Quality assessment of stitching of surround view system

Abstract

The present disclosure relates to stitch quality assessment of a surround view system. Stitching a plurality of images into a composite representation can be performed using a set of stitching parameters determined based at least in part on a subjective stitch quality assessment value. The stitched image can be compared to its constituent images to obtain one or more objective quality indicators. These objective quality indicators can be provided as input to a trained classifier, which can infer a subjective quality assessment indicator for the stitched (or otherwise synthesized) image. This subjective quality assessment indicator can be used to adjust one or more synthesis parameter values so that at least a minimum subjective quality assessment value can be provided for the synthesized image.

Description

Background Technology

[0001] As technology is increasingly used in fully or semi-automated tasks, such as those related to autonomous driving and robotics, the need for accurate information relating to the operation of that technology also increases. This could include, for example, capturing real-time video of the environment in which the technology is operating and providing an accurate video representation. To provide a view-consistent representation, video data captured from multiple cameras can be combined through processes such as image stitching to create composite or compound representations. Unfortunately, it is difficult to stitch together random, complex scenes in a realistic manner without glaring seams or image artifacts. 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 An example of an autonomous vehicle according to at least one embodiment is shown, along with an example camera position and field of view of the autonomous vehicle;

[0004] Figure 2A and 2B The image shown is a stitched and composite image that can be generated according to at least one embodiment;

[0005] Figure 3 An example view generator that can be used according to at least one embodiment is shown;

[0006] Figure 4A and 4B Synthetic images with different subjective quality judgments according to at least one embodiment are shown;

[0007] Figure 5 The process of adjusting splicing parameters using splicing quality assessment metrics according to at least one embodiment is illustrated;

[0008] Figure 6 Components of a system for encoding and transmitting image data 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 10 A 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, tuning, 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 an autonomous vehicle system according to at least one embodiment are shown. Detailed Implementation

[0020] Methods according to various embodiments can provide the generation, editing, or manipulation of image or video data. In particular, various embodiments use a stitching system having parameters determined, updated, and / or optimized using at least one stitching quality evaluation metric to provide the generation of synthetic image or video data. This may include, for example, but not limited to, stitching individual frames in a video sequence such that each video frame provides a larger field of view, such as 180 degrees or 360 degrees, than any single frame of the frames to be stitched together. At least some pixels may also have their color values ​​blended during the stitching or compositing process. Objective differences between the stitched image and its constituent images can be calculated and fed into a classifier. The classifier can be trained to infer values ​​using these values, such as subjective stitching quality evaluation values, which provide a measure of the subjective quality of the stitched image, possibly provided by the viewer of the image. The subjective stitching quality evaluation values ​​can be fed back to the stitching module, which, for example, can adjust one or more stitching parameters as needed to bring the subjective stitching quality evaluation values ​​to a target range or at least one target value. Then stitched or composite images can be provided to present to one or more viewers, monitoring systems, or other such options.

[0021] The stitched or composite image data generated using such a process can be used for a variety of purposes. It should be understood that, at least for ease of explanation, "image" data will be discussed here, but image data can take many different forms; for example, individual images may correspond to individual frames of a video, or the image data may be used to generate immersive video, augmented reality (AR), virtual reality (VR), or mixed reality (MR) experiences. In one example use case, real-time video data might be captured for a device or system, such as a robot or autonomous (or semi-autonomous) vehicle. It may be necessary to combine real-time video data from multiple cameras to generate a consistent view of the environment, such as a complete view of the surroundings of the device, which could be presented to an operator, monitoring system, passenger, or other such entity. For many of these systems, generating such composite video representations in real time can be important so that the operator or monitoring system can take action as needed based on real-time observations.

[0022] Consider an autonomous or semi-autonomous vehicle that may include one or more passengers. The vehicle may include or be associated with multiple cameras (or at least one multi-part camera) that capture images of the vehicle's environment. To provide passengers with a seamless visualization of the environment, these images may need to be stitched or composited into a single, real-time updated representation of the environment, for example, while the vehicle is in motion. This composite representation can also be transmitted to a remote system, such as a monitoring or control system, which may analyze the vehicle's performance or potentially modify the vehicle's operation based at least in part on aspects of the environment determined by this representation. This requires these visualizations to be as realistic and flawless as possible.

[0023] Figure 1A Examples of autonomous vehicle 100 according to at least one embodiment are shown. In at least one embodiment, autonomous vehicle 100 (also referred to herein as “vehicle 100”) may be, but is not limited to, a passenger vehicle, such as a car, truck, bus, and / or other type of vehicle, capable of accommodating one or more passengers. In at least one embodiment, vehicle 100 may be a semi-trailer for hauling goods. In at least one embodiment, vehicle 100 may be an aircraft, robotic vehicle, or other type of vehicle.

[0024] 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).

[0025] 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.

[0026] 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 vehicle braking in response to receiving signals from one or more brake actuators 148 and / or brake sensors.

[0027] 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 fifth controller 136 for redundancy in 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.

[0028] 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.), microphone 196, stereo camera 168, wide-angle camera 170 (e.g., fisheye camera), one or more infrared camera 172, one or more surround camera 174 (e.g., 360-degree camera), long-range camera (… 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.

[0029] 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 signal, 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 signs, caution signs, 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.).

