditory, and / or tactile notifications when an object is detected outside the range of the rear camera while the vehicle 1600 is reversing. In at least one embodiment, the RCTW system includes an AEB system to ensure the application of the vehicle brakes to avoid a collision. In at least one embodiment, the RCTW system may use one or more rear-facing RADAR sensors 1660 coupled to a dedicated processor, DSP, FPGA, and / or ASIC, which are electrically coupled to driver feedback such as a display, speaker, and / or vibration assembly.

[0265] In at least one embodiment, conventional ADAS systems may be prone to generating false alarms, which can be annoying and distracting to the driver, but are generally not catastrophic because conventional ADAS systems warn the driver and allow the driver to determine whether a safe situation truly exists and take appropriate action. In at least one embodiment, in the event of conflicting results, the vehicle 1600 itself decides whether to follow the result of the primary computer or the secondary computer (e.g., the first controller 1636 or the second controller 1636). For example, in at least one embodiment, ADAS system 1638 may be a backup and / or auxiliary computer for providing perception information to a backup computer rationality module. In at least one embodiment, the backup computer rationality monitor may run redundant software on hardware components to detect faults in perception and dynamic driving tasks. In at least one embodiment, the output from ADAS system 1638 may be provided to a monitoring MCU. In at least one embodiment, if the outputs from the primary computer and the auxiliary computer conflict, the monitoring MCU decides how to reconcile the conflict to ensure safe operation.

[0266] In at least one embodiment, the master computer may be configured to provide a confidence score to the supervisory MCU to indicate the master computer's confidence in the selected result. In at least one embodiment, if the confidence score exceeds a threshold, the supervisory MCU may follow the master computer's instructions regardless of whether the auxiliary computer provides conflicting or inconsistent results. In at least one embodiment, if the confidence score does not meet the threshold, and if the master computer and the auxiliary computer indicate different results (e.g., conflicting), the supervisory MCU may arbitrate between the computers to determine the appropriate result.

[0267] In at least one embodiment, the supervisory MCU may be configured to run a neural network trained and configured to determine, at least in part, the conditions under which the auxiliary computer provides a false alarm based on outputs from both the host computer and the auxiliary computer. In at least one embodiment, the neural network in the supervisory MCU may learn when the output of the auxiliary computer can be trusted and when it cannot. For example, in at least one embodiment, when the auxiliary computer is a RADAR-based FCW system, the neural network in the supervisory MCU may learn when the FCW system recognizes a metallic object that is not actually dangerous, such as a drain grat or manhole cover that would trigger an alarm. In at least one embodiment, when the auxiliary computer is a camera-based LDW system, the neural network in the supervisory MCU may learn to override the LDW when a cyclist or pedestrian is present and lane departure is actually the safest operation. In at least one embodiment, the supervisory MCU may include at least one of a DLA or GPU suitable for running a neural network with associated memory. In at least one embodiment, the supervisory MCU may include and / or be included as a component of one or more SoC 1604s.

[0268] In at least one embodiment, the ADAS system 1638 may include an auxiliary computer that performs ADAS functions using conventional computer vision rules. In at least one embodiment, the auxiliary computer may use classic computer vision rules (if-then), and the presence of a neural network in the supervisory MCU can improve reliability, security, and performance. For example, in at least one embodiment, diverse implementations and intentional non-identity make the entire system more fault-tolerant, especially for failures caused by software (or software-hardware interface) functionality. For example, in at least one embodiment, if a software vulnerability or bug exists in the software running on the host computer, and different software code running on the auxiliary computer provides the same overall result, the supervisory MCU can more confidently assume that the overall result is correct and that the vulnerability in the software or hardware on the host computer will not lead to a significant error.

[0269] In at least one embodiment, the output of the ADAS system 1638 can be input to the perception module and / or the dynamic driving task module of the host computer. For example, in at least one embodiment, if the ADAS system 1638 indicates a forward collision warning due to an object directly ahead, the perception block can use this information when identifying the object. In at least one embodiment, as described herein, the assistance computer can have its own neural network trained to reduce the risk of false alarms.

