Infrared lighting control for visible and infrared imaging modes

Abstract

The invention discloses infrared lighting control for visible and infrared imaging modes. In various examples, the image processing pipeline may switch between the IR imaging mode and the RGB imaging mode in response to different thresholds of detected light intensity dependent on the switching direction (e.g., a lower intensity threshold for transitioning from RGB imaging to IR imaging and a higher intensity threshold for transitioning from IR imaging to RGB imaging). For example, an image processing pipeline may convert from RGB imaging to IR imaging in response to detecting that an amount of light intensity (e.g., average intensity in a green channel) is below a first threshold, and the image processing pipeline may convert from IR imaging to RGB imaging in response to: (i) detecting that the amount of light intensity (e.g., average intensity in the green channel) exceeds a second threshold, and / or (ii) detecting that the ratio of detected light intensity (e.g., IR to green) is below a third threshold.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application is related to U.S. patent application No. 18 / 494,138, filed on October 25, 2023, and entitled “Selective Operating Mode Switching for Visible and Infrared Imaging.” Background Art

[0003] Autonomous and semi-autonomous vehicles and other machines rely on machine learning methods (e.g., methods using deep neural networks (DNNs)) to analyze images of interior spaces (e.g., cabins, cockpits) to perform many important purposes. An occupant monitoring system (OMS) is an example of a system that can be used within a vehicle cabin to perform real-time assessments of the presence, gaze, alertness, and / or other conditions of an occupant or operator. For example, OMS sensors (e.g., but not limited to RGB sensors, infrared (IR) sensors, depth sensors, cameras, and / or other optical sensors) can be used to track the gaze direction, head posture, and / or blinking of an occupant or operator. This information can be used to determine the occupant's or operator's attention level (e.g., to detect drowsiness, fatigue, and / or distraction), and / or take responsive measures to prevent harm to the occupant, operator, or surrounding environment, for example, by redirecting their attention to potential hazards, pulling the vehicle over, and the like. For example, a DNN may be used to detect whether an operator is falling asleep at the wheel based on the operator looking down at the vehicle floor or not blinking for an extended period of time, and this detection may result in adjusting the speed and / or direction of the car (e.g., pulling the vehicle over to the side of the road) or sounding an audible alert to the operator.

[0004] Conventional OMS have various challenges and shortcomings. For example, some OMS attempt to perform tasks such as driver distraction, drowsiness detection, hands on the steering wheel detection, three-dimensional (3D) pose estimation, monocular depth estimation, and / or child presence detection with high accuracy under different operating conditions to prevent overly frequent, redundant, or unnecessary alerts to occupants. However, some operating conditions can cause depth ambiguity and / or occlusions in the sensor data, which can limit the accuracy of these tasks. In one example, OMS often needs to perform in situations where lighting changes rapidly, frequently, and drastically, which can occur in scenarios such as vehicles entering or exiting tunnels or parking lots. However, lighting changes can negatively impact depth perception and detection accuracy, and can even cause detection to fail entirely - for example, when the image is too dark to detect the desired features during operation in the visible spectrum.

[0005] OMS systems have begun using RGB / IR cameras that can capture visible light (the red, green, and blue or "RGB" spectrum) and infrared light. These cameras are equipped with sensors that are sensitive to both types of light, enabling them to record images or videos in both the visible light spectrum and the IR light spectrum. Most conventional technologies tend to operate in a single mode, relying on either RGB or IR images to perform their respective tasks, thereby limiting their ability to operate accurately in the presence of changes in scene lighting. One conventional technology uses an ambient light sensor to detect ambient light and switches between using an RGB pixel sensor and an IR pixel sensor when the amount of ambient light detected is below a threshold. However, there are often moderate and low levels of ambient light where detection accuracy in the RGB and / or IR domains is negatively impacted.

[0006] One prior art technique attempts to handle changes in scene illumination by turning on an IR emitter to provide IR illumination, thereby improving the signal-to-noise ratio of the resulting image. However, the IR emitter has some degrading effects on the resulting image. IR light can contaminate color reproduction and cause color errors when generating RGB images. In addition, IR light can reduce the dynamic range of the camera by introducing additional illumination in bright areas. A currently available RGB / IR camera provides an operating mode called ABAB mode, which turns the IR emitter on and off and alternately generates "A" frames (IR images) and "B" frames (RGB images). However, this mode generates IR and RGB image data streams, one of which is typically not used, effectively wasting computing resources, power, bandwidth, and memory used to generate the stream.

[0007] Therefore, there is a need for an improved sensing and / or detection technique that generates image data more accurately and / or with sharper detail in the presence of changes in scene illumination, and / or that facilitates improved accuracy of detection from such image data. Summary of the invention

[0008] Embodiments of the present disclosure relate to operating modes for visible light and infrared imaging. For example, systems and methods are disclosed for toggling between an IR imaging mode and an RGB imaging mode (e.g., switching IR illumination) in response to different detected light intensity thresholds depending on the switching direction. Additionally or alternatively, some embodiments may switch between the following modes (e.g., based on vehicle speed or gear): i) a first operating mode that switches between the IR imaging mode and the RGB imaging mode at a fixed frame rate or interval, and ii) a second operating mode that switches between the IR imaging mode and the RGB imaging mode based on detected light intensity.

[0009] Compared to conventional systems such as those described above, the image processing pipeline can switch between the IR imaging mode and the RGB imaging mode in response to different detected light intensity thresholds depending on the switching direction (e.g., a lower intensity threshold for switching from RGB imaging to IR imaging, a higher intensity threshold for switching from IR imaging to RGB imaging). For example, the image processing pipeline can switch from RGB imaging to IR imaging in response to detecting that the amount of light intensity (e.g., the average intensity in the green channel) is below a first threshold, and the image processing pipeline can switch from IR imaging to RGB imaging in response to (i) detecting that the amount of light intensity (e.g., the average intensity in the green channel) exceeds a second threshold, and / or (ii) detecting that the ratio of the detected light intensities (e.g., IR to green) is below a third threshold. The gaps between the intensity thresholds can be specified to simulate a hysteresis effect that can reduce or prevent abrupt changes between the IR imaging mode and the RGB imaging mode in response to relatively small changes in the detected intensity.

[0010] In some embodiments, the image processing pipeline can switch between different operating or transition modes based on the speed and / or active gear (e.g., parked vs. driven) of the ego-motion of a vehicle or other ego-machine using an RGB / IR camera. For example, when the vehicle is in motion, in a particular gear (e.g., driving), and / or traveling at a speed above a threshold, a first operating or transition mode that switches between an IR imaging mode and an RGB imaging mode at a fixed frame rate or interval can be used, which facilitates relatively faster transition times and better performance of detection tasks during transitions between imaging modes compared to other operating or transition modes. For example, when driving into and out of a tunnel or parking lot, the interior of a vehicle may experience frequent, rapid, and / or dramatic lighting changes, and operating or transition modes such as these may have relatively short transition delays, thereby providing better data coverage during lighting transitions (e.g., because the imaging mode does not switch based on lighting changes).

[0011] In another example, when the vehicle is stationary, parked (or in neutral), and / or traveling at a speed below a threshold, a second operating or transition mode that switches between an IR imaging mode and an RGB imaging mode based on detected light intensity may be used. Since such an operating or transition mode can effectively generate a single image data stream, it can operate at a higher frame rate and use lower bandwidth and less data processing than an operating or transition mode that generates two simultaneous streams, thereby effectively saving resources when frequent or rapid lighting changes are not expected (e.g., because the vehicle is stationary).

[0012] Thus, the techniques described herein may be used to generate RGB and IR images or videos and / or perform one or more detection tasks on such images or videos. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The present system and method for visible light and infrared imaging modes of operation are described in detail below with reference to the accompanying drawings, in which:

[0014] Figure 1 is a data flow diagram illustrating an example image processing pipeline according to some embodiments of the present disclosure;

[0015] Figure 2 is a data flow diagram illustrating an example image processing pipeline supporting a light-dependent mode of operation according to some embodiments of the present disclosure;

[0016] Figure 3 shows example thresholds for detected light intensity for switching between IR imaging mode and RGB imaging mode according to some embodiments of the present disclosure;

[0017] Figure 4 shows example quantum efficiency curves for the green and IR bands according to some embodiments of the present disclosure;

[0018] Figure 5 illustrates an example timeline of switching between an IR imaging mode and an RGB imaging mode at a fixed frame rate or interval according to some embodiments of the present disclosure;

[0019] Figure 6 is a flow chart illustrating a method of switching between an RGB imaging mode and an IR imaging mode based on light intensity according to some embodiments of the present disclosure;

[0020] Figure 7 is a flow chart illustrating a method of switching between an RGB imaging mode and an IR imaging mode based on different detected light intensity thresholds according to some embodiments of the present disclosure;

[0021] Figure 8 is a flow chart illustrating a method of switching between operating modes of an image processing pipeline based at least on a speed or active gear of a self machine according to some embodiments of the present disclosure;

[0022] Fig.9A is an illustration of an example autonomous vehicle according to some embodiments of the present disclosure;

[0023] Fig. 9B According to some embodiments of the present disclosure Fig.9A Examples of autonomous vehicle camera positions and fields of view;

[0024] Fig. 9CAccording to some embodiments of the present disclosure Fig.9A a block diagram of an example system architecture for an example autonomous vehicle;

[0025] Fig.9D is a cloud-based server and Fig.9A System diagram of an example of communication between autonomous vehicles;

[0026] Fig.10 is a block diagram of an example computing device suitable for implementing some embodiments of the present disclosure; and

[0027] Fig.11 is a block diagram of an example data center suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0028] Systems and methods related to operating modes for visible light imaging and infrared imaging are disclosed. For example, systems and methods are disclosed for switching between an IR imaging mode and an RGB imaging mode (e.g., switching IR illumination) in response to different detected light intensity thresholds depending on the switching direction. The gap between the intensity thresholds can simulate a hysteresis effect that can reduce or prevent abrupt changes between the IR imaging mode and the RGB imaging mode in response to relatively small changes in detected intensity. Additionally or alternatively, some embodiments can switch between the following modes (e.g., based on vehicle speed or gear): i) a first operating mode that switches between the IR imaging mode and the RGB imaging mode at a fixed frame rate or interval, and ii) a second operating mode that switches between the IR imaging mode and the RGB imaging mode based on detected light intensity. The present technology can be used to generate images or videos and / or perform one or more detection tasks on such images or videos in monitoring systems (e.g., occupant or driver monitoring systems), security systems, photography or video systems, scientific or environmental observation systems, and / or other types of systems.

[0029] Although the example autonomous or semi-autonomous vehicle or machine 900 (referred to herein alternatively as “vehicle 900 ” or “self-machine 900 ”) may be described with reference to the example autonomous or semi-autonomous vehicle or machine 900 . Figures 9A-9DThe present disclosure may be described with respect to, but is not intended to be limiting. For example, the systems and methods described herein may be used by, but are not limited to, non-autonomous vehicles or machines, semi-autonomous vehicles or machines (e.g., in one or more advanced driver assistance systems (ADAS)), autonomous vehicles or machines, manned and unmanned robots or robotic platforms, warehouse vehicles, off-road vehicles, vehicles coupled to one or more trailers, aircraft, boats, shuttles, emergency response vehicles, motorcycles, electric or motorized bicycles, airplanes, engineering vehicles, trains, submarines, remotely controlled vehicles (e.g., drones), and / or other vehicle types. In addition, while the present disclosure may be described with respect to in-cabin sensing, this is not intended to be limiting, and the systems and methods described herein may be used for augmented reality, virtual reality, mixed reality, robotics, security and surveillance, autonomous or semi-autonomous machine applications, and / or any other technology space where visible light imaging and / or infrared imaging may be used.

[0030] One application of visible light imaging and infrared imaging is an occupant monitoring system (OMS), which can be used within a vehicle cabin to perform hands on the steering wheel detection, 3D pose estimation, monocular depth estimation, child presence detection, and / or other real-time assessments of occupant and / or operator presence, gaze, alertness, and / or other conditions. An OMS typically relies on observations from multiple OMS cameras (e.g., RGB cameras, infrared cameras, combined RGB / infrared (RGB / IR) cameras) located at various locations within the vehicle interior. Vehicle manufacturers tend to vary the number of OMS cameras based on model and trim level. Base models typically have a single camera facing the driver (e.g., located in the steering column, vehicle pillar, or infotainment console). Higher trim levels may include any number of additional cameras (e.g., one in the steering wheel facing the driver, one in the rearview mirror facing the driver or cabin, one in the vehicle pillar facing a particular row of seats, one above a row of headrests facing forward for child detection, etc.). Any or all of these cameras and / or cameras in other locations may be implemented using RGB / IR cameras. OMS cameras are just one possible application of this technology, and other applications are also within the scope of this disclosure.

[0031] In some embodiments, the image processing pipeline can adapt to changing lighting conditions by switching between an IR imaging mode and an RGB imaging mode. The operation or conversion mode that switches between the IR imaging mode and the RGB imaging mode in response to the detected light intensity can be referred to as a "day and night mode" because it can support transitions between daytime scenes and nighttime scenes. For example, an RGB / IR camera, an image signal processor (ISP), and / or some other components of the image processing pipeline can adjust one or more settings to optimize image quality and capture corresponding details in response to different lighting conditions. For example, when a measure of the detected light intensity meets or exceeds a specified threshold (e.g., during the day), the image processing pipeline can primarily capture and / or process the RGB band to produce a color image. As lighting conditions change and available visible light decreases, the image processing pipeline can shift to focus on capturing the IR band to achieve better detection and visibility in low-light or nighttime scenes.

[0032] More specifically, an IR emitter (e.g., an infrared emitter of an RGB / IR camera) can be switched and / or one or more camera settings (e.g., exposure time) can be set (e.g., using a control signal applied to an interface of the RGB / IR camera) and / or one or more image processing, rendering, and / or detection techniques can be applied in response to the amount of detected light intensity. For example, an IR imaging or low light mode (e.g., night mode) can include activating an IR emitter, setting a specified exposure time that accommodates expected scene lighting (e.g., low visible light plus infrared illumination), generating IR image data (e.g., a grayscale image), determining not to generate or discarding RGB image data, applying the generated IR image data to one or more machine learning models configured to operate on IR image data (e.g., at some specified frame rate), and / or presenting the generated IR image data (e.g., one or more still images and / or resulting video) on a display (e.g., visible to an operator or occupant of a vehicle using the RGB / IR camera). RGB imaging or bright light mode (e.g., daytime mode) can include operating in the absence of IR illumination (e.g., turning off the IR emitter), setting a specified exposure time that accommodates expected scene lighting (e.g., visible light), generating RGB image data (e.g., subtracting the amount of detected IR light intensity from the amount of detected light intensity in one or more visible light channels), determining not to generate or to discard IR image data, applying the generated RGB image data to one or more machine learning models configured to operate on the RGB image data (e.g., at some specified frame rate), and / or presenting the generated RGB image data (e.g., one or more still images and / or resulting video) on a display (e.g., visible to an operator or occupant of a vehicle using the RGB / IR camera).