[0030] 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.).

[0031] 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.

[0032] 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.

[0033] 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-functional 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).

[0034] 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.

[0035] 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.

[0036] 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 sense 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.

[0037] 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, one or more compact stereo vision sensors, which may include, but are 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.

[0038] 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, the 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.

[0039] 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.

[0040] Figure 2A The illustration depicts a set of four constituent images 200 captured by various cameras on or associated with an autonomous vehicle or other such system or device, according to various embodiments. In this example, the cameras have different but partially overlapping fields of view, so the images can be stitched together without filling gaps or generating additional image data, although it should be understood that there may be other situations where the cameras do not utilize at least partially overlapping views to generate images that might require such a task. In this example, each camera may have various intrinsic or extrinsic values ​​that can affect the appearance of the captured images, where these values ​​may be related to options such as field of view, optical center, focal length, or camera pose. As mentioned above, it may be necessary to generate a single, consistent view of the surrounding environment based at least in part on these captured images 200. This may include, for example, generating... Figure 2B The composite image 250 is shown. As illustrated, this composite image can provide a single, consistent representation of the environment, whether it's a complete 360-degree view or at least a portion of the angular range. Such a view can be presented as a single view showing the entire image 250, or portions of the image can be displayed at different times, where the view can be controlled by the user. In this example, an angular alpha map is used instead of, for example, a vertical alpha map, at least to avoid the alpha discontinuity problem observed in various conventional stitching techniques. The color continuity of the blended region can be improved by expanding the blended region to hide color discontinuities around corners or other such features. However, as... Figure 2B As shown, by Figure 2A The composite image 250, produced by stitching together the constituent images 200, may have various artifacts or elements that are unrealistic to the environment and clearly indicate that the composite image was not captured as a single image. These may include, for example, one or more seams 252 indicating transitions between data from different frames, as well as seam misalignment, ghosting, or object disappearance, and other such options. It may also include discontinuous regions or discontinuities 254 where features of the data are not aligned with the different images, perhaps due to misalignment or calibration of the respective cameras, or variations or differences in these camera parameters, and other such options.

[0041] Methods according to various embodiments can attempt to determine a measure of the visual quality of such synthesized images. This visual quality measure can then be used to adjust various aspects of the stitching or compositing process in an attempt to improve the visual quality of these synthesized images. However, at least in some cases, objective methods of quality assessment can be challenging because objective image quality determination may not correspond to a viewer's subjective determination of image quality. For example, an objective determination of the presence of seams or artifacts can be applied to attempt to minimize their presence. However, the resulting image may have blurry or other unrealistic or undesirable appearance aspects for the viewer, who may subjectively believe that the image would have higher quality if seams or artifacts were in place. Therefore, a quality assessment system can attempt to determine one or more objective quality measures, or quality assessment metrics. The system can then attempt to infer subjective measures of quality or quality assessment metrics based at least in part on the determined objective measures.

[0042] In at least one embodiment, a mapping indicating subjective quality values ​​already provided for a particular objective quality value can be obtained. In other embodiments, there may be thresholds or ranges of objective quality values ​​corresponding to a particular subjective quality metric, such as high, medium, or low subjective quality assessments. In still other embodiments, methods such as machine learning may be used to infer one or more subjective quality assessment values ​​or metrics, at least in part, based on objective quality assessment metrics represented by determined synthetic images or other synthetic data.

[0043] Figure 3 The illustration depicts one such system 300 that can be used according to various embodiments. In this example, a set of camera images 302 are received as input, which can be received from multiple cameras associated with a given device or system, or positioned relative to a given environment, and other such options. In at least one embodiment, these images will represent two or more distinct views of an environment with at most partial overlap. These images can represent complete or partial views of a scene, location, or environment. The image data can include “real-time” data that is streamed or transmitted shortly after image capture, or it can include previously captured image data provided in a more offline manner. Such images can also be in various color spaces, such as RGB, CIELAB, CMYK, YIQ, YCbCr, YUV, HSV, or HSL, and other such options.

[0044] In this example, camera images 302 can be provided to a view generator 304, which can utilize these input camera images 302 to generate an output view or composite image or video stream for presentation via at least one display 324 (e.g., a monitor, projector, or wearable display), among other such options. In this example, camera images 302 can be provided to a stitching module 306, which will attempt to stitch multiple images together to generate a composite representation. The stitching module can use any of a variety of different stitching or compositing algorithms, as various mixing or other image processing techniques can be performed. In at least one embodiment, the stitching module can utilize various intrinsic and extrinsic parameters of the cameras, at least within the range of values ​​known and available from a camera database 308 or other such location, to properly allocate image data for compositing. This can include, for example, information such as the relative pose or orientation of these different cameras, allowing at least an initial stitching position and orientation to be determined for each image. It should be understood that for a view generator system receiving a sequence of image or video frame data streams, the images or frames to be composited are images or frames corresponding to or captured at the same point in time, at least to the extent that such capture can be synchronized. Camera calibration parameters can be used to map camera views to a stitching space, such as a top-down view or "bowl" view in a projection space, equidistant rectangular projection space, perspective projection space, or stereoscopic projection space. This projection can be used to identify any overlapping areas between adjacent cameras, where one or more blending algorithms can be used to blend at least some pixels to make the stitching less visible or obvious. Stitching module 306 can also utilize the values ​​of one or more stitching parameters, such as those stored in a parameter database 310 or other such location. The values ​​of these parameters can determine aspects of how the component images are stitched together, which may involve the weighting or location of the blending, among other such aspects. Example stitching parameters include, but are not limited to, blending methods (e.g., alpha blending, multi-band blending, or Poisson blending), blending width, blending alpha mapping shape (e.g., angle-based or vertical-based), weights for blending different frequency bands in multi-band blending, weights for different color channels in different color spaces (e.g., RGB, CIELAB, CMYK, YIQ, YCbCr, YUV, HSV, or HSL), seam type (e.g., diagonal seam, vertical seam, or horizontal seam), and seam position. Stitching module 306 can use the values ​​of these various parameters with the input constituent images to generate a composite image or stitched image 312, which provides a single representation of the environment, scene, or location at a specific point in time (e.g., the "current" time point), taking into account some latency in transmission and processing.