[0270] In at least one embodiment, vehicle 1600 may also include an infotainment SoC 1630 (e.g., an in-vehicle infotainment system (IVI)). Although shown and described as an SoC, in at least one embodiment, the infotainment system SoC 1630 may not be an SoC and may include, but is not limited to, two or more discrete components. In at least one embodiment, the infotainment SoC 1630 may include, but is not limited to, a combination of hardware and software that can be used to provide audio (e.g., music, personal digital assistant, navigation instructions, news, radio, etc.), video (e.g., television, movies, streaming media, etc.), telephone (e.g., hands-free calling), network connectivity (e.g., LTE, WiFi, etc.) and / or information services (e.g., navigation systems, rear parking assist, radio data systems, vehicle-related information such as fuel level, total coverage distance, brake fuel level, fuel level, door opening / closing, air filter information, etc.) to vehicle 1600. For example, the infotainment SoC 1630 may include a radio, disk player, navigation system, video player, USB and Bluetooth connectivity, automotive, in-vehicle entertainment system, WiFi, steering wheel audio controls, hands-free voice control, head-up display (“HUD”), HMI display 1634, telematics device, control panel (e.g., for controlling and / or interacting with various components, features and / or systems) and / or other components. In at least one embodiment, the infotainment SoC 1630 may be further used to provide information (e.g., visual and / or auditory) to a user of vehicle 1600, such as information from ADAS system 1638, autonomous driving information (such as planned vehicle maneuvers), trajectory, surrounding environment information (e.g., intersection information, vehicle information, road information, etc.) and / or other information.

[0271] In at least one embodiment, the infotainment SoC 1630 may include any number and type of GPU functionality. In at least one embodiment, the infotainment SoC 1630 may communicate with other devices, systems, and / or components of the vehicle 1600 via a bus 1602 (e.g., CAN bus, Ethernet, etc.). In at least one embodiment, the infotainment SoC 1630 may be coupled to a monitoring MCU, enabling the GPU of the infotainment system to perform some autonomous driving functions in the event of a failure of the main controller 1636 (e.g., the main computer and / or backup computer of the vehicle 1600). In at least one embodiment, the infotainment SoC 1630 may cause the vehicle 1600 to enter a driver-to-safe-stop mode, as described herein.

[0272] In at least one embodiment, vehicle 1600 may also include instrument panel 1632 (e.g., digital instrument panel, electronic instrument panel, digital instrument control panel, etc.). In at least one embodiment, instrument panel 1632 may include, but is not limited to, controllers and / or supercomputers (e.g., discrete controllers or supercomputers). In at least one embodiment, instrument panel 1632 may include, but is not limited to, any number and combination of a set of instruments, such as speedometer, fuel level, oil pressure, tachometer, odometer, turn indicator, shift position indicator, one or more seatbelt warning lights, one or more parking brake warning lights, one or more engine malfunction lights, auxiliary restraint system (e.g., airbag) information, lighting controls, safety system controls, navigation information, etc. In some examples, information may be displayed and / or shared between infotainment SoC 1630 and instrument panel 1632. In at least one embodiment, instrument panel 1632 may be included as part of infotainment SoC 1630, or vice versa.

[0273] The inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. The following is in conjunction with... Figure 7A and / or Figure 7B Details are provided regarding the inference and / or training logic 715. In at least one embodiment, the inference and / or training logic 715 may be used in System Figure 16A to infer or predict operations based at least in part on weight parameters computed using neural network training operations, neural network functions and / or architectures, or neural network use cases described herein.

[0274] Figure 16B It is based on at least one embodiment in a cloud-based server and Figure 16AA diagram of a system 1676 for communication between autonomous vehicles 1600. In at least one embodiment, system 1676 may include, but is not limited to, one or more servers 1678, one or more networks 1690, and any number and type of vehicles, including vehicle 1600. In at least one embodiment, one or more servers 1678 may include, but is not limited to, multiple GPUs 1684(A)-1684(H) (collectively referred to herein as GPU 1684), PCIe switches 1682(A)-1682(D) (collectively referred to herein as PCIe switch 1682), and / or CPUs 1680(A)-1680(B) (collectively referred to herein as CPU 1680). GPU 1684, CPU 1680, and PCIe switch 1682 may be interconnected with high-speed cables, such as, but not limited to, NVLink interface 1688 developed by NVIDIA and / or PCIe connection 1686. The GPU 1684 is connected via NVLink and / or NVSwitchSoC, and the GPU 1684 and PCIe switch 1682 are connected via PCIe interconnect. In at least one embodiment, although eight GPUs 1684, two CPUs 1680, and four PCIe switches 1682 are shown, this is not intended to be limiting. In at least one embodiment, each of one or more servers 1678 may include, but is not limited to, any combination of any number of GPUs 1684, CPUs 1680, and / or PCIe switches 1682. For example, in at least one embodiment, one or more servers 1678 may each include eight, sixteen, thirty-two, and / or more GPUs 1684.