[0033] In some embodiments, the image processing pipeline can switch between these IR imaging modes and the RGB imaging mode in response to the detected light intensity meeting or exceeding one or more thresholds, which thresholds can include different detected light intensity thresholds depending on the switching direction (e.g., a lower intensity threshold for switching from RGB imaging to IR imaging, a higher intensity threshold for switching from IR imaging to RGB imaging). For example, the image processing pipeline can switch from RGB imaging to IR imaging in response to detecting that the amount of light intensity (e.g., the average intensity in the green channel) is below a first threshold, and the image processing pipeline can switch from IR imaging to RGB imaging in response to (i) detecting that the amount of light intensity (e.g., the average intensity in the green channel) exceeds a second threshold, and / or (ii) detecting that the ratio of the detected light intensity (e.g., IR to green) is below a third threshold. The gaps between the intensity thresholds can be specified to simulate a hysteresis effect that can reduce or prevent abrupt changes between the IR imaging mode and the RGB imaging mode due to relatively small changes in the detected intensity.

[0034] In general, different modes of operation or conversion may have different benefits in different scenarios and / or for different detection use cases. For example, in some implementations, transitions between different modes of operation, conversion, and / or imaging may result in latency issues, which may result in undesirable or unavailable frames during the transition. An operating or conversion mode that switches between an IR imaging mode and an RGB imaging mode at a fixed frame rate or interval may be advantageous in ensuring that both types of image data streams are available at a relatively fast frame rate, wherein transitions between imaging modes are relatively faster (e.g., by omitting logic for evaluating the image data of a previous frame), which reduces or avoids conversion delays that may result in undesirable or unavailable frames. Therefore, operating or conversion modes such as these may be more configured to handle frequent, rapid, and / or drastic lighting changes, and may facilitate the execution of one or more detection tasks at a minimum frame rate, effectively responding faster and extracting better performance during transitions compared to other operating or conversion modes. Furthermore, by efficiently generating simultaneous IR and RGB image data streams, either or both streams can be used for downstream applications (e.g., detection tasks), for example, by operating on one of the streams based on given lighting conditions or performing feature extraction using image data frames from both streams simultaneously (e.g., performing a single inference using consecutive RGB and IR image data frames).

[0035] On the other hand, an operating or conversion mode that switches between an IR imaging mode and an RGB imaging mode based on detected light intensity can be advantageous for optimizing bandwidth, power, and / or computing resources, for example, by reducing the processing load and resource requirements required to process simultaneous RGB and IR image data streams. In addition, configuring a single image data stream can facilitate the use of a higher frame rate for that stream than the image processing pipeline uses to process simultaneous RGB and IR image data streams. Thus, an operating or conversion mode such as this can be configured to generate an RGB or IR image data stream at a relatively higher frame rate than other operating or conversion modes, thereby effectively extracting better performance out of the transition, which can be advantageous for applications requiring real-time or high-speed monitoring (e.g., monitoring occupant and / or driver behavior).

[0036] In some embodiments, the image processing pipeline can switch between different operating or transition modes based on the self-motion speed and / or active gear (e.g., parking vs. driving) of a vehicle or other self-machine using an RGB / IR camera. For example, when the vehicle is in one or more motion states, in a particular gear (e.g., driving), and / or traveling at a speed above a threshold, a first operating or transition mode that switches between an IR imaging mode and an RGB imaging mode at a fixed frame rate or interval can be used, thereby facilitating a relatively faster transition time and better detection task execution during the transition between imaging modes compared to other operating or transition modes. For example, when a vehicle enters and exits a tunnel or parking lot, the interior of the vehicle may experience frequent, rapid, and / or drastic lighting changes, and operating or transition modes such as these can have relatively shorter transition delays, which provide better data coverage during the lighting transition (e.g., because the imaging mode is not switched based on the lighting change). In another example, when the vehicle is stationary, parked (or out of gear), and / or traveling at a speed below a threshold, a second operating or transition mode that switches between an IR imaging mode and an RGB imaging mode based on the detected light intensity can be used. Because an operation or conversion mode such as this can effectively generate a single image data stream, it can operate at a higher frame rate and use lower bandwidth and less data processing than an operation or conversion mode that generates two simultaneous streams, thereby effectively saving resources when frequent or rapid lighting changes are not expected (for example, because the vehicle is stationary).

[0037] Thus, the techniques described herein can be used to generate RGB and IR images or videos and / or perform one or more detection tasks on such images or videos. Using the techniques described herein, RGB and / or IR images can be generated more accurately and / or with sharper details than the prior art, and / or RGB and / or IR images can be generated in a manner that uses computing resources, memory, and / or bandwidth more efficiently than the prior art, thereby improving the accuracy and / or bandwidth of downstream applications (e.g., detection tasks) compared to the prior art.

[0038] refer to Figure 1 , Figure 1 An example image processing pipeline 100 is shown according to some embodiments of the present disclosure. It should be understood that this arrangement and other arrangements described herein are presented only as examples. Other arrangements and elements (e.g., machines, interfaces, functions, sequences, functional groupings, etc.) may be used in addition to or in place of the arrangements and elements shown, and some elements may be omitted entirely. In addition, many of the elements described herein are functional entities that may be implemented as discrete or distributed components or in conjunction with other components, and may be implemented in any suitable combination and location. The various functions performed by the entities described herein may be performed by hardware, firmware, and / or software. For example, the various functions may be implemented by a processor executing instructions stored in a memory. In some embodiments, the systems, methods, and processes described herein may be implemented using Figures 9A-9D Example of autonomous vehicle 900, Fig.10 The example computing device 1000 and / or Fig.11 The example data center 1100 may be implemented with similar components, features and / or functions.

[0039] exist Figure 1In the illustrated embodiment, the image processing pipeline 100 includes an RGB / IR camera 105, an IR emitter 110, an image processing module 115, a light-dependent operation mode control component 120, a light-independent operation mode control component 130, an operation mode selection component 140, a feature detector selector 150, one or more RGB feature detectors 160, one or more IR feature detectors 170, one or more RGB / IR feature detectors 180, and a rendering module 190. At a high level, the image processing pipeline 100 can operate in an RGB imaging mode in which the RGB / IR camera 105 and the image processing module 115 generate RGB image data 117 and / or an IR imaging mode in which the RGB / IR camera 105 and the image processing module 115 generate IR image data 119. In addition, the light-dependent operation mode control component 120 can control a light-dependent operation mode that switches between the RGB imaging mode and the IR imaging mode based at least on the amount of detected light intensity, and the light-independent operation mode control component 130 can control a light-independent operation mode that switches between the RGB imaging mode and the IR imaging mode at a fixed frame rate or interval. The operation mode selection component 140 can determine when to operate in the light-dependent operation mode and the light-independent operation mode (e.g., based on the speed 142 of the self-machine in which the RGB / IR camera 105 is operating and / or based on which gear 144 the self-machine is engaged) and switch the operation mode accordingly.

[0040] The availability of frames and / or streams of RGB image data 117 and IR image data 119 may depend on the operating (or conversion) mode, imaging mode, and / or embodiment, and thus feature detector selector 150 may identify an applicable downstream feature detector, package corresponding input data accordingly, and trigger corresponding feature detection (e.g., at a corresponding frame rate). Additionally or alternatively, depending on the availability of frames and / or streams of RGB image data 117 and IR image data 119, presentation module 190 may present a representation of RGB image data 117 and / or (e.g., color, grayscale) IR image data 119, for example, on a display visible to an occupant or operator of the self-machine. Although Figure 1 Some components are shown as separate, but this is not necessarily the case (eg, the functionality of some of the shown components may be combined into a common component).

[0041] The RGB / IR camera 105 may be any type of camera, optical sensor, or other device capable of generating image data in both visible light and IR bands. For example, the RGB / IR camera 105 may include or otherwise be associated with one or more (e.g., RGB) pixel sensors that may be used to observe visible light (e.g., RGB light) and generate visible light image data (e.g., RGB image data 117) representing a scene and / or one or more objects in the field of view of the RGB / IR camera 105. The RGB / IR camera 105 may include or otherwise be coordinated with an IR emitter 110 that may illuminate a target area in the field of view of the RGB / IR camera 105. Thus, the RGB / IR camera 105 may include or otherwise be associated with one or more IR sensors that may be used to observe or otherwise detect IR light (e.g., intensity of IR light) (e.g., radiated and / or reflected IR light) and generate IR image data (e.g., IR image data 119) representing a scene and / or one or more objects in the field of view of the RGB / IR camera 105. Visible light image data (e.g., RGB images) typically include pixels storing values ​​corresponding to detected colors. In contrast, IR image data (e.g., IR images) may include pixels storing values ​​corresponding to detected temperatures, and the IR image data 119 may be in the form of a grayscale image or a false color representation, where different shades of gray or different colors are used to represent different temperatures.

[0042] The RGB / IR camera 105 may be positioned and / or oriented in various ways depending on the application (e.g., sensing and / or detection tasks) and / or embodiment. For example, in the case of an application using the RGB / IR camera 105 to generate RGB image data 117 and IR image data 119 (e.g., images and / or videos) for use in a monitoring system, a security system, a photography or video system, a scientific or environmental observation system, and / or other types of systems, the RGB / IR camera 105 may be positioned and / or oriented to facilitate positioning a target area (e.g., an area or object being observed or monitored) within the field of view of the RGB / IR camera 105 and within a suitable distance from the RGB / IR camera 105. In applications involving, for example, vehicles (e.g., Figures 9A-9DIn example embodiments of self-objects such as vehicle 900 in the vehicle 900, the RGB / IR camera 105 can be positioned for interior or exterior sensing (e.g., OMS or driver monitoring system (DMS) cameras (e.g., OMS sensor 901 of vehicle 900), surround view cameras (e.g., surround view cameras 974 of vehicle 900)). Vehicle manufacturers tend to vary the number of OMS cameras by model and trim level, where any or all cameras and / or cameras in other locations can be implemented using the RGB / IR camera 105. These are just a few examples, and other applications, locations, and / or orientations of one or more RGB / IR cameras are also contemplated within the scope of the present disclosure.

[0043] The RGB / IR camera 105 may include a color filter array (CFA), such as an RGB-IR color filter array. The RGB-IR CFA is a variation of the standard Bayer CFA that replaces some locations in the color filter array that normally pass red, green, or blue light with IR filters that pass IR wavelengths (e.g., near infrared wavelengths) and block visible light. For example, for each 4x4 area of ​​the Bayer sensor, some embodiments replace two red filters and two blue filters with IR filters (e.g., IR cut filters with narrow passbands that match the emission peaks of the IR emitters 110), thereby forming a repeating pattern on the sensor. Although various embodiments are described as involving certain visible light (e.g., RGB) color channels, other combinations of color channels and / or corresponding CFAs are considered within the scope of the present disclosure.

[0044] The RGB / IR camera 105 may be equipped with an IR emitter 110 and may be configured to synchronize the illumination of the IR emitter 110 with the capture of image data. Additionally or alternatively, the RGB / IR camera 105 may be equipped with an interface that can be used to control image capture, illumination of the IR emitter 110, and / or one or more camera settings (e.g., exposure time / shutter speed, white balance, ISO setting, aperture, etc.). Although Figure 1 An embodiment is shown in which the IR emitter 110 is controlled by the RGB / IR camera 105, but this is not necessarily the case.

[0045] The image processing module 115 may be configured to receive image data from the RGB / IR camera 105 and perform any number and type of known image processing techniques (e.g., gamma correction, exposure compensation, tone mapping, noise reduction, removal of bad pixels, application of white balance, demosaicing, color correction, etc.) to generate RGB image data 117 and / or IR image data 119 (e.g., their corresponding frames). In general, the image data (e.g., each frame of image data) may represent a set of values ​​(e.g., resulting in corresponding resolutions) from visible light pixel sensors and IR pixel sensors arranged in any suitable manner, where the values ​​may include or otherwise represent intensity values ​​(e.g., from red, green, blue, and IR pixel sensors), color information (e.g., from RGB pixel sensors), monochrome information (e.g., from IR pixel sensors), calculated histograms (e.g., for each color channel, representing counts of pixels having a particular value or range of values), and / or the like. The image processing module 115 may include one or more image signal processors (ISPs), digital signal processors (DSPs), graphics processing units (GPUs), central processing units (CPUs), data processing units (DPUs), field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), some other integrated circuits, or a combination thereof.

[0046] Some embodiments may support one or more operating or transition modes that transition or switch between an RGB imaging mode and an IR imaging mode. For example, the light-dependent operating mode control component 120 may implement a light-dependent operating mode (e.g., a day-night mode) that dynamically transitions between an IR imaging mode and an RGB imaging mode in response to detected light intensity (e.g., as described in more detail below), and / or the light-independent operating mode control component 130 may implement a light-independent operating mode that transitions between an IR imaging mode and an RGB imaging mode at a fixed frame rate or interval. Depending on which operating mode is active (or implemented by a particular embodiment), the light-dependent operating mode control component 120 or the light-independent operating mode control component 130 (or some other component) may communicate with the RGB / IR camera 105, the IR emitter 110, the image processing module 115, the feature detector selector, and / or other components to transition between the IR imaging mode and the RGB imaging mode.

[0047] In an example implementation involving an IR imaging mode, the light-dependent operating mode control component 120 or the light-independent operating mode control component 130 can control, trigger, instruct, or otherwise facilitate activation and / or operation of the IR imaging mode, which illuminates the IR emitter 110, sets the RGB / IR camera 105 to have a specified exposure time that accommodates expected scene lighting (e.g., low visible light plus IR illumination), triggers the image processing module 115 to generate IR image data 119 (e.g., a grayscale image that may include or be based in part on RGB data), and / or determines not to generate or discards RGB image data. 117, triggering the feature detector selector 150 to apply the generated representation of the IR image data 119 to one or more machine learning models (e.g., the IR feature detector 170) configured to operate on the IR image data (e.g., at some specified frame rate), and / or triggering the presentation module 190 to present the generated representation of the IR image data 119 (e.g., one or more still images and / or resulting video, grayscale and / or color) on a display (e.g., visible to an operator or occupant of a self-machine that is using or otherwise associated with the RGB / IR camera 105).

[0048] In an example implementation involving an RGB mode imaging mode, the light-dependent operating mode control component 120 or the light-independent operating mode control component 130 can control, trigger, instruct, or otherwise facilitate activation and / or operation of the RGB imaging mode, which turns off the IR emitter 110 (or ensures that it remains off), sets the RGB / IR camera 105 to have a specified exposure time that is appropriate for expected scene lighting (e.g., visible light), triggers the image processing module 115 to generate RGB image data 117 (e.g., by subtracting the amount of detected IR light intensity from the detected light intensity in one or more visible light channels), and / or or determining not to generate or discard IR image data 119, triggering feature detector selector 150 to apply the generated representation of RGB image data 117 to one or more machine learning models (e.g., RGB feature detector 160) configured to operate on RGB image data (e.g., at some specified frame rate), and / or triggering presentation module 190 to present the generated representation of RGB image data 117 (e.g., one or more still images and / or resulting video) on a display (e.g., visible to an operator or occupant of an ego machine that is using or otherwise associated with RGB / IR camera 105). These are just a few possible ways that RGB and / or IR imaging modes may be implemented.