[0045] If the scene is incoherent between cameras, a larger blending weight or radius (e.g., 200) may be needed to provide a smoother transition between image data. For example, if it is a highly structured scene with many buildings and edges, a smaller blending weight (e.g., 2) may be needed to avoid ghosting and other artifacts due to misalignment between cameras. Single-band blending can also be used when blending images in only one band (or subset) of multiple bands. In at least one embodiment, the constituent images can be decomposed into different frequency bands or components, or blended in any suitable color space (e.g., RGB, CIELAB, CMYK, YIQ, YCbCr, YUV, HSV, HSL, etc.), and different blending weights can be applied to each of these bands, components, or color channels.

[0046] To attempt to provide a stitched image with high subjective quality, the stitched image may undergo some processing to assess its quality, and, at least if the determined quality falls below a target or threshold, the results of this assessment may be used to make any necessary changes to the stitching parameters to improve the quality. In this example, both the stitched image 312 from the stitching module 306 and the component images 314 used to generate the stitched image can be used for quality assessment. In some embodiments, the component images may directly correspond to the input camera image 302, while in others, these component images may have undergone at least some processing, such as reducing variations in brightness, color, or contrast, reducing the presence of noise, removing image artifacts, and other such options. In at least one embodiment, removing or reducing the presence of image artifacts in the individual component images before stitching can produce a higher quality stitched image.

[0047] In this example, the stitched image 312 and the constituent image 314 can be processed to produce image data that better provides one or more specific types of comparison. In at least one embodiment, this may include using a high-pass filter 316 (or an edge or feature detector) on the images to enhance or identify edges or other prominent features in the images. These edge-enhanced images can then be provided to a difference measurement module 318 (or process, etc.), which can compare the filtered stitched image 312 and the constituent images to produce one or more objective stitching quality assessment values. It should be understood that other synthetic quality assessment values ​​may also be generated if other synthesis techniques are used. These objective stitching quality assessment values ​​may include, for example, a set of structural similarity index measures (SSIM), blending width, pixel difference, or mean square error, or actual object size determination, and other such options. Values ​​such as SSIM values ​​can provide a measure of similarity between images, which can be used to infer the perceptual quality of the stitched image relative to its constituent images.

[0048] In this example, these target values ​​can be provided as input to a machine learning classifier 320. The machine learning classifier can be trained to infer a subjective stitching quality assessment value given one or more input target values. The classifier can be any suitable classifier, such as a convolutional neural network (CNN), support vector machine (SVM), neural network (NN), decision tree, or random forest, and other such options. During training, various images and objective evaluation data can be provided as input, and a subjective stitching quality assessment value can be provided as ground truth for each set of images and objective evaluation data. The subjective stitching quality assessment value can be obtained through any suitable mechanism, for example, by presenting the stitched or synthesized image to multiple viewers and having them each provide a subjective assessment of the image quality, which can then be averaged or otherwise used to determine the subjective stitching quality assessment value. In some embodiments, this can correspond to consensus among viewers, taking outliers into account or not.

[0049] In this example, the ML classifier 320 can take an objective value as input and output a subjective stitching quality assessment value for inference. In some embodiments, this can be numerical, but for the classifier, among other such options, it can also include classifications such as "high quality" or "low quality". In this example, the current stitched or synthesized image can be provided as output for presentation on at least one display, particularly for live or real-time video. The subjective stitching quality assessment value can be provided back to the stitching module, for example, the stitching module can then attempt to adjust the stitching parameters to improve the subjective stitching quality of subsequent stitched images. In at least one embodiment, this analysis can be performed until an acceptable subjective stitching quality assessment value is obtained, and those stitching parameters can continue to be used, at least for the remainder of the current session. In other embodiments, this assessment can continue to adapt to changing conditions, such as changes in brightness or image content type. For example, a vehicle traveling in a city may be in an environment with many sharp edges due to buildings, signs, and sidewalks, while driving in the countryside may result in few sharp edges, so different stitching parameters and / or filtering methods may be optimal. This can be performed on each set of images or frames at every time point, or it can be performed periodically or upon detection of changes in conditions, in order to reduce the amount of processing required and conserve computational resources. In some embodiments, intelligent scene analysis can be performed to attempt to narrow down the selection range for stitching quality assessment. In some embodiments, the stitching module can also receive objective quality assessment values, such as the SSIM value of a given composite frame, to assist in adjusting stitching parameters. Certain objective values ​​or ranges of values ​​may correspond to specific stitching parameters, and changing these values ​​in a specific direction or by a specific amount may also be associated with specific types of changes to those stitching parameters. Various methods can also be used to attempt to reduce the search space for stitching parameters. For example, there may be identified sets of parameter values ​​applicable to different situations, from which the stitching module can select to attempt to improve the subjective stitching quality assessment value of the inference. In addition to subjective or objective quality values, a suitable set can also be predicted based on factors such as scene content.