[0275] In at least one embodiment, one or more servers 1678 may receive image data representing an image from a vehicle via one or more networks 1690, the image showing unexpected or changed road conditions, such as recently commenced roadworks. In at least one embodiment, one or more servers 1678 may transmit an updated neural network 1692 and / or map information 1694, including but not limited to information about traffic and road conditions, to the vehicle via one or more networks 1690. In at least one embodiment, updating the map information 1694 may include, but is not limited to, updating the HD map 1622, such as information about construction sites, potholes, sidewalks, floods, and / or other obstacles. In at least one embodiment, the neural network 1692, the updated neural network 1692, and / or the map information 1694 may be generated from new training and / or experience represented by data received from any number of vehicles in the environment, and / or at least based on training performed in a data center (e.g., using one or more servers 1678 and / or other servers).

[0276] In at least one embodiment, one or more servers 1678 can be used to train a machine learning model (e.g., a neural network) at least in part based on training data. In at least one embodiment, the training data can be generated by the vehicle, and / or can be generated in a simulation (e.g., using a game engine). In at least one embodiment, any amount of training data is labeled (e.g., where the associated neural network benefits from supervised learning) and / or undergoes other preprocessing. In at least one embodiment, no amount of training data is labeled and / or preprocessed (e.g., where the associated neural network does not require supervised learning). In at least one embodiment, once the machine learning model is trained, the machine learning model can be used by the vehicle (e.g., transmitted to the vehicle via one or more networks 1690), and / or the machine learning model can be used by one or more servers 1678 to remotely monitor the vehicle.

[0277] In at least one embodiment, one or more servers 1678 may receive data from the vehicle and apply the data to a state-of-the-art real-time neural network for real-time intelligent inference. In at least one embodiment, one or more servers 1678 may include a deep learning supercomputer and / or a dedicated AI computer powered by one or more GPUs 1684, such as the DGX and DGX Station machines developed by NVIDIA. However, in at least one embodiment, one or more servers 1678 may include a deep learning infrastructure in a data center using CPU power.

[0278] In at least one embodiment, the deep learning infrastructure of one or more servers 1678 may be capable of fast, real-time inference and can use this capability to assess and verify the health of the processor, software, and / or associated hardware in vehicle 1600. For example, in at least one embodiment, the deep learning infrastructure may receive periodic updates from vehicle 1600, such as image sequences and / or objects located by vehicle 1600 in the image sequence (e.g., via computer vision and / or other machine learning object classification techniques). In at least one embodiment, the deep learning infrastructure may run its own neural network to identify objects and compare them with objects identified by vehicle 1600, and if the results do not match and the deep learning infrastructure determines that the AI ​​in vehicle 1600 is malfunctioning, one or more servers 1678 may signal to vehicle 1600 to instruct the fail-safe computer of vehicle 1600 to take control, notify passengers, and complete a safe stopping operation.

[0279] In at least one embodiment, one or more servers 1678 may include one or more GPUs 1684 and one or more programmable inference accelerators (e.g., NVIDIA's TensorRT 3 devices). In at least one embodiment, the combination of GPU-driven servers and inference acceleration enables real-time response. In at least one embodiment, for example, where performance is less critical, servers driven by CPUs, FPGAs, and other processors may be used for inference. In at least one embodiment, inference and / or training logic 715 is used to execute one or more embodiments. Details regarding the inference and / or training logic 715 are incorporated below. Figure 7A Provided with and / or 7B.

[0280] Other variations are within the spirit of this disclosure. Therefore, although the disclosed technology is readily adaptable to various modifications and alternative constructions, certain embodiments thereof are illustrated in the accompanying drawings and have been described in detail above. However, it should be understood that the disclosure is not intended to be limited to one or more specific forms disclosed, but rather, it is intended to cover all modifications, alternative constructions, and equivalents falling within the spirit and scope of this disclosure as defined in the appended claims.

[0281] Unless otherwise stated or obviously contradicted by the context, the terms “a,” “an,” and “the,” and similar references, used in the context of describing the disclosed embodiments (particularly in the context of the appended claims), should be interpreted as encompassing both singular and plural forms, rather than as definitions of terms. Unless otherwise stated, the terms “comprising,” “having,” “including,” and “containing” should be interpreted as open-ended terms (meaning “including, but not limited to”). The term “connection” (referring to a physical connection when unmodified) should be interpreted as partially or wholly contained, attached to, or joined together, even with some intervention. Unless otherwise indicated herein, references to numerical ranges herein are intended only as a way of abbreviating each individual value falling within that range, and each individual value is incorporated into the specification as if it were separately described herein. Unless otherwise indicated or contradicted by the context, the use of the terms “set” (e.g., “item set”) or “subset” should be interpreted as a non-empty set comprising one or more members. Furthermore, unless otherwise indicated or contradicted by the context, the term “subset” of the corresponding set does not necessarily mean an appropriate subset of the corresponding set, but rather that the subset and the corresponding set can be equal.