[0049] In some embodiments, the light-dependent operating mode may switch between an RGB imaging mode and an IR imaging mode based on the amount of detected light intensity. Figure 2 is a data flow diagram illustrating an example image processing pipeline 200 supporting a light-dependent mode of operation according to some embodiments of the present disclosure. Figure 2 The embodiment shown in FIG. Figure 1 A subset of components of the image processing pipeline 100 may be used to implement an example light-dependent mode of operation. Figure 2 In the implementation scheme, the light-related operation mode control component 120 includes a light detection component 222, an IR imaging mode control component 224 and an RGB imaging mode control component 226.

[0050] At a high level, the light detection component 222 can determine, calculate, or otherwise access a measure of detected light intensity, the IR imaging mode control component 224 can apply logic for determining when to activate the IR imaging mode and activating the IR imaging mode, and the RGB imaging mode control component 226 can apply logic for determining when to activate the RGB imaging mode and activating the RGB imaging mode. For example, the image processing pipeline 200 can operate at a specified frame rate (e.g., 30 frames per second (fps)), the light detection component 222 can analyze each frame of image data generated by the RGB / IR camera 105 and / or the image processing module 115 to determine a measure of detected light intensity in the frame, and the IR imaging mode control component 224 and / or the RGB imaging mode control component 226 can use the measure of detected light intensity to determine whether to apply a corresponding control (e.g., switch to IR imaging mode or RGB imaging mode) before the RGB / IR camera 105 and / or the image processing module 115 generates a subsequent frame.

[0051] The light detection component 222 can determine, calculate, or otherwise access a measurement of the intensity of the detected light in various ways. As a non-limiting example, each pixel sensor (e.g., per color channel) can output a value (e.g., expressed in digital units) that is proportional to the product of the light intensity incident on the pixel sensor, the exposure time, and the sensor gain, so the light detection component 222 and / or the image processing module 115 can divide the output of any given pixel sensor by the known exposure time and sensor gain of the pixel sensor to calculate the intensity measurement value of each pixel. In this way, the light detection component 222 can calculate the average intensity of one or more pixels in one or more color channels in each frame.

[0052] In some embodiments, the light detection component 222 uses a histogram of values ​​to calculate the average intensity. For example, the light detection component 222 and / or the image processing module 115 can calculate a histogram representing pixel counts with a specific (e.g., digital unit or intensity) value or value range (e.g., in each color channel in one or more color channels). The light detection component 222 and / or the image processing module 115 can bin the values ​​and count the number of pixels in each bin (e.g., in each channel). According to an embodiment, the digital unit values ​​can be binned and converted to intensity values, and / or the digital unit values ​​can be converted to intensity values ​​and then binned. Therefore, the light detection component 222 can calculate the average intensity (e.g., in each color channel in one or more color channels) using a weighted average of the intensity values ​​weighted by the pixel counts of each bin.

[0053] In some embodiments, the light detection component 222 may bin, average, and / or otherwise consider only those pixels in a specified region of interest. Taking the example embodiment where the RGB / IR camera 105 is positioned to view the interior of a vehicle cabin with a window, where the monitoring target (e.g., an operator or occupant) is located inside the cabin, a portion of the field of view of the RGB / IR camera 105 may not be of interest (e.g., pixels representing the area outside the cabin through the window). Therefore, a region of interest can be specified to identify some subset of pixels in each frame. For example, one or more shapes (e.g., an ellipse, a rectangle, an intersection of multiple shapes, any geometric primitives, etc.) can be located in the frame (e.g., centered on the area where the operator or occupant's face and / or body is expected to be located), where one or more shapes and / or positioning can be fixed or dynamic (e.g., a detected mask or bounding box predicted to contain the monitoring target (e.g., a detected face or a detected person)). Thus, light detection component 222 may bin, average, and / or otherwise consider only those pixels within a designated area of ​​each frame when determining measurements of detected light intensity.

[0054] In some embodiments, light detection component 222 can discard or ignore pixels (e.g., highlights and / or lowlights) whose intensity values ​​exceed a certain (e.g., statistical) threshold. For example, the tails of a histogram can represent outliers in the intensity values, so light detection component 222 can discard or ignore some top and / or bottom percentile (e.g., 5% or 10%) intensity values ​​from the average, effectively discarding or ignoring the tails of the histogram, which should reduce the risk of the tails disproportionately affecting the average.

[0055] Thus, light detection component 222 can determine, calculate, or otherwise access average intensity values ​​in each of one or more color channels (eg, in a specified region of interest) (eg, green G (G avg ) and IR(I avg ) channel). Note that certain embodiments described herein focus on calculating and applying one or more thresholds to average the intensity in the green channel because the green channel is typically wider than the red and blue channels and therefore can capture more ambient light and can more accurately represent the intensity of ambient light in certain scenes (e.g., in the presence of red or blue light) than using the red or blue channels. However, this is not necessarily the case, and certain embodiments may average the intensities and apply corresponding thresholds in any desired channel of visible light (e.g., red / blue / green, red / yellow / blue, cyan / yellow / magenta, cyan / yellow / green / magenta, etc.) and / or channel combinations (e.g., weighted averages across multiple channels).

[0056] In some embodiments, the IR imaging mode control component 224 determines a measurement of the detected light intensity (eg, G avg ) is less than a certain threshold intensity level, and if so, triggers the IR imaging mode (or if the image processing pipeline 200 is already in the IR imaging mode, maintains the operation in the IR imaging mode). In some embodiments, the RGB imaging mode control component 226 determines the measured value of the detected light intensity (e.g., G avg ) is greater than a certain threshold intensity level and / or determines a certain measure of the detected light intensity across multiple color channels (e.g., such as I avg / G avg The RGB imaging mode control component 226 may trigger the RGB imaging mode (or maintain the operation in the RGB imaging mode if the image processing pipeline 200 is already in the RGB imaging mode) if one or both of them are true.

[0057] In some embodiments, the IR imaging mode control component 224 and the RGB imaging mode control component 226 apply different threshold intensity levels. The gap between the intensity thresholds can simulate a hysteresis effect that can reduce or prevent abrupt changes between the IR imaging mode and the RGB imaging mode in response to relatively small changes in detected intensity. As an illustration, Figure 3 3 shows an example detected light intensity threshold for switching between IR imaging mode and RGB imaging mode according to some embodiments of the present disclosure. In this example, the intensity axis 310 represents a value from 0.01 to 10 6310 (in LUX), and a range of intensity values ​​that an example camera is capable of capturing. Aligned with intensity axis 310 (in LUX) are two other intensity axes, intensity axis 320 representing a first range of intensity values ​​(expressed in digits (DN)) that the camera is capable of capturing in RGB imaging mode (e.g., when the ambient light is at least a threshold amount, such as during the day), and intensity axis 330 representing a second range of intensity values ​​(expressed in digits (DN)) that the camera is capable of capturing in IR imaging mode (e.g., when the ambient light is less than the threshold amount, such as at night). Intensity axes 320 and 330 are offset due to the longer exposure time in the example IR imaging mode than in the example RGB imaging mode, mapping the same digit to a lower intensity value (in LUX).

[0058] Intensity axis 320 shows an example threshold intensity level T1, which is lower than an example threshold intensity level T2 on intensity axis 330. For example, assume that the example image processing pipeline is in RGB imaging mode. The area to the right of threshold intensity level T1 on intensity axis 320 represents a range of detected intensity values ​​(e.g., derived from the green channel) at which the image processing pipeline can continue to operate in RGB imaging mode. Once an intensity value is detected to the left of threshold intensity level T1, the image processing pipeline can switch to IR imaging mode (e.g., night mode). Subsequent detected intensity values ​​can be tested relative to threshold intensity level T2 shown on intensity axis 330. The area to the left of threshold intensity level T2 on intensity axis 330 represents a range of detected intensity values ​​(e.g., derived from the green channel) at which the image processing pipeline can continue to operate in IR imaging mode. Once an intensity value is detected to the right of threshold intensity level T2 (and / or the ratio of detected light intensities across multiple color channels is less than some other threshold), the image processing pipeline can switch to RGB imaging mode (e.g., day mode).

[0059] Thresholds T1 and T2 may be selected in any suitable manner. In some embodiments, different thresholds T1 and T2 may be selected to form a gap that simulates a hysteresis effect when transitioning between imaging modes. For example, in some embodiments, a threshold T1 is selected below which the signal-to-noise ratio (SNR) is deemed undesirable (because detected light intensities below threshold T1 may trigger an IR imaging mode, which may include illuminating an IR emitter). Taking an example embodiment involving in-cabin sensing to detect the presence of a child in a vehicle footwell, threshold T1 may be selected at or near a point where the resulting image is too dark to detect any object in the footwell. In some embodiments, threshold T2 may be selected to be greater than threshold T1 and to provide a sufficiently large gap to prevent jumping between imaging modes in response to relatively small changes in detected intensity. By way of non-limiting example, the gap between threshold intensity levels may correspond to three f-stops.

[0060] Back to Figure 2 In some embodiments, the RGB imaging mode control component 226 checks multiple conditions before switching from the IR imaging mode to the RGB imaging mode. For example, if the IR imaging mode control component 224 determines that the detected light intensity (e.g., G avg ) is less than a certain threshold value T1, the scene may be dark, so the IR imaging mode control component 224 may need to turn on the IR imaging mode (e.g., turn on the IR emitter 110). avg ) is greater than some threshold T2, the ambient light may still be low, but the detected light intensity may be high due to the illumination produced by the IR emitter 110. The quantum efficiency of the pixel sensor explains why the detected light intensity may be high even in the absence of ambient light. Figure 4 Example quantum efficiency curves for the green and IR bands according to some embodiments of the present disclosure are shown. Note that the quantum efficiency of the sensor for the green channel (which represents how many photons are converted into electrons in the sensor) is almost equal to the quantum efficiency of the IR channel in the IR wavelength (approximately 780 nanometers to 1 millimeter). In other words, the pixel sensor for the green channel can pick up light from the IR band, so even in the dark, in the presence of IR illumination, the detected light intensity may still be high. If the IR emitter 110 is turned off in this case, the SNR of the resulting image may be insufficient or suboptimal. Therefore, in addition to determining the measured value of the detected light intensity (e.g., G avg) is greater than a certain threshold intensity level, the RGB imaging mode control component 226 can also determine whether there is a certain baseline amount of ambient light, for example, by determining the measured values ​​of the detected light intensity across multiple color channels (e.g., such as I avg / G avg is less than a certain threshold T (or whether its reciprocal is greater than a certain threshold T).

[0061] The threshold T used to determine whether a baseline amount of ambient light is present can be selected in any suitable manner. For example, the threshold T can be selected so that IR energy does not dominate the energy in the visible light range. Typically, ambient light sources have very small amounts of energy in the IR wavelengths. Due to the quantum efficiency design of most RGB / IR cameras, the I avg / G avg The ratio can be approximated as:

[0062] I avg / G avg =I energy / (I energy +Visible energy )(Equation 1)

[0063] Among them I energy is a measure of the energy or pixel value in the IR wavelength, while Visible energy It is a measure of the energy or pixel value in visible wavelengths. energy For I energy Solve equation 1 by multiplying the specified number X by . Therefore, the Visible energy Or the pixel value should be greater than I in IR imaging mode energy Or how many times larger the pixel value is X to determine the example threshold T:

[0064] T = 1 / (1+X) (Equation 2)

[0065] These are just a few examples of possible thresholds, and other thresholds are also considered within the scope of the present disclosure.Thus, in response to detecting light intensity meeting or exceeding one or more thresholds, the light-dependent operating mode can be used to switch between the IR imaging mode and the RGB imaging mode.

[0066] Back to Figure 1 In some embodiments, the light-independent operation mode control component 130 can implement a light-independent operation mode that switches between the RGB imaging mode and the IR imaging mode at a fixed frame rate or interval. Figure 5An example timeline for switching between an IR imaging mode and an RGB imaging mode at a fixed frame rate or interval according to some embodiments of the present disclosure is shown. The example timeline represents switching at a fixed frame rate (e.g., 30 or 60fps) or interval such that the IR imaging mode (A frames) and the RGB imaging mode (B frames) alternate. Taking the example embodiment of switching at 60fps as an example, the IR frames and the RGB frames can be effectively generated at a lower frame rate (e.g., 30fps each). Thus, the light-independent operating mode can generate a stream of IR image data 119 and RGB image data 117.

[0067] In some embodiments, feature detector selector 150 may select a feature detector corresponding to an imaging mode. For example, when image processing pipeline 100 is in an IR imaging mode, feature detector selector 150 may apply a representation of IR image data 119 to one or more machine learning models (e.g., one or more IR feature detectors 170) configured to operate on IR image data, and / or when image processing pipeline 100 is in an RGB imaging mode, feature detector selector 150 may apply a representation of RGB image data 117 to one or more machine learning models (e.g., one or more RGB feature detectors 160) configured to operate on RGB image data. In some embodiments, this may be done independently of whether image processing pipeline 100 is operating in a light-dependent operating mode or a light-independent operating mode.

[0068] Additionally or alternatively, in some embodiments, such as embodiments that switch between an RGB imaging mode and an IR imaging mode at an appropriate rate (e.g., when operating a light-independent operating mode at a specified frame rate), feature detector selector 150 may group and / or otherwise encode together frames of RGB image data 117 and IR image data 119 representing multiple (e.g., consecutive) time slices (or one or more encompassing time slices) to form corresponding representations and apply them to one or more machine learning models (e.g., one or more RGB / IR feature detectors 180) that are configured to operate on RGB image data and IR image data, for example, at some specified frame rate.

[0069] Some embodiments may support multiple modes of operation or transition (e.g., light-dependent modes of operation and light-independent modes of operation) that transition or switch between RGB imaging modes and IR imaging modes. Thus, the operation mode selection component 140 (or some other component) may select and enable the corresponding operation mode based on any suitable criteria. Taking the example embodiment where the RGB / IR camera 105 is associated with an ego machine (e.g., a vehicle) (e.g., an external or internal camera thereof), the operation mode selection component 140 may switch the operation mode based on the speed 142 of the ego machine's ego motion and / or the gear 144 engaged by the ego machine's transmission (e.g., park vs. drive, neutral vs. gear). For example, the operation mode selection component 140 may receive a representation of the speed 142 of the ego machine (e.g., a speed signal generated by a speed sensor and / or derived by an inertial measurement unit) and / or a representation of the gear 144 engaged by the ego machine's transmission, and the operation mode selection component 140 may select and enable the operation mode based on the speed 142 and / or the gear 144.