[0050] Figure 4A and Figure 4B The illustration shows different composite images 400 and 450 of the same constituent images using different stitching parameters. In this example, the box in image 400 represents the blended region where data from different images are stitched together. Figure 4AAs shown in the stitched image 400, clearly visible seams or transitions exist in each of these blending regions 402. The SSIM of the high-pass filtered version 420 of this stitched image shows clearly visible and well-defined seams. This version includes white areas determined to have high image quality based on subjective stitching quality assessment values ​​and black areas considered to have low image quality. As example values, the SSIM value of the upper left region 402 is 0.996947 for overlapping regions (where at least two images include image data from the same location, such as possible pixel data blocks) and 0.918620 for blending regions (where pixel values ​​from at least two partially overlapping images are blended), used to infer a “low” subjective quality assessment value. In contrast, Figure 4B The stitched image 450 shows some blurring in the seam area, but no obvious seam. Similarly, the SSIM visualization of the high-pass filter version 470 shows some blurred edges, but no clearly defined seam. As example values, the SSIM value of the top-left region of the overlapping area is 0.989522, and the SSIM value of the mixed region is 0.947744, used to infer a "high" subjective quality assessment value. Therefore, it is used to create Figure 4B The stitching parameters for the stitched image 450 in the image. This may be more than used for... Figure 4A The stitching parameters of the stitched image 400 are more suitable (from a subjective quality perspective). However, it should be mentioned that using only the SSIM value may not be sufficient. Visualizations of the SSIM values ​​for high-pass filter versions 420 and 470 show different types of seams, one small but well-defined, and another larger but less defined. Based solely on these factors, it may be impossible to identify which high-pass filter version will correspond to a higher subjective quality image evaluation. For example, such an evaluation may not be applicable to a grass view, where variations in the position of individual blades of grass may be insignificant, but blurring of grass areas may result in a lower subjective quality image evaluation. In at least some embodiments, it may be beneficial to utilize a classifier to analyze multiple objective stitching quality evaluation values ​​to provide more accurate results for a wider range of environments or situations. In addition to subjective stitching quality evaluation values, some systems may also attempt to optimize (e.g., maximize) objective stitching quality evaluation values. In some embodiments, objective stitching values ​​may be optimized even if the subjective stitching value of an image is determined to correspond to high quality.

[0051] In at least one embodiment, aspects such as the dimension and location of the blending region can be optimized. The size and / or width of the blending region can be adjusted based on factors such as scene content to avoid the blending region crossing objects. The optimal blending region size can be calculated at least in part based on frequency information of the image content. For images with low-frequency content, a larger blending width can be used to avoid color discontinuities. For images with high-frequency content (e.g., prominent edges), a smaller blending width can be used to avoid ghosting artifacts or other such problems. At least one embodiment can optimize multi-band blending weights. A pyramid decomposition of the image can be used to obtain a multi-scale or multi-level representation of the image. Content-aware blending weights can be used when assigning various alpha weights to different pyramid levels, instead of using linearly increasing blending for coarse pyramid levels as in other methods. The frequency of the image content can be calculated, and one or more optimal weights can be used for various image contents. The number of pyramid levels can also be optimized. If the image content frequency is widely distributed, a full pyramid can be used. However, if the image contains only (or primarily) low-frequency elements (e.g., two images with uniform colors), a single pyramid level with a wider blending width or smoother weights can be used instead of building the full pyramid, which helps save computation and improve the stitching results.

[0052] As described above, such high-quality synthetic images can be used for a variety of different purposes. For example, such images can be used as visualizations presented to passengers inside vehicles. They can also be provided to remove monitoring systems or fleet management systems that can receive these images via at least one network (e.g., the Internet or a cellular network) and can determine, at least in part, whether to take specific action based on these images. This could include, for example, determining to reroute vehicle routes or allocate additional (or backup) robotic equipment to perform tasks.