[0282] Unless otherwise explicitly stated or clearly contradicted by the context, connective phrases such as “at least one of A, B, and C” or “at least one of A, B, and C” are understood in the context to generally refer to items, terms, etc., which can be A or B or C, or any non-empty subset of the set A, B, and C. For example, in an illustrative example of a set with three members, the connective phrases “at least one of A, B, and C” and “at least one of A, B, and C” refer to any of the following sets: {A}, {B}, {C}, {A, B}, {A, C}, {B, C}, {A, B, C}. Therefore, such connective language is generally not intended to imply that some embodiments require the presence of at least one of A, at least one of B, and at least one of C. Additionally, unless otherwise stated or contradicted by the context, the term “multiple” indicates a plural state (e.g., “multiple items” means multiple items). Multiple means at least two items, but more may be indicated if explicitly stated or by the context. Furthermore, unless otherwise stated or clearly understood from the context, the phrase “based on” means “at least partially based on” rather than “based on only”.

[0283] Unless otherwise stated herein or clearly contradicted by the context, the operations of the processes described herein may be performed in any suitable order. In at least one embodiment, processes such as those described herein (or variations thereof and / or combinations thereof) are executed under the control of one or more computer systems configured with executable instructions and are implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) that are executed jointly on one or more processors via hardware or a combination thereof. In at least one embodiment, the code is stored on a computer-readable storage medium, for example, in the form of a computer program comprising a plurality of instructions executable by one or more processors. In at least one embodiment, the computer-readable storage medium is a non-transitory computer-readable storage medium that excludes transient signals (e.g., propagating transient electrical or electromagnetic transmissions) but includes non-transitory data storage circuitry (e.g., buffers, caches, and queues). In at least one embodiment, code (e.g., executable code or source code) is stored on one or more non-transitory computer-readable storage media (or other memory for storing executable instructions) on which executable instructions are stored, which, when executed by one or more processors of a computer system (i.e., as a result of execution), cause the computer system to perform the operations described herein. In at least one embodiment, the set of non-transitory computer-readable storage media comprises multiple non-transitory computer-readable storage media, and one or more of the individual non-transitory storage media lack all the code, but the multiple non-transitory computer-readable storage media collectively store all the code. In at least one embodiment, the executable instructions are executed such that different instructions are executed by different processors; for example, the non-transitory computer-readable storage media store the instructions, and the main central processing unit (“CPU”) executes some instructions while the graphics processing unit (“GPU”) executes other instructions. In at least one embodiment, different components of the computer system have separate processors, and the different processors execute different subsets of the instructions.

[0284] Therefore, in at least one embodiment, the computer system is configured to implement one or more services that perform the operations of the processes described herein, either individually or collectively, and such a computer system is configured with suitable hardware and / or software to enable the implementation of the operations. Furthermore, the computer system implementing at least one embodiment of this disclosure is a single device, and in another embodiment it is a distributed computer system comprising multiple devices operating in different ways, such that the distributed computer system performs the operations described herein, and that a single device does not perform all the operations.

[0285] The use of any and all examples or exemplary language (e.g., “such as”) provided herein is intended only to better illustrate embodiments of this disclosure and does not constitute a limitation on the scope of the disclosure unless otherwise required. No language in the specification should be construed as indicating that any unclaimed element is essential to the practice of the disclosure.

[0286] All references cited in this article, including publications, patent applications and patents, are incorporated herein by reference as if each reference were individually and specifically indicated to be incorporated herein by reference and the entire contents of which are described herein.

[0287] The terms “coupled” and “connected”, as well as their derivatives, may be used in the specification and claims. It should be understood that these terms may not be intended to be synonyms with each other. Rather, in certain examples, “connected” or “coupled” may be used to indicate that two or more elements are in direct or indirect physical or electrical contact with each other. “Coupled” may also mean that two or more elements are not in direct contact with each other, but still cooperate or interact with each other.