[0070] In some embodiments, the operating mode selection component 140 can select and enable the light-independent operating mode based on determining that the self-machine is in motion (e.g., speed 142 is non-zero), traveling at (e.g., speed 142 is) above a threshold speed, and / or in a particular gear (e.g., driving, in gear), thereby facilitating relatively faster transition times and better performance of detection tasks during transitions between imaging modes. For example, when driving into and out of a tunnel or parking lot, the interior of the vehicle may experience frequent, rapid, and / or drastic lighting changes, and operating or transition modes such as these can have relatively short transition delays, which provide better data coverage during lighting transitions (e.g., because the imaging mode does not switch based on lighting changes). In some embodiments, the operating mode selection component 140 can select and enable the light-dependent operating mode based on determining that the self-machine is stationary (e.g., speed 142 is zero), traveling at (e.g., speed 142) below a threshold speed, and / or parked (or out of gear). Because an operation or conversion mode such as this can effectively generate a single image data stream at a time, it can operate at a higher frame rate and use lower bandwidth and less data processing than an operation or conversion mode that generates two simultaneous streams, thereby effectively saving resources when frequent or rapid lighting changes are not expected (for example, because the vehicle is stationary).

[0071] Switching operating modes like this can optimize the performance of downstream feature detectors. Generally, RGB feature detector 160, IR feature detector 170 and / or RGB / IR feature detector 180 can perform feature detection on the corresponding input data using any known technology. For example, RGB feature detector 160, IR feature detector 170 and / or RGB / IR feature detector 180 can be implemented using one or more deep neural networks (DNNs) such as convolutional neural networks (CNNs). Although certain embodiments are described as using neural networks to implement RGB feature detector 160, IR feature detector 170 and / or RGB / IR feature detector 180, this is not intended to be limiting. For example, but not limited to, the RGB feature detector 160, the IR feature detector 170 and / or the RGB / IR feature detector 180 may include any type of multiple different networks or machine learning models, such as machine learning models using linear regression, logistic regression, decision trees, support vector machines (SVM), naive Bayes, k-nearest neighbors (Knn), K-means clustering, random forests, dimensionality reduction algorithms, gradient boosting algorithms, neural networks (e.g., autoencoders, convolutions, transformers, loops, perceptrons, long / short term memory (LSTM), Hopfield, Boltzmann, deep belief, deconvolution, generative adversarial, liquid machines, etc.), and / or other types of machine learning models.

[0072] When the self-machine is in motion, traveling at a speed above a threshold, and / or in a corresponding gear, the self-machine may experience frequent and rapid lighting changes, such as entering and exiting tunnels, parking lots, and other scenarios. In this case, the light-independent operation mode has advantages over the light-dependent operation mode because the delay in the light-dependent operation mode causes transition delays, which may cause undesirable or unusable frames during the transition phase. In contrast, the light-independent operation mode can capture RGB and IR image data streams (e.g., in a synchronized manner), which effectively provides two types of data for any given frame or surrounding time slice. Therefore, both types of data should be available for downstream processing and analysis by the RGB feature detector 160 (e.g., for each frame of RGB image data 117), the IR feature detector 170 (e.g., for each frame of IR image data 119), and / or the RGB / IR feature detector 180 (e.g., for pairs of frames of RGB image data 117 and IR image data 119). Example feature detectors that may be enabled while the self-machine is in motion include feature detectors for driver distraction detection, driver drowsiness detection, driver hands on the steering wheel detection, driver and / or occupant 3D pose estimation (e.g., for size-based age estimation, gesture recognition), monocular depth estimation, and / or other feature detectors. In the light-independent mode of operation, the availability of both types of data provides flexibility in selecting the desired downstream feature detector. For example, the feature detector selector 150 may use the RGB feature detector 160 for each RGB frame and may use the IR feature detector 170 for each IR frame, and / or may select the RGB feature detector 160 or the IR feature detector 170, for example, based on the amount of detected light intensity (e.g., detected using an ambient light sensor, detected based on a measurement of the detected light intensity of the previous frame). This flexibility may be advantageous in scenarios where real-time decision making or immediate access to all data is critical (e.g., in the case of driver hands on the steering wheel detection).

[0073] In some embodiments, the RGB / IR feature detector 180 that uses IR frames and RGB frames for reasoning provides multiple benefits. For example, in some cases, IR image data can better represent depth clues than RGB image data, which can be beneficial to occupant monitoring functions such as hands on the steering wheel detection, posture estimation, monocular depth estimation, etc. For hands on the steering wheel detection, RGB clues help the appearance and shape of the hand and grasping detection, but may not be able to distinguish certain depth ambiguities (for example, how far the driver's hand is from the steering wheel) that are difficult to resolve in two dimensions of the RGB color space. IR can help resolve these ambiguities, so the combination of RGB and IR can enhance the accuracy and robustness of the hands on the steering wheel detection algorithm. For depth estimation, IR image data provides additional depth clues to supplement RGB image data, especially in challenging scenes such as occlusion or low texture environments. The combination of IR and RGB image data can improve the accuracy of features such as monocular depth estimation, thereby enabling a more accurate understanding of the 3D structure of the scene. For 3D pose estimation, RGB data provides visual cues for estimating the positions of body joints, while IR can provide additional depth cues, helping resolve ambiguities and improving the accuracy of pose estimation in 3D space (e.g., which joint is in front, which joint is behind, etc.), especially for challenging poses and / or occluded scenes.

[0074] Furthermore, in some embodiments, the light-independent mode of operation facilitates comprehensive monitoring of both the driver and the occupants of the self-machine using a single sensor (i.e., the RGB / IR camera 105). In some embodiments, the RGB image data 117 may be used for occupant monitoring, such as detecting the number of occupants, tracking their movements, and / or analyzing their behavior. In the same time slice, the IR image data 119 from the same RGB / IR camera 105 may be used for driver monitoring, such as monitoring the driver's attention, detecting drowsiness or distraction, and / or tracking facial expressions. Thus, the light-independent mode of operation may facilitate simultaneous driver monitoring and occupant monitoring using different types of image data generated by the same RGB / IR camera 105.

[0075] When the self-machine is stationary, traveling at a speed below a threshold, and / or in a corresponding gear (or in neutral), frequent or rapid lighting changes are unlikely. In this case, the light-dependent operating mode can provide various advantages. For example, since the light-dependent operating mode can only capture one stream (RGB image data 117 or IR image data 119) at a time, it facilitates operation at a relatively high frame rate. For example, the light-independent operating mode can run at 60fps, but provide individual streams of RGB and IR image data at 30fps, while the light-dependent operating mode can run at 60fps, but generate RGB image data or IR image data at 60fps. This increased frame rate is beneficial for applications that require real-time or high-speed monitoring of occupant and driver behavior, thereby enabling more sensitive analysis and detection algorithms. In addition, the light-dependent operating mode can optimize bandwidth usage because it only generates one stream, thereby reducing the amount of data that needs to be transmitted, thereby optimizing bandwidth usage. In addition, the light-dependent operating mode can prioritize RGB image data under conditions of sufficient light, thereby reducing the processing load and resource requirements for processing both RGB image data and IR image data at the same time (or vice versa). By focusing only on RGB image data when appropriate, the light-dependent mode of operation can simplify the data processing pipeline and improve overall system efficiency. Example feature detectors that can be enabled when the self-machine is stationary include feature detectors for child presence detection, 3D pose estimation (e.g., for size-based age estimation, gesture recognition), monocular depth estimation, and / or others.

[0076] Reference now Figure 6 , Figure 7 and Figure 8 , each of the blocks of methods 600, 700, and 800 described herein includes a computing process that can be performed using any combination of hardware, firmware, and / or software. For example, various functions can be implemented by a processor executing instructions stored in a memory. These methods can also be embodied as computer-usable instructions stored on a computer storage medium. These methods can be provided by a stand-alone application, a service or a hosted service (standalone or in combination with another hosted service), or a plug-in for another product, to name a few. In addition, methods 600, 700, and 800 are provided as examples of Figure 1 The image processing pipeline 100 is described herein. However, these methods may additionally or alternatively be performed by any one system or any combination of systems, including but not limited to the systems described herein.

[0077] Figure 6 6 is a flow chart illustrating a method 600 for switching between an RGB imaging mode and an IR imaging mode based on light intensity according to some embodiments of the present disclosure. The method 600 includes, at block B602, generating a first frame of RGB image data based at least on operating an image processing pipeline in the RGB imaging mode. For example, Figure 1 and Figure 2 In the image processing pipelines 100 and 200 in FIG. 1 , the light-dependent operating mode control component 120 can control, trigger, indicate, or otherwise facilitate activation and / or operation of an RGB imaging mode that turns off the IR emitter 110 (or ensures that it remains off), sets the RGB / IR camera 105 to have a specified exposure time that accommodates expected scene lighting (e.g., visible light), triggers the image processing module 115 to generate RGB image data 117 (e.g., by subtracting the amount of detected IR light intensity from the amount of detected light intensity in one or more visible light channels), and / or determines not to generate or discards IR image data 117 . 19, triggering the feature detector selector 150 to apply the generated representation of the RGB image data 117 to one or more machine learning models (e.g., the RGB feature detector 160) configured to operate on the RGB image data (e.g., at some specified frame rate), and / or triggering the presentation module 190 to present the generated representation of the RGB image data 117 (e.g., one or more still images and / or resulting video) on a display (e.g., visible to an operator or occupant of an ego machine that is using or otherwise associated with the RGB / IR camera 105).

[0078] Method 600 includes, at block B604, switching to operating the image processing pipeline in an IR imaging mode to generate a second frame of infrared (IR) image data based at least on detecting that a first light intensity amount associated with the first frame of RGB image data is less than a first intensity threshold. Figure 2 In the image processing pipeline 200, the light detection component 222 can determine, calculate, or otherwise access a measurement of the detected light intensity, and the IR imaging mode control component 224 can determine a measurement of the detected light intensity (e.g., G avg ) is less than a certain threshold intensity level, and if so, the IR imaging mode can be triggered (or if the image processing pipeline 200 is already in the IR imaging mode, it is maintained to operate in the IR imaging mode). More specifically, with respect to Figure 1 and Figure 2In the image processing pipelines 100 and 200, the light-dependent operating mode control component 120 can control, trigger, indicate, or otherwise facilitate activation and / or operation of an IR imaging mode that illuminates the IR emitter 110, sets the RGB / IR camera 105 to have a specified exposure time that accommodates expected scene lighting (e.g., low visible light plus IR illumination), triggers the image processing module 115 to generate IR image data 119 (e.g., a grayscale image) and / or determines not to generate or discard RGB image data 117, triggers the feature detector selector 150 to generate IR image data 119 (e.g., a grayscale image), and / or triggers the feature detector selector 150 to generate IR image data 119 (e.g., a grayscale image). The representation of the IR image data 119 is applied to one or more machine learning models (e.g., IR feature detector 170) configured to operate on the IR image data (e.g., at some specified frame rate), and / or triggers a presentation module 190 to present a generated representation of the IR image data 119 (e.g., one or more still images and / or resulting video, in grayscale and / or color) on a display (e.g., visible to an operator or occupant of an ego machine using or otherwise associated with the RGB / IR camera 105).

[0079] Method 600 includes, at block B606, switching to operating the image processing pipeline in an RGB imaging mode based at least on detecting that a second light intensity amount associated with the second frame of IR image data exceeds a second intensity threshold. Figure 2 In the image processing pipeline 200, the RGB imaging mode control component 226 can determine the measured value of the detected light intensity (e.g., G avg ) is greater than a certain threshold intensity level and / or determines a certain measure of the detected light intensity across multiple color channels (e.g., such as I avg / G avg The RGB imaging mode control component 226 may trigger the RGB imaging mode (or maintain the operation in the RGB imaging mode if the image processing pipeline 200 is already in the RGB imaging mode) if one or both of them are true.

[0080] Figure 7 7 is a flow chart showing a method 700 for switching between an RGB imaging mode and an IR imaging mode based on different detected light intensity thresholds according to some embodiments of the present disclosure. The method 700 includes at block B702: calculating two example channels (green (G avg ) and IR(I avg )) is the average value of the detected light intensity. Figure 2In the image processing pipeline 200 of FIG. 2 , the light detection component 222 may calculate the average intensity of one or more pixels in one or more color channels in each frame. The light detection component 222 may calculate the average intensity (e.g., in each of the one or more color channels) using a weighted average of the intensity values ​​weighted by the pixel counts in each bin of the corresponding histogram. In some embodiments, the light detection component 222 may bin, average, and / or otherwise consider only those pixels in a specified region of interest, and / or may discard or ignore pixels (e.g., high light and / or low light) whose intensity values ​​exceed a certain (e.g., statistical) threshold. Thus, the light detection component 222 may determine, calculate, or otherwise access the average intensity value in each of the one or more color channels (e.g., in a specified region of interest) (e.g., green G (G avg ) and IR(I avg ) channel’s average intensity value).

[0081] Method 700 includes, at block B704: determining G avg Is it less than the first detection light intensity threshold? Figure 2 The image processing pipeline 200, the IR imaging mode control component 224 can determine a measured value of the detected light intensity (e.g., G avg ) is less than a certain threshold intensity level. If so, the method 700 proceeds to block B706, which includes turning on the IR imaging mode. For example, for Figure 2 If the image processing pipeline 200 is in IR imaging mode, the IR imaging mode control component 224 may trigger the IR imaging mode (or maintain operation in the IR imaging mode if the image processing pipeline 200 is already in IR imaging mode). Otherwise, the method 700 may proceed to blocks B708 ​​and B710.

[0082] Method 700 includes, at block B708, determining G avg Is it greater than the second detection light intensity threshold? Figure 2 The image processing pipeline 200 of the embodiment of the present invention can be used to determine the measured value of the detected light intensity (e.g., G avg ) is greater than a certain threshold intensity level.

[0083] Method 700 includes, at block B710, determining G avg Is it greater than the second detection light intensity threshold? Figure 2 In the image processing pipeline 200, the RGB imaging mode control component 226 can determine a certain measurement value (e.g., such as I avg / G avg is less than a certain threshold level (or whether its reciprocal is greater than a certain threshold level).

[0084] Method 700 includes, at block B712 (illustrated as an AND gate), determining whether both conditions determined at blocks B708 ​​and B710 are true. If true, method 700 proceeds to block B714, which includes turning on the RGB imaging mode. For example, for Figure 2 The image processing pipeline 200 of the embodiment of the present invention can be used to determine the measured value of the detected light intensity (e.g., G avg ) is greater than a certain threshold intensity level, and determining a certain measurement of the detected light intensity across multiple color channels (e.g., such as I avg / G avg The RGB imaging mode control component 226 may determine whether the ratio of the image processing pipeline 200 to the RGB imaging mode is less than a certain threshold level (or whether the inverse thereof is greater than a certain threshold level). If both are true, the RGB imaging mode control component 226 may trigger the RGB imaging mode (or if the image processing pipeline 200 is already in the RGB imaging mode, maintain operation in the RGB imaging mode).