[0053] Figure 5An example process 500 for optimizing stitching parameters, which can be performed according to various embodiments, is illustrated. It should be understood that, for this process and others discussed herein, unless specifically stated otherwise, additional, fewer, or alternative steps may exist within the scope of various embodiments, performed in a similar or alternative order or at least partially in parallel. Furthermore, while stitching is used as a primary example, it should be understood that other image compositing or generation methods may also be used within the scope of various embodiments. In this example, receiving 502 includes a set of images comprising different views of a scene or environment. The stitching module may generate a stitched representation 504 of these images, for example, by projecting the images into a common space using a set of camera features, and by using a set of stitching parameters to determine how to stitch the projected image data together. For example, this may include determining which pixels to blend and how to blend them. The stitched image and the corresponding constituent image can then be processed 506 using a high-pass filter, an edge detector, or other such mechanisms to highlight specific elements in the images, such as edges. One or more difference measurements 508 may be calculated for the stitched image and the constituent image, which are used as objective stitching quality evaluation values. For example, these may include SSIM, blend width, and actual object size values. These objective evaluation values ​​can be provided as input to a machine learning classifier, such as a CNN, which is trained to infer subjective stitching quality evaluation values ​​based on these input objective values. At least if the subjective image quality evaluation value meets a minimum criterion or threshold, the subjective stitching quality evaluation value inferred by the classifier can be provided back to the stitching module, and the stitched image can be provided as output for display. It can be determined whether the subjective quality of the image is deemed acceptable, for example, the stitched image has inferred "high" image quality. If so, the process can continue to the next set of images. If not, one or more stitching parameter adjustments can be made to attempt to improve the subjective quality evaluation, and the process can continue, with the adjusted stitching parameters used for the next set of input images.

[0054] As discussed, the various methods presented in this paper are lightweight enough to be executed in real time on client devices such as personal computers or game consoles. This processing can be performed on content generated on this client device or received from an external source, such as streaming content received via at least one network. The source can be any suitable source, such as a game console, streaming provider, third-party content provider, or other client device, among other such options. In some cases, the processing and / or rendering of the content 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 other similar purposes.

[0055] For example, Figure 6An example network configuration 600 is illustrated that can be used to provide, generate, modify, encode, and / or transmit content. In at least one embodiment, a client device 602 can generate or receive session content using components of a content application 604 on the client device 602 and data locally stored on the client device. In at least one embodiment, a content application 624 (e.g., an image generation or editing application) executing on a content server 620 (e.g., a cloud server or edge server) can initiate a session associated with at least the client device 602, such as by utilizing a session manager and user data stored in a user database 634, and content 632 can be determined by a content manager 626. An image stitching module 628 can acquire image data of a scene or environment and generate a composite representation of the scene or environment. A quality assessment module 630 can attempt to infer the subjective quality of the composite representation, thereby allowing stitching parameters to be adjusted if necessary. At least a portion of the content can then be transmitted to the client device 602 using an appropriate transmission manager 622 for transmission via download, streaming, or other such transmission channels. An encoder can be used to encode and / or compress the data before transmission to the client device 602. In at least one embodiment, the content 632 may include video or image data of a scene. In at least one embodiment, the client device 602 receiving the content may provide the content to a corresponding content application 604, which may also or alternatively include a stitching module 612 or a quality assessment module 614 for stitching together image data received or captured by the client device 602. A decoder may also be used to decode data received via network 640 for presentation via client device 602, such as image or video content presented via display 606 and audio, such as sound and music, presented via at least one audio playback device 608, such as a speaker or headphones. In at least one embodiment, at least some of the content may already be stored on, rendered on, or accessible to client device 602, such that at least this portion of the content does not require transmission via network 640; for example, the content may have previously been downloaded or locally stored on a hard drive or optical disc. In at least one embodiment, a transmission mechanism such as data streaming may be used to transfer the content from server 620 or content database 634 to client device 602. In at least one embodiment, at least a portion of the content may be obtained from or streamed from another source, such as a third-party content service 660, which may also include a content application 662 for generating or providing the content. 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, for example, a combination of CPU and GPU may be included.

[0056] In this example, these client devices can include any suitable computing device, such as desktop computers, laptops, set-top boxes, streaming media devices, game consoles, smartphones, tablets, VR headsets, AR goggles, wearable computers, or smart TVs. Each client device can submit requests across at least one wired or wireless network, which can include the Internet, Ethernet, a local area network (LAN), or a cellular network, among other such options. In this example, these requests can be submitted to an address associated with a cloud provider, which can operate or control one or more electronic resources within the cloud provider's environment, such as data centers or server clusters. In at least one embodiment, the request can 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's environment. In this way, latency can be reduced by enabling client devices to interact with servers in closer proximity, while also improving the security of resources within the cloud provider's environment.

[0057] 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 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.

[0058] Reasoning and training logic

[0059] 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.

[0060] 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, 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.

[0061] 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.

[0062] 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, an arithmetic logic unit (ALU)). 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.

[0063] 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.

[0064] 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, wherein 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, and 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.

[0065] 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.

[0066] 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 7A 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 such as field programmable gate array (“FPGA”)

[0067] 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 7BThe 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.

[0068] 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.

[0069] Data Center

[0070] 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.

[0071] In at least one embodiment, such as Figure 8As 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.

[0072] 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.

[0073] 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.

[0074] In at least one embodiment, such as Figure 8As shown, framework layer 820 includes job scheduler 822, configuration manager 824, resource manager 826, and 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 of 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™ (hereinafter referred to as "Spark") which can utilize distributed file system 828 for large-scale data processing (e.g., "big data"). In at least one embodiment, job scheduler 832 may include Spark drivers to facilitate the scheduling of workloads supported by the various layers of data center 800. In at least one embodiment, configuration manager 824 may be able to configure different layers, such as software layer 830 and framework layer 820 including Spark and distributed file system 828 for supporting large-scale data processing. In at least one embodiment, resource manager 826 is capable of managing cluster or group computing resources mapped to or allocated to support distributed file system 828 and job scheduler 822. In at least one embodiment, cluster or group computing resources may include group computing resources 814 on data center infrastructure layer 810. In at least one embodiment, resource manager 826 may coordinate with resource coordinator 812 to manage these mapped or allocated computing resources.