[0288] Unless otherwise expressly stated, it will be understood that throughout this specification, terms such as “processing,” “computing,” “determining,” etc., refer to the actions and / or processes of a computer or computing system or similar electronic computing device that process and / or convert data represented as physical quantities (e.g., electrons) in the registers and / or memory of the computing system into other data represented as physical quantities in the memory, registers, or other such information storage, transmission, or display devices of the computing system.

[0289] In a similar manner, the term "processor" can refer to any device or part of memory that processes electronic data from registers and / or memory and converts that electronic data into other electronic data that can be stored in registers and / or memory. As a non-limiting example, a "processor" can be a CPU or a GPU. A "computing platform" can include one or more processors. As used herein, a "software" process can include, for example, software and / or hardware entities that perform work over time, such as tasks, threads, and intelligent agents. Similarly, each process can refer to multiple processes that execute instructions sequentially or intermittently, sequentially, or in parallel. The terms "system" and "method" are used interchangeably herein, provided that a system can embody one or more methods, and a method can be considered a system.

[0290] This document refers to the process of acquiring, obtaining, receiving, or inputting analog or digital data into a subsystem, computer system, or computer-implemented machine. Acquiring, obtaining, receiving, or inputting analog and digital data can be accomplished in various ways, such as by receiving data as a parameter to a function call or an application programming interface (API) call. In some implementations, the process of acquiring, obtaining, receiving, or inputting analog or digital data can be accomplished by transmitting data via a serial or parallel interface. In another implementation, the process of acquiring, obtaining, receiving, or inputting analog or digital data can be accomplished by transmitting data from a providing entity to an acquiring entity via a computer network. Reference can also be made to providing, outputting, transmitting, sending, or presenting analog or digital data. In various examples, the process of providing, outputting, transmitting, sending, or presenting analog or digital data can be implemented by transmitting data as an input or output parameter to a function call, an API call, or an inter-process communication mechanism.

[0291] While the discussion above illustrates example implementations of the described technologies, other architectures can be used to implement the described functionality and are intended to fall within the scope of this disclosure. Furthermore, although specific assignments of responsibilities have been defined above for discussion purposes, various functions and responsibilities can be assigned and divided in different ways depending on the circumstances.

[0292] Furthermore, although the subject matter has been described in language specific to structural features and / or methodological actions, it should be understood that the subject matter claimed in the appended claims is not necessarily limited to the specific features or actions described. Rather, specific features and actions are disclosed as exemplary forms for implementing the claims.

Claims

1. A computer-implemented method, comprising: Identify a set of facial landmarks in the image using an image representation that includes a human face; Determine the behavioral data of the person in at least a first portion of the image; Determine eye state information indicating whether the person's eyes are open or closed from at least a second portion of the image; The head posture information of the person is determined at least in part based on the facial landmarks; Based at least in part on the set of facial landmarks, the head posture information, and the eye state information, a set of blinking parameters of the person over a recent period of time is determined; The blink frequency information over the recent period is determined using the eye state information; The set of blink parameters is provided as input to the first time network, and the blink frequency information is provided as input to the second time network. A first drowsiness prediction for the person is generated using the first temporal network, and a second drowsiness prediction for the person is generated using the second temporal network, wherein at least one of the first drowsiness prediction or the second drowsiness prediction is normalized based at least on the behavioral data; as well as The overall drowsiness determination of the person is generated based at least in part on the first drowsiness prediction and the second drowsiness prediction.

2. The computer-implemented method according to claim 1 further includes: Detect the portion of the image that corresponds to the person's face; as well as Identify the set of facial landmarks from the portion of the image.

3. The computer-implemented method according to claim 1 further includes: A subset of the facial landmarks is used to identify one or more eye regions to be used to determine the eye state information.

4. The computer-implemented method of claim 1, wherein the first temporal network and the second temporal network are Long Short-Term Memory (LSTM) networks, and wherein the first drowsiness prediction and the second drowsiness prediction generated by the LSTM network correspond to Karolinska Sleepiness Scale (KSS) values.

5. The computer-implemented method according to claim 1, further comprising: The image is used to identify the person; Identify a blink profile of the person that indicates one or more blinking behaviors; as well as Further, at least the first drowsiness prediction is generated based on the data from the one or more blinking behaviors.

6. The computer-implemented method according to claim 1, wherein, The set of blink parameters includes at least blink amplitude, blink duration, or blink speed.

7. The computer-implemented method according to claim 1, further comprising: The transformation of the set of facial landmarks is performed, at least in part, based on the head pose information, in order to adjust the orientation of the set of facial landmarks.