[0085] Figure 8 8 is a flow chart illustrating a method 800 for switching between operating modes of an image processing pipeline based at least on a speed or active gear of a self machine according to some embodiments of the present disclosure. The method 800 includes, at block B802, operating the image processing pipeline of the self machine in a first operating mode that switches between an RGB imaging mode and an infrared (IR) imaging mode at a fixed rate. For example, for Figure 1 In the image processing pipeline 100, the light-independent operation mode control component 130 can implement a light-independent operation mode that switches between the RGB imaging mode and the IR imaging mode at a fixed frame rate or interval. Figure 5 An example timeline of switching between IR imaging mode and RGB imaging mode at a fixed frame rate or interval is shown in accordance with some embodiments of the present disclosure.

[0086] Method 800 includes, at block B804, switching to operate the image processing pipeline in a second operating mode based at least on the speed or active gear of the self machine, the second operating mode switching between an RGB imaging mode and an IR imaging mode based at least on the amount of detected light intensity. Figure 1In the image processing pipeline 100 of FIG. 1 , the operation mode selection component 140 can switch the operation mode based on the speed 142 of the self-motion of the self-machine associated with the image processing pipeline 100 (e.g., the vehicle in which at least a portion of the image processing pipeline 100 is operated) and / or the gear 144 (e.g., parked vs. driven, neutral vs. engaged) of the transmission of the self-machine. When the self-machine is stationary, traveling at a speed below a threshold, and / or in a corresponding gear (or neutral), frequent or rapid lighting changes are unlikely. Therefore, the operation mode selection component 140 can select and enable the light-related operation mode based on determining that the self-machine is stationary (e.g., the speed 142 is zero), traveling at a speed (e.g., the speed 142) below a threshold speed, and / or in a parked state (or out of gear).

[0087] The systems and methods described herein may be used by, but are not limited to, non-autonomous vehicles, semi-autonomous vehicles (e.g., in one or more adaptive driver assistance systems (ADAS)), manned and unmanned robots or robotic platforms, warehouse vehicles, off-road vehicles, vehicles connected to one or more trailers, airships, boats, shuttles, emergency response vehicles, motorcycles, electric or motorized bicycles, airplanes, engineering vehicles, trains, submarines, remotely operated vehicles such as drones, and / or other vehicle types. In addition, the systems and methods described herein may be used for a variety of purposes, such as, but not limited to, for machine control, machine motion, machine driving, synthetic data generation, model training, perception, augmented reality, virtual reality, mixed reality, robotics, safety and surveillance, simulation and digital twins, autonomous or semi-autonomous machine applications, deep learning, environmental simulation, object or actor simulation and / or digital twins, data center processing, conversational AI, light transport simulation (e.g., ray tracing, path tracing, etc.), collaborative content creation of 3D assets, cloud computing, generative AI, and / or any other suitable application.

[0088] The disclosed embodiments may be included in a variety of different systems, such as automotive systems (e.g., control systems for autonomous or semi-autonomous machines, perception systems for autonomous or semi-autonomous machines), systems implemented using robots, aviation systems, medical systems, boating systems, smart area monitoring systems, systems for performing deep learning operations, systems for performing simulation operations, systems for performing digital twin operations, systems implemented using edge devices, systems incorporating one or more virtual machines (VMs), systems for performing synthetic data generation operations, systems implemented at least in part in a data center, systems for performing conversational AI operations, systems implementing one or more language models (such as, one or more large language models (LLMs)), systems for performing light transport simulations, systems for performing collaborative content creation for 3D assets, systems implemented at least in part using cloud computing resources, and / or other types of systems.

[0089] Example Autonomous Vehicle

[0090] Fig.9A is an illustration of an example autonomous vehicle 900 according to some embodiments of the present disclosure. Autonomous vehicle 900 (also referred to herein as “vehicle 900”) may include, but is not limited to, a passenger vehicle, such as a car, a truck, a bus, an emergency vehicle, a shuttle, an electric or motorized bicycle, a motorcycle, a fire truck, a police car, an ambulance, a boat, an engineering vehicle, a submarine, a robotic vehicle, an airplane, a drone, a vehicle connected to a trailer (e.g., a semi-trailer truck for transporting goods), and / or other types of vehicles (e.g., unmanned and / or capable of accommodating one or more passengers). Autonomous vehicles are generally described according to the automation levels defined by the National Highway Traffic Safety Administration (NHTSA) of the U.S. Department of Transportation and the Society of Automotive Engineers (SAE) in the “Classification and Definition of Terms Related to Driving Automation Systems for Road Motor Vehicles” (Standard No. J3016-201806 issued on June 15, 2018, Standard No. J3016-201609 issued on September 30, 2016, and previous and future versions of the standard). The vehicle 900 may be capable of having one or more functions according to levels 3-5 of autonomous driving levels. The vehicle 900 may be capable of functioning according to one or more of levels 1-5 of autonomous driving levels. For example, the vehicle 900 may be capable of providing driver assistance (level 1), partial automation (level 2), conditional automation (level 3), high automation (level 4) and / or full automation (level 5), depending on the embodiment. As used herein, the term "autonomy" may include any and / or all types of autonomy of the vehicle 900 or other machines, such as full autonomy, high autonomy, conditional autonomy, partial autonomy, providing assisted autonomy, semi-autonomy, main autonomy or other names.

[0091] The vehicle 900 may include components such as a chassis, a body, wheels (e.g., 2, 4, 6, 8, 18, etc.), tires, axles, and other components of the vehicle. The vehicle 900 may include a propulsion system 950, such as an internal combustion engine, a hybrid power plant, an all-electric engine, and / or another type of propulsion system. The propulsion system 950 may be connected to a drive train of the vehicle 900, which may include a transmission, to achieve propulsion of the vehicle 900. The propulsion system 950 may be controlled in response to receiving a signal from a throttle / accelerator 952.

[0092] A steering system 954, which may include a steering wheel, may be used to steer the vehicle 900 (e.g., along a desired path or route) when the propulsion system 950 is operating (e.g., when the vehicle is in motion). The steering system 954 may receive signals from a steering actuator 956. For fully automated (Level 5) functionality, a steering wheel may be optional.

[0093] Brake sensor system 946 may be used to operate vehicle brakes in response to receiving signals from brake actuator 948 and / or brake sensors.

[0094] May include one or more system on chip (SoC) 904 ( Fig. 9C ) and / or one or more controllers 936 of one or more GPUs may provide signals (e.g., representing commands) to one or more components and / or systems of the vehicle 900. For example, the one or more controllers may send signals to operate vehicle brakes via one or more brake actuators 948, to operate a steering system 954 via one or more steering actuators 956, and to operate a propulsion system 950 via one or more throttles / accelerators 952. The one or more controllers 936 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 representing commands) to enable autonomous driving and / or assist a human driver in driving the vehicle 900. The one or more controllers 936 may include a first controller 936 for autonomous driving functions, a second controller 936 for functional safety functions, a third controller 936 for artificial intelligence functions (e.g., computer vision), a fourth controller 936 for infotainment functions, a fifth controller 936 for redundancy in emergency situations, and / or other controllers. In some examples, a single controller 936 may handle two or more of the above functions, two or more controllers 936 may handle a single function, and / or any combination thereof.

[0095] The one or more controllers 936 may provide signals for controlling one or more components and / or systems of the vehicle 900 in response to sensor data (e.g., sensor input) received from one or more sensors. The sensor data may be received from, for example and without limitation, a global navigation satellite system sensor 958 (e.g., a global positioning system sensor), a RADAR sensor 960, an ultrasonic sensor 962, a LIDAR sensor 964, an inertial measurement unit (IMU) sensor 966 (e.g., an accelerometer, a gyroscope, a magnetic compass, a magnetometer, etc.), a microphone 996, a stereo camera 968, a wide angle camera 970 (e.g., a fisheye camera), an infrared camera 972, a surround camera 974 (e.g., a 360 degree camera), a long-range and / or mid-range camera 998, a speed sensor 944 (e.g., for measuring the velocity of the vehicle 900), a vibration sensor 942, a steering sensor 940, a brake sensor (e.g., as part of a brake sensor system 946), one or more occupant monitoring system (OMS) sensors 901 (e.g., one or more interior cameras), and / or other sensor types.

[0096] One or more of the controllers 936 may receive inputs (e.g., represented by input data) from the instrument cluster 932 of the vehicle 900 and provide outputs (e.g., represented by output data, display data, etc.) via a human machine interface (HMI) display 934, an audible annunciator, a speaker, and / or via other components of the vehicle 900. These outputs may include information such as vehicle speed, velocity, time, map data (e.g., Fig. 9C The HMI display 934 may display information about the presence of one or more objects (e.g., street signs, warning signs, traffic light changes, etc.) and / or information about driving maneuvers that the vehicle has made, is making, or will make (e.g., changing lanes now, leaving 34B in two miles, etc.).

[0097] The vehicle 900 further includes a network interface 924 that can communicate via one or more networks using one or more wireless antennas 926 and / or a modem. For example, the network interface 924 may be capable of communicating via Long Term Evolution (“LTE”), Wideband Code Division Multiple Access (“WCDMA”), Universal Mobile Telecommunications System (“UMTS”), Global System for Mobile Communications (“GSM”), IMT-CDMA Multi-Carrier (“CDMA2000”), etc. The one or more wireless antennas 926 may also enable communication between objects in the environment (e.g., vehicles, mobile devices, etc.) using 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 (LPWANs) such as LoRaWAN, SigFox, etc.

[0098] Fig. 9B For use according to some embodiments of the present disclosure Fig.9A An example of camera positions and fields of view for an example autonomous vehicle 900 is shown. The cameras and respective fields of view are an example embodiment and are not intended to be limiting. For example, additional and / or replaceable cameras may be included, and / or the cameras may be located at different locations on the vehicle 900.

[0099] The camera type for the camera may include, but is not limited to, a digital camera that may be suitable for use with components and / or systems of the vehicle 900. The camera may operate at an automotive safety integrity level (ASIL) B and / or at another ASIL. The camera type may have any image capture rate, such as 60 frames per second (fps), 120fps, 240fps, etc., depending on the embodiment. The camera may be capable of using a rolling shutter, a global shutter, another type of shutter, or a combination thereof. In some examples, the color filter array may include a red transparent (RCCC) color filter array, a red 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 some embodiments, a clear pixel camera such as a camera with an RCCC, RCCB, and / or RBGC color filter array may be used in an effort to improve light sensitivity.

[0100] In some examples, one or more of the cameras can be used to perform advanced driver assistance system (ADAS) functions (e.g., as part of a redundant or fail-safe design). For example, a multi-function monocular camera can be installed to provide functions including lane departure warning, traffic sign assistance, and intelligent headlight control. One or more of the cameras (e.g., all of the cameras) can simultaneously record and provide image data (e.g., video).

[0101] One or more of the cameras may be mounted in a mounting assembly such as a custom designed (three-dimensional ("3D") printed) assembly to cut out stray light and reflections from within the car (e.g., reflections from the dashboard reflected in the windshield mirror) that may interfere with the camera's image data capture capabilities. With respect to the wing mirror mounting assembly, the wing mirror assembly may be custom 3D printed so that the camera mounting plate matches the shape of the wing mirror. In some examples, one or more cameras may be integrated into the wing mirror. For the side view cameras, one or more cameras may also be integrated into the four pillars at each corner of the cab.

[0102] A camera (e.g., a front-facing camera) having a field of view that includes a portion of the environment in front of the vehicle 900 can be used for surround view to help identify the forward path and obstacles, as well as assist in providing information critical to generating an occupancy grid and / or determining a preferred vehicle path with the help of one or more controllers 936 and / or control SoCs. The front-facing camera can be used to perform many of the same ADAS functions as LIDAR, including emergency braking, pedestrian detection, and collision avoidance. The front-facing camera can also be used for ADAS functions and systems, including lane departure warning ("LDW"), autonomous cruise control ("ACC"), and / or other functions such as traffic sign recognition.

[0103] A variety of cameras may be used in the front-facing configuration, including, for example, a monocular camera platform including a complementary metal oxide semiconductor ("CMOS") color imager. Another example may be a wide-angle camera 970, which may be used to sense objects (e.g., pedestrians, intersection traffic, or bicycles) entering the field of view from the periphery. Fig. 9B Only one wide-angle camera is shown in the figure, but there may be any number (including zero) of wide-angle cameras 970 on the vehicle 900. In addition, any number of long-range cameras 998 (e.g., a long-view stereo camera pair) may be used for depth-based object detection, especially for objects for which a neural network has not been trained. Long-range cameras 998 may also be used for object detection and classification and basic object tracking.

[0104] Any number of stereo cameras 968 may also be included in the front configuration. In at least one embodiment, one or more of the stereo cameras 968 may include an integrated control unit including a scalable processing unit that may provide a multi-core microprocessor and programmable logic (FPGA) with an integrated controller area network ("CAN") or Ethernet interface on a single chip. Such a unit can be used to generate a 3D map of the vehicle environment, including distance estimates for all points in the image. An alternative stereo camera 968 may include a compact stereo vision sensor that may include two camera lenses (one on the left and one on the right) and an image processing chip that may measure the distance from the vehicle to the target object and use the generated information (e.g., metadata) to activate autonomous emergency braking and lane departure warning functions. Other types of stereo cameras 968 may be used in addition to or alternatively to those described herein.

[0105] A camera having a field of view of a portion of the environment including the sides of the vehicle 900 (e.g., a side view camera) can be used for surround viewing, providing information used to create and update the occupancy grid and generate side impact collision warnings. Fig. 9B The four surround cameras 974 shown in FIG. 9 can be placed on the vehicle 900. The surround cameras 974 can include a wide-angle camera 970, a fisheye camera, a 360-degree camera, and / or the like. For example, the four fisheye cameras can be placed in front, behind, and on the sides of the vehicle. In an alternative arrangement, the vehicle can use three surround cameras 974 (e.g., left, right, and rear), and can utilize one or more other cameras (e.g., a forward-facing camera) as a fourth surround camera.

[0106] A camera having a field of view that includes a portion of the environment behind the vehicle 900 (e.g., a rear view camera) can be used to assist with parking, surround view, rear collision warning, and creating and updating an occupancy grid. A variety of cameras can be used, including but not limited to cameras that are also suitable as front cameras as described herein (e.g., long-range and / or mid-range cameras 998, stereo cameras 968, infrared cameras 972, etc.).

[0107] A camera (e.g., one or more OMS sensors 901) having a view of the interior environment of each part of the cabin of the vehicle 900 can be used as a part of an occupant monitoring system (OMS), such as, but not limited to, a driver monitoring system (DMS). For example, an OMS sensor (e.g., OMS sensor 901) can be used to track the direction of sight, head posture, and / or blinking of an occupant and / or driver (e.g., by a controller 936). The gaze information can be used to determine the attention level of the occupant or driver (e.g., to detect drowsiness, fatigue, and / or distraction), and / or to take responsive actions to prevent harm to the occupant or operator. In some embodiments, data from the OMS sensor can be used to implement gaze-controlled operations triggered by a driver and / or non-driver occupant, such as, but not limited to, adjusting cabin temperature and / or airflow, opening and closing windows, controlling cabin lighting, controlling an entertainment system, adjusting rearview mirrors, adjusting seat positions, and / or other operations. In some embodiments, the OMS can be used for applications such as determining when an object and / or occupant is left in the cabin (e.g., by detecting the presence of an occupant after the driver leaves the vehicle).