[0075] 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.

[0076] 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.

[0077] 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.

[0078] 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.

[0079] 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.

[0080] 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 are provided regarding the inference and / or training logic 715. In at least one embodiment, the inference and / or training logic 715 can be implemented in the system. Figure 8 Used in this context 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.

[0081] These components can be used to synthesize a compositional image into a single representation using parameters determined from one or more quality assessment values.

[0082] Computer System

[0083] Figure 9 This 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™ XScale™ and / or StrongARM™ 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.

[0084] 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.

[0085] 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.

[0086] 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 external 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.

[0087] 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.

[0088] 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.

[0089] In at least one embodiment, the system logic chip may be coupled to the processor bus 910 and the 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, the MCH 916 may be coupled to the memory 920 via the high-bandwidth memory path 918, and the graphics / video card 912 may be coupled to the MCH 916 via an Accelerated Graphics Port (“AGP”) interconnect 914.

[0090] 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 interface 925, serial expansion port 927 (e.g., 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.

[0091] 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 9The 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.

[0092] 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 about the inference and / or training logic 715. In at least one embodiment, the inference and / or training logic 715 can be 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.

[0093] These components can be used to synthesize a compositional image into a single representation using parameters determined from one or more quality assessment values.

[0094] Figure 10 This 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.

[0095] 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.

[0096] In at least one embodiment, Figure 10 It 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.

[0097] 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) audio encoder / decoder (“codec”) and 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”).

[0098] 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 can 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.

[0099] These components can be used to synthesize a compositional image into a single representation using parameters determined from one or more quality assessment values.

[0100] 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.

[0101] 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.

[0102] 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 different instruction sets 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).

[0103] 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.

[0104] 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.

[0105] 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) or augmented reality (AR) applications.

[0106] 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, network controller 1134 can enable network connectivity to a wired network. In at least one embodiment, a high-performance network controller (not shown) is coupled to interface bus 1110. In at least one embodiment, audio controller 1146 is a multi-channel high-definition audio controller. In at least one embodiment, 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, platform controller hub 1130 may also be connected to one or more Universal Serial Bus (USB) controllers 1142 to connect input devices, such as keyboard and mouse combinations 1143, cameras 1144, or other USB input devices.

[0107] 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.

[0108] 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 7A7B 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.

[0109] These components can be used to synthesize a compositional image into a single representation using parameters determined from one or more quality assessment values.

[0110] Figure 12 This 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.

[0111] 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.

[0112] 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).

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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. Furthermore, in at least one embodiment, the inference and / or training operations described herein can use, except... 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 ALU of the graphics processor 1200 for executing one or more machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0119] These components can be used to synthesize a compositional image into a single representation using parameters determined from one or more quality assessment values.

[0120] Virtualization computing platform

[0121] 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.

[0122] 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.

[0123] 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.

[0124] In at least one embodiment, training pipeline 1404 ( Figure 14This could include a scenario where facility 1302 is training its own machine learning model, or has 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 can be received. In at least one embodiment, once the imaging data 1308 is received, AI-assisted annotation 1310 can 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 can 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 can then be used directly, or it can 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 can 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.

[0125] In at least one embodiment, training pipeline 1404 ( Figure 14 This could include scenarios where facility 1302 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 a purpose). In at least one embodiment, an existing machine learning model can be selected from model registry 1324. In at least one embodiment, model registry 1324 can include machine learning models trained to perform various inference tasks on imaging data. In at least one embodiment, the machine learning models in model registry 1324 may have already been trained on imaging data from facilities other than facility 1302 (e.g., facilities located remotely). In at least one embodiment, the machine learning models may have already been trained on imaging data from one location, two locations, or any number of locations.

[0126] In at least one embodiment, when training on imaging data from a specific location, training may occur at that location, or at least in a manner that protects the confidentiality of the imaging data or restricts its transmission from the field. In at least one embodiment, once the model has been trained or partially trained at one location, the machine learning model can be added to the 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 the model registry 1324. In at least one embodiment, the machine learning model can then be selected from the 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.

[0127] In at least one embodiment, training pipeline 1404 ( Figure 14 The 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.

[0128] 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.

[0129] 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 output 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.

[0130] 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.

[0131] 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 uses its SDK to test the developed application locally (e.g., at the first facility, with 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 with respect to data at the user's facility (e.g., a second facility).

[0132] 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).

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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 implemented as a combination of 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.

[0138] 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.

[0139] In at least one embodiment, the training system 1304 may execute the training pipeline 1404, similar to that described herein. Figure 13 Those described. 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 may 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 13The 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.

[0140] 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.

[0141] 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 (e.g., conventional annotations) can be generated using any number of techniques. In at least one embodiment, labels or other annotations can 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 can be hand-drawn in some examples. In at least one embodiment, the ground reality data can 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 can 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 for diagnostic applications (or other application types). 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.

[0142] 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.

[0143] 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.

[0144] 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 may be even more user-friendly, providing easier integration and producing more accurate, efficient, and timely results.

[0145] 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.