8. The computer-implemented method according to claim 1, wherein, The eye state information is determined based on one or more eye portions of the image and independently of the set of facial landmarks.

9. The computer-implemented method according to claim 1, wherein, At least one subset of the set of blink parameters is determined using aspect ratio information calculated from the set of facial landmarks.

10. A system comprising at least one processor to perform the following operations: A face detection network is used to identify the parts of an image that correspond to the face of a person inside the machine and to determine the person's behavioral data. A facial landmark detection network is used to identify multiple facial landmarks present in the portion of the image corresponding to the face; The eye state of the person is determined from the image using an eye state network, the eye state corresponding at least to being open or closed; A first drowsiness prediction of the person is generated using a first temporal network based at least in part on a set of blink parameters determined from the plurality of facial landmarks, and a second drowsiness prediction of the person is generated using a second temporal network based at least in part on a blink frequency determined using the eye state. as well as The processor is used to perform one or more control operations on the machine based at least on one or more of the first drowsiness prediction and the second drowsiness prediction.

11. The system of claim 10, further comprising: The facial recognition module is used to determine the identity of the person and to determine a blink profile indicating one or more blinking behaviors of the person for at least generating the first drowsiness prediction.

12. The system of claim 10, wherein the first temporal network and the second temporal network are Long Short-Term Memory (LSTM) networks, and wherein the first drowsiness prediction and the second drowsiness prediction generated by the LSTM network correspond to Karolinska Sleepiness Scale (KSS) values.

13. The system according to claim 10, wherein the operation further comprises: A head pose determination network is used to determine the head pose information of the person using the plurality of facial landmarks, wherein the first time network is used to perform transformations on the plurality of facial landmarks based at least in part on the head pose information in order to adjust the orientation of the plurality of facial landmarks.

14. The system according to claim 10, wherein, At least one subset of the set of blink parameters is determined using aspect ratio information calculated from the set of facial landmarks.

15. The system according to claim 10, wherein, The system includes at least one of the following: A system used to perform simulation operations; A system used to perform simulations to test or validate autonomous machine applications; A system used for rendering graphics output; A system used to perform deep learning operations; Systems implemented using edge devices; A system containing one or more virtual machines (VMs); A system that is at least partially implemented in a data center; or A system that utilizes cloud computing resources at least in part.

16. A drowsiness detection system, comprising: A camera, used to capture image data, including a representation of a person's face over a period of time; One or more processors; as well as The memory includes instructions that, when executed by the one or more processors, cause the system to: Identify a set of facial landmarks in an image that includes a representation of a human face; Determine the behavioral data of the person in at least a first portion of the image; Determine eye state information, at least indicating whether the person's eyes are open or closed, from at least a second portion of the image; The head posture information of the person is determined at least in part based on the facial landmarks; Based at least in part on the set of facial landmarks, the head posture information, and the eye state information, a set of blinking parameters of the person over a recent period of time is determined; The blink frequency information over the recent period is determined using the eye state information; A first drowsiness prediction of the person is determined using a first time network and at least based on the set of blink parameters as input to the first time network, and a second drowsiness prediction of the person is determined using a second time network and at least based on the blink frequency information applied to the second time network, wherein at least one of the first drowsiness prediction or the second drowsiness prediction is normalized at least based on the behavioral data. as well as The overall drowsiness determination of the person is generated based at least in part on the first drowsiness prediction and the second drowsiness prediction.

17. The drowsiness detection system according to claim 16, wherein, If the instruction is executed, the drowsiness detection system is further configured to: The determination of at least one action to be taken against the person is based at least in part on the determination of overall drowsiness.

18. The drowsiness detection system according to claim 16, wherein, If the instruction is executed, the drowsiness detection system is further configured to: The image is used to identify the person; Identify a blink profile of the person that indicates one or more blinking behaviors; as well as Further, at least the first drowsiness prediction is generated based on the data from the one or more blinking behaviors.

19. The drowsiness detection system according to claim 16, wherein, If the instruction is executed, the drowsiness detection system is further configured to: The transformation of the set of facial landmarks is performed, at least in part, based on the head pose information, in order to adjust the orientation of the set of facial landmarks.

20. The drowsiness detection system according to claim 16, wherein, The first temporal network and the second temporal network are Long Short-Term Memory (LSTM) networks, and the first drowsiness prediction and the second drowsiness prediction generated by the LSTM networks correspond to Karolinska Sleepiness Scale (KSS) values.

Images