[0108] Fig. 9C For use according to some embodiments of the present disclosure Fig.9A Block diagram of an example system architecture for an example autonomous vehicle 900. It should be understood that this arrangement and other arrangements described herein are set forth merely as examples. Other arrangements and elements (e.g., machines, interfaces, functions, sequences, functional groupings, etc.) may be used in addition to or in place of those shown, and some elements may be omitted entirely. Further, many of the elements described herein are functional entities that may be implemented as discrete or distributed components or in combination with other components, and in any appropriate combination and location. The various functions described herein as being performed by an entity may be implemented by hardware, firmware, and / or software. For example, the various functions may be implemented by a processor executing instructions stored in a memory.

[0109] Fig. 9C Each of the components, features, and systems of the vehicle 900 is illustrated as being connected via a bus 902. The bus 902 may include a controller area network (CAN) data interface (alternatively, referred to herein as a "CAN bus"). The CAN may be a network inside the vehicle 900 that assists in controlling various features and functions of the vehicle 900, such as the actuation of brakes, acceleration, braking, steering, windshield wipers, and the like. The CAN bus may be configured to have tens or even hundreds of nodes, each with its own unique identifier (e.g., a CAN ID). The CAN bus may be read to find steering wheel angle, ground speed, engine speed per minute (RPM), button position, and / or other vehicle status indicators. The CAN bus may be ASIL B compatible.

[0110] Although bus 902 is described as a CAN bus here, this is not intended to be limiting. For example, in addition to or alternatively to the CAN bus, FlexRay and / or Ethernet can be used. In addition, although bus 902 is represented by a single line, this is not intended to be limiting. For example, there can be any number of buses 902, which may include one or more CAN buses, one or more FlexRay buses, one or more Ethernet buses, and / or one or more other types of buses using different protocols. In some examples, two or more buses 902 can be used to perform different functions, and / or can be used for redundancy. For example, a first bus 902 can be used for a collision avoidance function, and a second bus 902 can be used for drive control. In any example, each bus 902 can communicate with any component of the vehicle 900, and two or more buses 902 can communicate with the same component. In some examples, each SoC 904, each controller 936, and / or each computer in the vehicle can have access to the same input data (e.g., input from a sensor of the vehicle 900), and can be connected to a common bus such as a CAN bus.

[0111] The vehicle 900 may include one or more controllers 936, such as those described herein. Fig.9A Those controllers described. Controller 936 can be used for a variety of functions. Controller 936 can be coupled to any other different components and systems of vehicle 900, and can be used for control of vehicle 900, artificial intelligence of vehicle 900, infotainment for vehicle 900, and / or the like.

[0112] The vehicle 900 may include one or more system on chip (SoC) 904. The SoC 904 may include a CPU 906, a GPU 908, a processor 910, a cache 912, an accelerator 914, a data store 916, and / or other components and features not shown. The SoC 904 may be used to control the vehicle 900 in a variety of platforms and systems. For example, one or more SoCs 904 may be combined with an HD map 922 in a system (e.g., a system of the vehicle 900), and the HD map may be downloaded from one or more servers (e.g., a server) via a network interface 924. Fig.9D one or more servers 978) to obtain map refreshes and / or updates.

[0113] The CPU 906 may include a CPU cluster or CPU complex (alternatively, referred to herein as a "CCPLEX"). The CPU 906 may include multiple cores and / or L2 caches. For example, in some embodiments, the CPU 906 may include eight cores in a coherent multiprocessor configuration. In some embodiments, the CPU 906 may include four dual-core clusters, each of which has a dedicated L2 cache (e.g., a 2MB L2 cache). The CPU 906 (e.g., CCPLEX) may be configured to support simultaneous cluster operations, such that any combination of CPU 906 clusters can be active at any given time.

[0114] The CPU 906 may implement power management capabilities including one or more of the following features: each hardware block may be automatically clock gated when idle to save dynamic power; each core clock may be gated when the core is not actively executing instructions due to the execution of WFI / WFE instructions; each core may be independently power gated; each core cluster may be independently clock gated when all cores are clock gated or power gated; and / or each core cluster may be independently power gated when all cores are power gated. The CPU 906 may further implement an enhanced algorithm for managing power states, in which allowed power states and expected wake-up times are specified, and hardware / microcode determines the optimal power state to enter for the core, cluster, and CCPLEX. The processing core may support a simplified power state entry sequence in software, with the work being offloaded to the microcode.

[0115] The GPU 908 may include an integrated GPU (alternatively, referred to herein as an "iGPU"). The GPU 908 may be programmable and efficient for parallel workloads. In some examples, the GPU 908 may use an enhanced tensor instruction set. The GPU 908 may include one or more streaming microprocessors, each of which may include an L1 cache (e.g., an L1 cache with at least 96KB storage capacity), and two or more of these streaming microprocessors may share an L2 cache (e.g., an L2 cache with 512KB storage capacity). In some embodiments, the GPU 908 may include at least eight streaming microprocessors. The GPU 908 may use a computing application programming interface (API). In addition, the GPU 908 may use one or more parallel computing platforms and / or programming models (e.g., NVIDIA's CUDA).

[0116] In the case of automotive and embedded use, GPU 908 can be power optimized to achieve optimal performance. For example, GPU 908 can be manufactured on fin field effect transistors (FinFETs). However, this is not intended to be limiting, and GPU 908 can be manufactured using other semiconductor manufacturing processes. Each streaming microprocessor can merge several mixed precision processing cores divided into multiple blocks. For example and without limitation, 64 PF32 cores and 32 PF64 cores can be divided into four processing blocks. In such an example, each processing block can be allocated 16 FP32 cores, 8 FP64 cores, 16 INT32 cores, two mixed precision NVIDIA tensor cores for deep learning matrix arithmetic, L0 instruction cache, thread beam (warp) scheduler, dispatch unit and / or 64KB register file. In addition, the streaming microprocessor can include independent parallel integer and floating point data paths to provide efficient execution of workloads using a mix of calculations and addressing calculations. The streaming microprocessor may include independent thread scheduling capabilities to allow for finer-grained synchronization and collaboration between parallel threads. A streaming microprocessor may include a combined L1 data cache and shared memory unit to increase performance while simplifying programming.

[0117] GPU 908 may include high bandwidth memory (HBM) and / or a 16GB HBM2 memory subsystem that provides a peak memory bandwidth of approximately 900 GB / s in some examples. In some examples, synchronous graphics random access memory (SGRAM), such as fifth generation graphics double data rate synchronous random access memory (GDDR5), may be used in addition to or in lieu of HBM memory.

[0118] The GPU 908 may include unified memory technology that includes access counters to allow memory pages to be more accurately migrated to the processor that accesses them most frequently, thereby improving the efficiency of memory ranges shared between processors. In some examples, address translation service (ATS) support may be used to allow the GPU 908 to directly access the CPU 906 page table. In such an example, when the GPU 908 memory management unit (MMU) experiences a miss, an address translation request may be transmitted to the CPU 906. In response, the CPU 906 may look up the virtual-physical mapping for the address in its page table and transmit the translation back to the GPU 908. In this way, unified memory technology may allow a single unified virtual address space to be used for memory of both the CPU 906 and the GPU 908, thereby simplifying GPU 908 programming and porting applications to the GPU 908.

[0119] In addition, GPU 908 may include access counters that can track how often GPU 908 accesses the memory of other processors. The access counters can help ensure that memory pages are moved to the physical memory of the processor that accesses them most frequently.

[0120] SoC 904 may include any number of caches 912, including those described herein. For example, cache 912 may include an L3 cache available to both CPU 906 and GPU 908 (e.g., connected to both CPU 906 and GPU 908). Cache 912 may include a write-back cache that may track the state of a line, for example, by using a cache coherence protocol (e.g., MEI, MESI, MSI, etc.). Depending on the embodiment, the L3 cache may include 4MB or more, although smaller cache sizes may also be used.

[0121] The SoC 904 may include an arithmetic logic unit (ALU) that may be used to perform processing for any of a variety of tasks or operations with respect to the vehicle 900 - such as processing a DNN. In addition, the SoC 904 may include a floating point unit (FPU) - or other math coprocessor or digital coprocessor type - for performing mathematical operations within the system. For example, the SoC 904 may include one or more FPUs integrated as execution units within the CPU 906 and / or GPU 908.

[0122] SoC 904 may include one or more accelerators 914 (e.g., hardware accelerators, software accelerators, or a combination thereof). For example, SoC 904 may include a hardware acceleration cluster, which may include optimized hardware accelerators and / or large on-chip memory. The large on-chip memory (e.g., 4MB SRAM) may enable the hardware acceleration cluster to accelerate neural networks and other calculations. The hardware acceleration cluster may be used to supplement GPU 908 and offload some tasks of GPU 908 (e.g., free up more cycles of GPU 908 for performing other tasks). As an example, accelerator 914 may be used for targeted workloads (e.g., perception, convolutional neural networks (CNNs), etc.) that are sufficiently stable to be easily controlled for acceleration. When used herein, the term "CNN" may include all types of CNNs, including region-based or regional convolutional neural networks (RCNNs) and fast RCNNs (e.g., for object detection).

[0123] Accelerator 914 (e.g., hardware acceleration cluster) may include a deep learning accelerator (DLA). DLA may include one or more tensor processing units (TPUs) that may be configured to provide an additional 10 trillion operations per second for deep learning applications and reasoning. TPU may be an accelerator configured to perform image processing functions (e.g., for CNN, RCNN, etc.) and optimized for performing image processing functions. DLA may be further optimized for a specific set of neural network types and floating point operations and reasoning. The design of DLA may provide higher performance per millimeter than a general-purpose GPU, and far exceeds the performance of a CPU. TPU may perform several functions, including a single instance convolution function, support, for example, INT8, INT16, and FP16 data types for both features and weights, and post-processor functions.

[0124] The DLA can quickly and efficiently execute neural networks, particularly CNNs, on processed or unprocessed data for any of a wide variety of functions, such as, but not limited to: a CNN for object recognition and detection using data from a camera sensor; a CNN for distance estimation using data from a camera sensor; a CNN for emergency vehicle detection and identification and detection using data from a microphone; a CNN for facial recognition and vehicle owner identification using data from a camera sensor; and / or a CNN for safety and / or security-related events.

[0125] The DLA can perform any function of the GPU 908, and by using an inference accelerator, for example, the designer can target any function to either the DLA or the GPU 908. For example, the designer can focus the processing of CNNs and floating point operations on the DLA, and leave other functions to the GPU 908 and / or other accelerators 914.

[0126] The accelerator 914 (e.g., a hardware acceleration cluster) may include a programmable vision accelerator (PVA), which may be alternatively referred to herein as a computer vision accelerator. The PVA may be designed and configured to accelerate computer vision algorithms for advanced driver assistance systems (ADAS), autonomous driving, and / or augmented reality (AR) and / or virtual reality (VR) applications. The PVA may provide a balance between performance and flexibility. For example, each PVA may include, for example and without limitation, any number of reduced instruction set computer (RISC) cores, direct memory access (DMA), and / or any number of vector processors.

[0127] The RISC core can interact with an image sensor (e.g., an image sensor of any camera described herein), an image signal processor, and / or the like. Each of these RISC cores can include any number of memories. Depending on the embodiment, the RISC core can use any of a number of protocols. In some examples, the RISC core can execute a real-time operating system (RTOS). The RISC core can be implemented using one or more integrated circuit devices, application specific integrated circuits (ASICs), and / or storage devices. For example, the RISC core can include an instruction cache and / or a tightly coupled RAM.

[0128] The DMA may enable components of the PVA to access system memory independently of the CPU 906. The DMA may support any number of features used to provide optimizations for the PVA, including, but not limited to, support for multi-dimensional addressing and / or circular addressing. In some examples, the DMA may support addressing in up to six or more dimensions, which may include block width, block height, block depth, horizontal block stepping, vertical block stepping, and / or depth stepping.

[0129] The vector processor can be a programmable processor that can be designed to efficiently and flexibly perform programming for computer vision algorithms and provide signal processing capabilities. In some examples, the PVA can include a PVA core and two vector processing subsystem partitions. The PVA core can include a processor subsystem, one or more DMA engines (e.g., two DMA engines), and / or other peripherals. The vector processing subsystem can operate as the main processing engine of the PVA, and can include a vector processing unit (VPU), an instruction cache, and / or a vector memory (e.g., VMEM). The VPU core can include a digital signal processor, such as, for example, a single instruction multiple data (SIMD), a very long instruction word (VLIW) digital signal processor. The combination of SIMD and VLIW can enhance throughput and rate.

[0130] Each of the vector processors may include an instruction cache and may be coupled to a dedicated memory. As a result, in some examples, each of the vector processors may be configured to execute independently of the other vector processors. In other examples, the vector processors included in a particular PVA may be configured to employ data parallelism. For example, in some embodiments, multiple vector processors included in a single PVA may execute the same computer vision algorithm, but on different regions of an image. In other examples, the vector processors included in a particular PVA may execute different computer vision algorithms simultaneously on the same image, or even execute different algorithms on sequence images or portions of an image. Among other things, any number of PVAs may be included in a hardware acceleration cluster, and any number of vector processors may be included in each of these PVAs. In addition, the PVA may include additional error correction code (ECC) memory to enhance overall system security.

[0131] The accelerator 914 (e.g., a hardware acceleration cluster) may include an on-chip computer vision network and SRAM to provide high bandwidth, low latency SRAM for the accelerator 914. In some examples, the on-chip memory may include at least 4MB of SRAM consisting of, for example and not limited to, eight field-configurable memory blocks that can be accessed by both the PVA and the DLA. Each pair of memory blocks may include an advanced peripheral bus (APB) interface, a configuration circuit system, a controller, and a multiplexer. Any type of memory may be used. The PVA and DLA may access the memory via a backbone that provides high-speed memory access to the PVA and DLA. The backbone may include an on-chip computer vision network that interconnects the PVA and DLA to the memory (e.g., using APB).

[0132] 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. Such an interface may provide separate phases and separate channels for transmitting control signals / addresses / data, as well as burst communication for continuous data transmission. This type of interface may comply with ISO 26262 or IEC 61508 standards, but other standards and protocols may also be used.

[0133] In some examples, SoC 904 may include a real-time ray tracing hardware accelerator such as described in U.S. Patent Application No. 16 / 101,232 filed on August 10, 2018. The real-time ray tracing hardware accelerator may be used to quickly and efficiently determine the position and range of objects (e.g., within a world model) to generate real-time visualization simulations for RADAR signal interpretation, for sound propagation synthesis and / or analysis, for SONAR system simulations, for general wave propagation simulations, for comparison with LIDAR data for the purpose of positioning and / or other functions, and / or for other purposes. In some embodiments, one or more tree traversal units (TTUs) may be used to perform one or more ray tracing related operations.