[0146] 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 deploying 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 (e.g., as...) Figure 12 As shown in the diagram (cc), pipeline manager 1412 may be included in service 1320. In at least one embodiment, 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 (e.g., refactored applications, split applications, etc.) from deployment pipeline 1410 with separate containers, each application can execute in a self-contained environment (e.g., at the kernel level) to improve speed and efficiency.

[0147] 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 thus 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.

[0148] 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.

[0149] In at least one embodiment, AI service 1418 may be used to perform an inference service 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 (one or more) deploying pipeline 1410 may use one or more 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 a high-priority / low-waittime path that implements a higher service level agreement, 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 a standard priority path that may be used for requests that are not urgent or in which 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.

[0150] 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 on 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.

[0151] 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.

[0152] 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 on 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.

[0153] 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 queues via an API with a unique application / tenant ID combination, and the SDK pulls requests from the queues 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 routed to a queue with a majority of instances of the application connected to it, while the lowest priority work can be routed 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 GPU-accelerated instances generated in cloud 1426, and the inference service can perform inference on the GPU.

[0154] 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 image and / or other rendering or image processing capabilities or functions (e.g., ray tracing, rasterization, internal optics, etc.).

[0155] 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.

[0156] 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.

[0157] 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 utilizing 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 provide other functionalities for system 1400.

[0158] 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 14System 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. In at least one embodiment, the refined model 1512 generated by process 1500 may be executed by deployment system 1306 for one or more containerized applications in deployment pipeline 1410.

[0159] 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 truth data associated with the input data). 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 based on loss calculations associated with the accuracy of the output or (one or more) lost layers, such as customer dataset 1506 (e.g., customer dataset 1506 ... Figure 13 Image data 1308).

[0160] 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 performing process 1500. In at least one embodiment, to protect the privacy and permissions of patients, subjects, or clients at different facilities, the pre-trained model 1406 may be trained on-site using client 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 client 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.

[0161] 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.

[0162] 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).

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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 real-world 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.

[0168] These components can be used to synthesize a compositional image into a single representation using parameters determined from one or more quality assessment values.

[0169] Automation technology

[0170] 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.

[0171] 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.

[0172] In at least one embodiment, vehicle 1600 may include one or more controllers 1636, such as those described herein. Figure 1A The 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.

[0173] 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), the high-definition map 1622 being available from one or more servers via a network interface 1624. Figure 16A (Not shown in the image) Get map refresh and / or update.

[0174] 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.

[0175] 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 cores, clusters, 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.

[0176] 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).

[0177] 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 collaboration 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.

[0178] 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”).

[0179] 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 (“MMUs”) experience a miss, an address translation request can be sent to one or more CPUs 1606. In response, in at least one embodiment, two CPUs 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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 memory devices. For example, in at least one embodiment, the RISC core may include an instruction cache and / or tightly coupled RAM.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] In at least one embodiment, one or more accelerators 1614 (e.g., hardware acceleration clusters) 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).

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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).

[0197] 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.

[0198] 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).

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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 bulb accompanied by 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 recognized 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 the 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 the DLA and / or on one or more GPUs 1608.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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).

[0215] 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.

[0216] 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.

[0217] In at least one embodiment, the 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, the 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.

[0218] 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.

[0219] In at least one embodiment, vehicle 1600 may also include one or more RADAR sensors 1660. 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. One or more RADAR sensors 1660 may use a CAN bus and / or bus 1602 (e.g., to transmit data generated by one or more RADAR sensors 1660) for control and access to object tracking data, and in some examples, may access Ethernet to access 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.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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).

[0224] 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 may 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.

[0225] 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.

[0226] 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.

[0227] In at least one embodiment, one or more IMU sensors 1666 can 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 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 can be combined in a single integrated unit.

[0228] 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.

[0229] 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.

[0230] 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).

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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 warnings, vibrations, and / or rapid braking pulses.

[0235] 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 may 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.

[0236] 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.

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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.

[0244] 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 system, rear parking assist, radio data system, 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, automobile, 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 further be 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.

[0245] 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.

[0246] 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.

[0247] 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 can be implemented in the system. Figure 16A The operation is used to infer or predict the operation based at least in part on weight parameters calculated using neural network training operations, neural network functions and / or architectures or neural network use cases described herein.

[0248] 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 interconnects, 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.

[0249] 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).

[0250] 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.

[0251] 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.

[0252] 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.

[0253] 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.

[0254] 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.

[0255] 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 the 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 where not modified) 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.

[0256] 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”.

[0257] Unless otherwise indicated 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 is 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.

[0258] 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.

[0259] 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.

[0260] 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.

[0261] The terms “coupled” and “connected”, and 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.

[0262] 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.

[0263] 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.

[0264] 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.

[0265] 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.

[0266] 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: Acquire multiple component images of the environment; Using one or more color values ​​of the pixels of the constituent images and based on at least one stitching parameter, the constituent images are stitched together to generate a composite image, wherein one or more blending weights are applied to one or more corresponding color channels to blend the one or more color values, and the blending weights are determined in part based on what is represented in the constituent images; Calculate multiple objective quality metrics for one or more differences between the synthesized image and the constituent images; The trained classifier is used to infer subjective quality metrics for the splicing, and the trained classifier uses a plurality of objective quality metrics as input, including a structural similarity index measure, a blending width, and an actual object size value. as well as At least one stitching parameter is adjusted, at least in part, based on the subjective quality metric, for stitching the constituent images of subsequent groups, wherein the subjective quality metric for the subsequent groups at least satisfies a threshold condition.