[0134] The accelerator 914 (e.g., a hardware accelerator cluster) has a wide range of uses in autonomous driving. The PVA can be a programmable visual accelerator that can be used in key processing stages in ADAS and autonomous vehicles. The capabilities of the PVA are a good match for algorithmic domains that require predictable processing, low power, and low latency. In other words, the PVA performs well on semi-intensive or intensive rule computations, and even on small data sets that require predictable runtimes with low latency and low power. Therefore, in the context of a platform for autonomous vehicles, the PVA is designed to run classic computer vision algorithms because they are efficient at object detection and integer math.

[0135] For example, according to one embodiment of the technology, PVA is used to perform computer stereo vision. In some examples, algorithms based on semi-global matching can be used, but this is not intended to be limiting. Many applications for level 3-5 autonomous driving require instant motion estimation / stereo matching (e.g., structure from motion, pedestrian recognition, lane detection, etc.). PVA can perform computer stereo vision functions on input from two monocular cameras.

[0136] In some examples, PVA can be used to perform dense optical flow. According to the process raw RADAR data (e.g., using 4D fast Fourier transform) to provide processed RADAR. In other examples, PVA is used for time-of-flight depth processing, which is for example by processing raw time-of-flight data to provide processed time-of-flight data.

[0137] DLA can be used to run any type of network to enhance control and driving safety, including, for example, a neural network that outputs a confidence measure for each object detection. Such a confidence value can be interpreted as a probability, or as providing a relative "weight" of each detection compared to other detections. This confidence value enables the system to make further decisions about which detections should be considered true positive detections rather than false positive detections. For example, the system can set a threshold for confidence and only consider detections that exceed the threshold as true positive detections. In an automatic emergency braking (AEB) system, a false positive detection will cause the vehicle to automatically perform emergency braking, which is obviously undesirable. Therefore, only the most confident detection should be considered a trigger for AEB. DLA can run a neural network for regressing confidence values. The neural network can take at least some subset of parameters as its input, such as bounding box dimensions, ground plane estimates obtained (e.g., from another subsystem), inertial measurement unit (IMU) sensor 966 output related to vehicle 900 orientation and distance, 3D position estimates of objects obtained from neural networks and / or other sensors (e.g., LIDAR sensor 964 or RADAR sensor 960), etc.

[0138] SoC 904 may include one or more data stores 916 (e.g., memory). Data store 916 may be on-chip memory of SoC 904 that may store neural networks to be executed on the GPU and / or DLA. In some examples, data store 916 may be large enough to store multiple instances of the neural network for redundancy and safety. Data store 916 may include L2 or L3 cache 912. References to data store 916 may include references to memory associated with PVA, DLA, and / or other accelerators 914 as described herein.

[0139] SoC 904 may include one or more processors 910 (e.g., embedded processors). Processor 910 may include a boot and power management processor, which may be a dedicated processor and subsystem for handling boot power and management functions and related safety implementations. The boot and power management processor may be part of the SoC 904 boot sequence and may provide runtime power management services. The boot power and management processor may provide clock and voltage programming, auxiliary system low power state transitions, SoC 904 thermal and temperature sensor management, and / or SoC 904 power state management. Each temperature sensor may be implemented as a ring oscillator whose output frequency is proportional to the temperature, and SoC 904 may use the ring oscillator to detect the temperature of CPU 906, GPU 908, and / or accelerator 914. If it is determined that the temperature exceeds a threshold, the boot and power management processor may enter a temperature fault routine and place SoC 904 in a lower power state and / or place the vehicle 900 in a driver safety parking mode (e.g., parking the vehicle 900 safely).

[0140] The processor 910 may further include a set of embedded processors that may be used as an audio processing engine. The audio processing engine may be an audio subsystem that allows for full hardware support for multi-channel audio through multiple interfaces and a wide range of flexible audio I / O interfaces. In some examples, the audio processing engine is a dedicated processor core having a digital signal processor with dedicated RAM.

[0141] The processor 910 may further include an always-on processor engine that may provide the necessary hardware features to support low-power sensor management and wake-up use cases. The always-on processor engine may include a processor core, tightly coupled RAM, supporting peripherals (e.g., timers and interrupt controllers), various I / O controller peripherals, and routing logic.

[0142] The processor 910 may further include a safety cluster engine, which includes a dedicated processor subsystem that handles safety management of automotive applications. The safety cluster engine may include two or more processor cores, tightly coupled RAM, supporting peripherals (e.g., timers, interrupt controllers, etc.), and / or routing logic. In safety mode, the two or more cores may operate in lockstep mode and act as a single core with comparison logic to detect any differences between their operations.

[0143] Processor 910 may further include a real-time camera engine, which may include a dedicated processor subsystem for handling real-time camera management.

[0144] Processor 910 may further include a high dynamic range signal processor, which may include an image signal processor, which is a hardware engine that is part of the camera processing pipeline.

[0145] The processor 910 may include a video image compositer, which may be a processing block (e.g., implemented on a microprocessor) that implements video post-processing functions required for a video playback application to produce a final image for a player window. The video image compositer may perform lens distortion correction for the wide-angle camera 970, the surround camera 974, and / or for an in-cab surveillance camera sensor. The in-cab surveillance camera sensor is preferably monitored by a neural network running on another instance of the advanced SoC, configured to recognize in-cab events and respond accordingly. The in-cab system may perform lip reading to activate mobile phone service and place calls, dictate emails, change vehicle destinations, activate or change the vehicle's infotainment system and settings, or provide voice-activated web surfing. Certain functions are only available to the driver when the vehicle is operating in autonomous mode and are disabled in other circumstances.

[0146] The video image compositer may include enhanced temporal noise reduction for both spatial and temporal noise reduction. For example, in the case of motion in the video, the noise reduction appropriately weights the spatial information and reduces the weight of information provided by adjacent frames. In the case where an image or portion of an image does not include motion, the temporal noise reduction performed by the video image compositer may use information from previous images to reduce noise in the current image.

[0147] The video image compositor may also be configured to perform stereoscopic rectification on the input stereoscopic footage frames. The video image compositor may further be used for user interface composition when the operating system desktop is in use and the GPU 908 does not need to continuously render new surfaces. Even when the GPU 908 is powered on and active for 3D rendering, the video image compositor may be used to offload the GPU 908 to improve performance and responsiveness.

[0148] The SoC 904 may further include a mobile industry processor interface (MIPI) camera serial interface for receiving video and input from a camera, a high-speed interface, and / or a video input block that may be used for camera and related pixel input functions. The SoC 904 may further include an input / output controller that may be controlled by software and may be used to receive I / O signals that are not committed to a specific role.

[0149] SoC 904 may further include a wide range of peripheral interfaces to enable communication with peripherals, audio codecs, power management and / or other devices. SoC 904 may be used to process data from cameras (connected via Gigabit multimedia serial links and Ethernet), sensors (e.g., LIDAR sensor 964, RADAR sensor 960, etc., which may be connected via Ethernet), data from bus 902 (e.g., speed of vehicle 900, steering wheel position, etc.), data from GNSS sensor 958 (connected via Ethernet or CAN bus). SoC 904 may further include dedicated high-performance mass storage controllers, which may include their own DMA engines, and which may be used to release CPU 906 from routine data management tasks.

[0150] SoC 904 can be an end-to-end platform with a flexible architecture that spans automation levels 3-5, thereby providing a comprehensive functional safety architecture that utilizes and efficiently uses computer vision and ADAS technologies to achieve diversity and redundancy, together with deep learning tools to provide a platform for a flexible and reliable driving software stack. SoC 904 can be faster, more reliable, and even more energy efficient and space efficient than conventional systems. For example, when combined with CPU 906, GPU 908, and data storage 916, accelerator 914 can provide a fast and efficient platform for level 3-5 autonomous vehicles.

[0151] The technology thus provides capabilities and functionality that cannot be achieved by conventional systems. For example, computer vision algorithms can be executed on CPUs, which can be configured using high-level programming languages ​​such as the C programming language to execute a wide variety of processing algorithms across a wide variety of visual data. However, CPUs often fail to meet the performance requirements of many computer vision applications, such as those related to, for example, execution time and power consumption. In particular, many CPUs are unable to execute complex object detection algorithms in real time, which is a requirement for in-vehicle ADAS applications and a requirement for practical Level 3-5 autonomous vehicles.

[0152] In contrast to conventional systems, by providing a CPU complex, a GPU complex, and a hardware acceleration cluster, the techniques described herein allow multiple neural networks to be executed simultaneously and / or sequentially, and the results to be combined together to achieve Level 3-5 autonomous driving functions. For example, a CNN executed on a DLA or dGPU (e.g., GPU 920) may include text and word recognition, allowing the supercomputer to read and understand traffic signs, including signs for which a neural network has not been specifically trained. The DLA may further include a neural network capable of recognizing, interpreting, and providing semantic understanding of the signs, and passing that semantic understanding to a path planning module running on the CPU complex.

[0153] As another example, as required for Level 3, 4, or 5 driving, multiple neural networks may be running simultaneously. For example, a warning sign consisting of "Caution: Flashing Lights Indicate Icing Conditions" along with electric lights may be interpreted by several neural networks independently or collectively. The sign itself may be recognized as a traffic sign by a deployed first neural network (e.g., a trained neural network), and the text "Flashing Lights Indicate Icing Conditions" may be interpreted by a deployed second neural network that informs the vehicle's path planning software (preferably executing on a CPU complex) that icing conditions exist when the flashing lights are detected. The flashing lights may be recognized by operating a deployed third neural network over multiple frames that informs the vehicle's path planning software of the presence (or absence) of the flashing lights. All three neural networks may be running simultaneously, for example, within the DLA and / or on the GPU 908.

[0154] In some examples, a CNN for facial recognition and owner recognition can use data from the camera sensor to identify the presence of an authorized driver and / or owner of the vehicle 900. The always-on sensor processing engine can be used to unlock the vehicle and turn on the lights when the owner approaches the driver's door, and in security mode, disable the vehicle when the owner leaves the vehicle. In this way, the SoC 904 provides security against theft and / or carjacking.

[0155] In another example, a CNN for emergency vehicle detection and identification can use data from microphone 996 to detect and identify emergency vehicle sirens. In contrast to conventional systems that use general classifiers to detect sirens and manually extract features, SoC 904 uses CNN to classify environmental and urban sounds and to classify visual data. In a preferred embodiment, the CNN running on the DLA is trained to identify the relative closing rate of emergency vehicles (e.g., by using the Doppler effect). The CNN can also be trained to identify emergency vehicles specific to the local area in which the vehicle is operating, as identified by the GNSS sensor 958. Thus, for example, when operating in Europe, the CNN will seek to detect European sirens, and when in the United States, the CNN will seek to identify only North American sirens. Once an emergency vehicle is detected, with the assistance of the ultrasonic sensor 962, the control program can be used to execute emergency vehicle safety routines to slow the vehicle, drive to the side of the road, stop the vehicle, and / or idle the vehicle until the emergency vehicle passes.

[0156] The vehicle may include a CPU 918 (e.g., a discrete CPU or dCPU) that may be coupled to the SoC 904 via a high-speed interconnect (e.g., PCIe). The CPU 918 may include, for example, an X86 processor. The CPU 918 may be used to perform any of a variety of functions, including, for example, arbitrating potentially inconsistent results between ADAS sensors and the SoC 904, and / or monitoring the status and health of the controller 936 and / or the infotainment SoC 930.

[0157] The vehicle 900 may include a GPU 920 (e.g., a discrete GPU or dGPU) that may be coupled to the SoC 904 via a high-speed interconnect (e.g., NVIDIA's NVLINK). The GPU 920 may provide additional artificial intelligence functionality, for example, by executing redundant and / or different neural networks, and may be used to train and / or update the neural network based on input from sensors of the vehicle 900 (e.g., sensor data).

[0158] The vehicle 900 may further include a network interface 924, which may include one or more wireless antennas 926 (e.g., one or more wireless antennas for different communication protocols, such as cellular antennas, Bluetooth antennas, etc.). The network interface 924 can be used to enable wireless connection with the cloud (e.g., with a server 978 and / or other network devices), with other vehicles, and / or with a computing device (e.g., a passenger's client device) via the Internet. In order to communicate with other vehicles, a direct link can be established between the two vehicles, and / or an indirect link can be established (e.g., across a network and through the Internet). The direct link can be provided using a vehicle-to-vehicle communication link. The vehicle-to-vehicle communication link can provide the vehicle 900 with information about vehicles approaching the vehicle 900 (e.g., vehicles in front of, to the side of, and / or behind the vehicle 900). This functionality can be part of the collaborative adaptive cruise control functionality of the vehicle 900.

[0159] The network interface 924 may include a SoC that provides modulation and demodulation functions and enables the controller 936 to communicate via a wireless network. The network interface 924 may include a radio frequency front end for up-conversion from baseband to radio frequency and down-conversion from radio frequency to baseband. Frequency conversion may be performed by a known process, and / or may be performed using a super-heterodyne process. In some examples, the radio frequency front end function may be provided by a separate chip. The network interface may include a wireless function for communicating via LTE, WCDMA, UMTS, GSM, CDMA2000, Bluetooth, Bluetooth LE, Wi-Fi, Z-wave, ZigBee, LoRaWAN, and / or other wireless protocols.

[0160] The vehicle 900 may further include data storage 928, which may include off-chip storage (e.g., outside the SoC 904). The data storage 928 may include one or more storage elements, including RAM, SRAM, DRAM, VRAM, flash memory, hard disk, and / or other components and / or devices that can store at least one bit of data.

[0161] The vehicle 900 may further include a GNSS sensor 958. The GNSS sensor 958 (e.g., GPS, assisted GPS sensor, differential GPS (DGPS) sensor, etc.) is used to assist in mapping, perception, occupancy grid generation, and / or path planning functions. Any number of GNSS sensors 958 may be used, including, for example and without limitation, GPS using a USB connector with an Ethernet to serial (RS-232) bridge.

[0162] The vehicle 900 may further include a RADAR sensor 960. The RADAR sensor 960 may be used by the vehicle 900 for remote vehicle detection even in darkness and / or inclement weather conditions. The RADAR functional safety level may be ASIL B. The RADAR sensor 960 may use CAN and / or bus 902 (e.g., to transmit data generated by the RADAR sensor 960) for control and access to object tracking data, accessing Ethernet in some examples to access raw data. A variety of RADAR sensor types may be used. For example and without limitation, the RADAR sensor 960 may be suitable for front, rear, and side RADAR use. In some examples, a pulse Doppler RADAR sensor is used.