2. The computer-implemented method as described in claim 1, further comprising: Determine one or more camera parameters from a set of camera parameters used to capture the group of constituent images; as well as The constituent images are projected into a common space for stitching, based at least in part on one or more camera parameters.

3. The computer-implemented method as described in claim 1, further comprising: The constituent images are stitched together using stitching parameters of the initial group, which include at least one of the following: blend type, blend width, blend alpha shape, seam type, or seam position.

4. The computer-implemented method of claim 1, wherein the plurality of objective quality metrics include at least one of the following: structural similarity index (SSIM), blending width, a set of pixel differences or mean square error, or actual object size determination.

5. The computer-implemented method as described in claim 1, further comprising: Before calculating the plurality of objective quality metrics, at least one of a high-pass filter or an edge detector is used to process the synthetic image and the composition image.

6. The computer-implemented method as described in claim 1, further comprising: Before adjusting at least one of the splicing parameters, it is determined that the subjective quality indicator has failed to at least approach the target value.

7. The computer-implemented method as described in claim 1, further comprising: The synthesized image is provided as a visualization of the environment for presentation.

8. The computer-implemented method of claim 1, wherein stitching the constituent images into the composite image comprises: The color values ​​of one or more pixels in the constituent image are blended using one or more blending parameters determined at least in part based on determined content in the constituent image that corresponds to one or more objects in the environment represented in the constituent image.

9. The computer-implemented method as described in claim 8, further comprising: Different mixing parameters are determined for different frequency bands of the content in the constituent image.

10. A system comprising: One or more processors; as well as A memory storing instructions that, when executed by the one or more processors, cause the system to: Obtain multiple component images of the environment; A composite image is generated using the plurality of component images based on at least one synthesis parameter. The composite image is generated by mixing one or more color values ​​of pixels in the component images and applying one or more mixing weights to one or more corresponding color channels. The mixing weights are determined at least in part based on the content represented in the component images. Calculate at least one objective quality metric for one or more differences between the synthesized image and the constituent images; The trained classifier infers a subjective quality metric for the synthesis of the synthesized image, the trained classifier using at least one objective quality metric as input, the at least one objective quality metric including a structural similarity index measure, a blending width, and an actual object size value. as well as The at least one synthesis parameter is adjusted at least in part based on the subjective quality index for synthesizing compositional images of subsequent groups, wherein the subjective quality index for the subsequent groups at least satisfies a threshold condition.

11. The system of claim 10, wherein a trained machine learning classifier is used to infer the subjective quality metric.

12. The system of claim 10, wherein the instructions, when executed, further cause the system to: Determine multiple camera parameters used to capture this set of constituent images; and The composition image is projected into a common space for the synthesis, at least in part based on the camera parameters.

13. The system of claim 10, wherein the instructions, when executed, further cause the system to: The composite image is generated in part by stitching the constituent images together using the synthesis parameters of the initial group, which include at least one of the following: blend type, blend width, blend alpha shape, seam type, or seam position.

14. The system of claim 10, wherein the at least one objective quality indicator includes: The structural similarity index (SSIM) measure, blending width, a set of pixel differences or mean square error, or actual object size are used to determine the measurement.

15. The system of claim 10, wherein the system comprises 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 non-transitory computer-readable storage medium comprising instructions that, if executed by one or more processors, cause the one or more processors to: Obtain a set of component images of the environment; A composite image is generated using the set of constituent images based on at least one stitching parameter. The composite image is generated by mixing one or more color values ​​of pixels in the constituent images and applying one or more mixing weights to one or more corresponding color channels. The mixing weights are determined at least in part based on the content represented in the constituent images. Calculate at least one objective quality metric for one or more differences between the synthesized image and the constituent images; A trained classifier is used to infer a subjective quality metric for the synthesis of the synthesized image, the trained classifier taking at least one objective quality metric as input, the at least one objective quality metric including a structural similarity index measure, a blending width, and an actual object size value; and The at least one synthesis parameter is adjusted to synthesize the composition images of subsequent groups, wherein the subjective quality index for the subsequent groups at least meets a threshold condition.

17. The non-transitory computer-readable storage medium of claim 16, wherein a trained machine learning classifier is used to infer the subjective quality metric.

18. The non-transitory computer-readable storage medium of claim 16, wherein the instructions, if executed, also cause the one or more processors to: Determine multiple camera parameters used to capture this set of constituent images; and The composition image is projected into a common space for the synthesis, at least in part based on the camera parameters.

19. The non-transitory computer-readable storage medium of claim 16, wherein the instructions, if executed, also cause the one or more processors to: The composite image is generated in part by stitching the constituent images together using the synthesis parameters of the initial group, the stitching parameters including at least one of the following: blend type, blend width, blend alpha shape, seam type, or seam position.

20. The non-transitory computer-readable storage medium of claim 16, wherein the at least one objective quality indicator includes: The structural similarity index (SSIM) is measured by the blending width, a set of pixel differences or mean square error, or the actual object size.

Images