[0163] The RADAR sensor 960 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, and the like. In some examples, the long-range RADAR may be used for adaptive cruise control functions. The long-range RADAR system may provide a wide field of view (e.g., within a range of 250m) achieved by two or more independent scans. The RADAR sensor 960 may help distinguish between static objects and moving objects, and may be used by the ADAS system for emergency braking assistance and forward collision warnings. The long-range RADAR sensor may include a single-station multimode RADAR with multiple (e.g., six or more) fixed RADAR antennas and high-speed CAN and FlexRay interfaces. In an example with six antennas, the central four antennas may create a focused beam pattern designed to record the surroundings of the vehicle 900 at a higher rate with minimal traffic interference from adjacent lanes. The other two antennas may expand the field of view, making it possible to quickly detect vehicles entering or leaving the lane of the vehicle 900.

[0164] As an example, a medium-range RADAR system may include a range of up to 960m (front) or 80m (rear) and a field of view of up to 42 degrees (front) or 950 degrees (rear). A short-range RADAR system may include, but is not limited to, a RADAR sensor designed to be mounted on both ends of a rear bumper. When mounted on both ends of a rear bumper, such a RADAR sensor system may create two beams that continuously monitor the blind spots behind and beside the vehicle.

[0165] Short-range RADAR systems can be used in ADAS systems for blind spot detection and / or lane change assistance.

[0166] The vehicle 900 may further include an ultrasonic sensor 962. The ultrasonic sensor 962, which may be placed on the front, rear, and / or sides of the vehicle 900, may be used for parking assistance and / or creating and updating an occupancy grid. A variety of ultrasonic sensors 962 may be used, and different ultrasonic sensors 962 may be used for different detection ranges (e.g., 2.5 m, 4 m). The ultrasonic sensor 962 may operate at a functional safety level of ASIL B.

[0167] The vehicle 900 may include a LIDAR sensor 964. The LIDAR sensor 964 may be used for object and pedestrian detection, emergency braking, collision avoidance, and / or other functions. The LIDAR sensor 964 may be ASIL B for functional safety level. In some examples, the vehicle 900 may include multiple LIDAR sensors 964 (e.g., two, four, six, etc.) that may use Ethernet (e.g., to provide data to a Gigabit Ethernet switch).

[0168] In some examples, the LIDAR sensor 964 may be able to provide a list of objects and their distances for a 360-degree field of view. Commercially available LIDAR sensors 964 may have, for example, an advertised range of approximately 900m, an accuracy of 2cm-3cm, and support for 900Mbps Ethernet connections. In some examples, one or more non-protruding LIDAR sensors 964 may be used. In such examples, the LIDAR sensor 964 may be implemented as a small device that can be embedded in the front, back, side, and / or corner of the vehicle 900. In such examples, the LIDAR sensor 964 may provide a field of view of up to 120 degrees horizontally and 35 degrees vertically, with a range of 200m, even for low reflectivity objects. The front-mounted LIDAR sensor 964 may be configured for a horizontal field of view between 45 and 135 degrees.

[0169] In some examples, LIDAR technologies such as 3D flash LIDAR may also be used. 3D flash LIDAR uses flashes of laser as an emission source to illuminate the vehicle's surroundings up to about 200m. The flash LIDAR unit includes a receiver that records the laser pulse transmission time and reflected light on each pixel, which in turn corresponds to the range from the vehicle to the object. Flash LIDAR can allow highly accurate and distortion-free images of the surrounding environment to be generated with each laser flash. In some examples, four flash LIDAR sensors may be deployed, one on each side of the vehicle 900. Available 3D flash LIDAR systems include solid-state 3D staring array LIDAR cameras (e.g., non-scanning LIDAR devices) with no moving parts other than fans. The flash LIDAR device can use 5 nanosecond Class I (eye-safe) laser pulses per frame, and can capture the reflected laser light in the form of a 3D range point cloud and co-registered intensity data. By using flash LIDAR, and because flash LIDAR is a solid-state device with no moving parts, LIDAR sensor 964 may be less susceptible to motion blur, vibration, and / or shock.

[0170] The vehicle may further include an IMU sensor 966. In some examples, the IMU sensor 966 may be located at the center of the rear axle of the vehicle 900. The IMU sensor 966 may include, for example and without limitation, an accelerometer, a magnetometer, a gyroscope, a magnetic compass, and / or other sensor types. In some examples, for example, in a six-axis application, the IMU sensor 966 may include an accelerometer and a gyroscope, and in a nine-axis application, the IMU sensor 966 may include an accelerometer, a gyroscope, and a magnetometer.

[0171] In some embodiments, the IMU sensor 966 can be implemented as a miniature high-performance GPS-assisted inertial navigation system (GPS / INS) that combines a micro-electromechanical system (MEMS) inertial sensor, a high-sensitivity GPS receiver, and an advanced Kalman filter algorithm to provide estimates of position, velocity, and attitude. Thus, in some examples, the IMU sensor 966 can enable the vehicle 900 to estimate heading by directly observing and correlating velocity changes from the GPS to the IMU sensor 966 without the need for input from a magnetic sensor. In some examples, the IMU sensor 966 and the GNSS sensor 958 can be combined into a single integrated unit.

[0172] The vehicle may include a microphone 996 positioned in and / or around the vehicle 900. The microphone 996 may be used for, among other things, emergency vehicle detection and identification.

[0173] The vehicle may further include any number of camera types, including a stereo camera 968, a wide angle camera 970, an infrared camera 972, a surround camera 974, a long-range and / or mid-range camera 998, and / or other camera types. These cameras may be used to capture image data around the entire periphery of the vehicle 900. The type of camera used depends on the embodiment and the requirements of the vehicle 900, and any combination of camera types may be used to provide the necessary coverage around the vehicle 900. In addition, the number of cameras may vary depending on the embodiment. For example, the vehicle may include six cameras, seven cameras, ten cameras, twelve cameras, and / or another number of cameras. As an example and not limitation, the cameras may support Gigabit Multimedia Serial Link (GMSL) and / or Gigabit Ethernet. Each of the cameras described herein may include a 10GbE ... Fig.9A and Fig. 9B Described in more detail.

[0174] The vehicle 900 may further include a vibration sensor 942. The vibration sensor 942 may measure vibrations of components of the vehicle, such as axles. For example, changes in vibration may indicate changes in the road surface. In another example, when two or more vibration sensors 942 are used, the difference between the vibrations may be used to determine friction or slip of the road surface (e.g., when there is a vibration difference between a powered drive shaft and a freely rotating shaft).

[0175] The vehicle 900 may include an ADAS system 938. In some examples, the ADAS system 938 may include a SoC. The ADAS system 938 may include autonomous / adaptive / automatic cruise control (ACC), cooperative adaptive cruise control (CACC), forward collision warning (FCW), automatic emergency braking (AEB), lane departure warning (LDW), lane keeping assist (LKA), blind spot warning (BSW), rear cross traffic warning (RCTW), collision warning system (CWS), lane centering (LC), and / or other features and functions.

[0176] The ACC system may use a RADAR sensor 960, a LIDAR sensor 964, and / or a camera. The ACC system may include a longitudinal ACC and / or a lateral ACC. The longitudinal ACC monitors and controls the distance to the vehicle immediately in front of the vehicle 900, and automatically adjusts the vehicle speed to maintain a safe distance from the vehicle in front. The lateral ACC performs distance keeping and suggests that the vehicle 900 change lanes when necessary. The lateral ACC is related to other ADAS applications such as LCA and CWS.

[0177] CACC uses information from other vehicles, which can be received indirectly from other vehicles via a wireless link or through a network connection (e.g., through the Internet) via a network interface 924 and / or a wireless antenna 926. A direct link can be provided by a vehicle-to-vehicle (V2V) communication link, while an indirect link can be an infrastructure-to-vehicle (I2V) communication link. Typically, the V2V communication concept provides information about the vehicle immediately ahead (e.g., the vehicle immediately ahead of the vehicle 900 and in the same lane as it), while the I2V communication concept provides information about traffic farther ahead. The CACC system may include either or both of the I2V and V2V information sources. Given information about the vehicle ahead of the vehicle 900, CACC can be more reliable, and it is possible to improve the smoothness of traffic flow and reduce road congestion.

[0178] The FCW system is designed to alert the driver to hazards so that the driver can take corrective action. The FCW system uses a front camera and / or RADAR sensor 960 coupled to a dedicated processor, DSP, FPGA and / or ASIC, which is electrically coupled to driver feedback such as a display, speaker and / or vibrating components. The FCW system can provide warnings in the form of, for example, sound, visual warnings, vibrations and / or rapid brake pulses.

[0179] The AEB system detects an impending front collision with another vehicle or other object and can automatically apply the brakes if the driver does not take corrective action within specified time or distance parameters. The AEB system can use a front camera and / or RADAR sensor 960 coupled to a dedicated processor, DSP, FPGA and / or ASIC. When the AEB system detects a hazard, it typically first alerts the driver to take corrective action to avoid the collision, and if the driver does not take corrective action, the AEB system can automatically apply the brakes in an effort to prevent or at least mitigate the effects of the predicted collision. The AEB system may include technologies such as dynamic brake support and / or collision approach braking.

[0180] The LDW system provides visual, audible, and / or tactile warnings, such as steering wheel or seat vibrations, to alert the driver when the vehicle 900 crosses a lane marking. When the driver indicates an intention to leave the lane, by activating a turn signal, the LDW system is not activated. The LDW system may use a front-facing camera coupled to a dedicated processor, DSP, FPGA, and / or ASIC that is electrically coupled to driver feedback such as a display, speaker, and / or vibrating component.

[0181] The LKA system is a variation of the LDW system. If the vehicle 900 begins to leave the lane, the LKA system provides steering input or braking to correct the vehicle 900.

[0182] The BSW system detects and warns the driver of vehicles in the car's blind spot. The BSW system can provide visual, auditory and / or tactile alerts to indicate that merging or changing lanes is unsafe. The system can provide additional warnings when the driver uses a turn signal. The BSW system can use a rear-facing camera and / or RADAR sensor 960 coupled to a dedicated processor, DSP, FPGA and / or ASIC, which is electrically coupled to driver feedback such as a display, speaker and / or vibration components.

[0183] The RCTW system can provide visual, audible, and / or tactile notifications when an object is detected outside the range of the rear camera while the vehicle 900 is in reverse. Some RCTW systems include AEB to ensure that the vehicle brakes are applied to avoid a crash. The RCTW system can use one or more rear RADAR sensors 960 coupled to a dedicated processor, DSP, FPGA, and / or ASIC that is electrically coupled to driver feedback such as a display, speaker, and / or vibrating component.

[0184] Conventional ADAS systems may be prone to false positive results, which may annoy and distract the driver, but are typically not catastrophic because the ADAS system alerts the driver and allows the driver to decide whether the safety condition really exists and take action accordingly. However, in the autonomous vehicle 900, in the case of conflicting results, the vehicle 900 itself must decide whether to pay attention to the results from the main computer or the auxiliary computer (e.g., the first controller 936 or the second controller 936). For example, in some embodiments, the ADAS system 938 can be a backup and / or auxiliary computer for providing perception information to the backup computer rationality module. The backup computer rationality monitor can run redundant and diverse software on hardware components to detect faults in perception and dynamic driving tasks. The output from the ADAS system 938 can be provided to the supervisory MCU. If the outputs from the main computer and the auxiliary computer conflict, the supervisory MCU must determine how to coordinate the conflict to ensure safe operation.

[0185] In some examples, the master computer can be configured to provide a confidence score to the supervisory MCU, indicating the master computer's confidence in the selected result. If the confidence score exceeds a threshold, the supervisory MCU can follow the direction of the master computer, regardless of whether the auxiliary computer provides conflicting or inconsistent results. In the case where the confidence score does not meet the threshold and the master computer and the auxiliary computer indicate different results (e.g., conflicts), the supervisory MCU can arbitrate between these computers to determine the appropriate result.

[0186] The supervisory MCU can be configured to run a neural network that is trained and configured to determine conditions under which the auxiliary computer provides a false alarm based on outputs from the main computer and the auxiliary computer. Therefore, the neural network in the supervisory MCU can learn when the output of the auxiliary computer can be trusted and when it cannot. For example, when the auxiliary computer is a RADAR-based FCW system, the neural network in the supervisory MCU can learn when the FCW system is identifying a metal object that is not actually dangerous, such as a drainage grid or manhole cover that triggers an alarm. Similarly, when the auxiliary computer is a camera-based LDW system, the neural network in the supervisory MCU can learn to ignore the LDW when a cyclist or pedestrian is present and lane departure is actually the safest strategy. In an embodiment including a neural network running on the supervisory MCU, the supervisory MCU may include at least one of a DLA or GPU suitable for running the neural network with associated memory. In a preferred embodiment, the supervisory MCU may include a component of SoC 904 and / or be included as a component of SoC 904.

[0187] In other examples, the ADAS system 938 may include an auxiliary computer that uses traditional computer vision rules to perform ADAS functions. In this way, the auxiliary computer can use classic computer vision rules (if-then), and the presence of a neural network in the supervisory MCU can improve reliability, safety, and performance. For example, diverse implementations and intentional non-identity make the entire system more fault-tolerant, especially for failures caused by software (or software-hardware interface) functions. For example, if there is a software vulnerability or error in the software running on the main computer and the non-identical software code running on the auxiliary computer provides the same overall result, the supervisory MCU can be more confident that the overall result is correct and that the vulnerability in the software or hardware on the main computer does not cause a substantial error.

[0188] In some examples, the output of the ADAS system 938 can be fed to the perception block of the main computer and / or the dynamic driving task block of the main computer. For example, if the ADAS system 938 indicates a forward collision warning due to an object immediately ahead, the perception block can use this information when identifying the object. In other examples, the auxiliary computer can have its own neural network that is trained and thus reduces the risk of false positives as described herein.

[0189] The vehicle 900 may further include an infotainment SoC 930 (e.g., an in-vehicle infotainment system (IVI)). Although illustrated and described as an SoC, the infotainment system may not be an SoC and may include two or more discrete components. The infotainment SoC 930 may include a combination of hardware and software that may be used to provide audio (e.g., music, personal digital assistant, navigation instructions, news, radio, etc.), video (e.g., TV, movies, streaming media, etc.), phone (e.g., hands-free calling), network connectivity (e.g., LTE, Wi-Fi, etc.), and / or information services (e.g., navigation system, rear parking assistance, radio data system, vehicle-related information such as fuel level, total distance covered, brake fuel level, oil level, door open / closed, air filter information, etc.) to the vehicle 900. For example, the infotainment SoC 930 may include a radio, a disc player, a navigation system, a video player, USB and Bluetooth connections, an onboard computer, onboard entertainment, Wi-Fi, steering wheel audio controls, hands-free voice controls, a head-up display (HUD), an HMI display 934, a telematics device, a control panel (e.g., for controlling and / or interacting with various components, features and / or systems), and / or other components. The infotainment SoC 930 may further be used to provide information (e.g., visual and / or auditory) to a user of the vehicle, such as information from an ADAS system 938, autonomous driving information such as planned vehicle maneuvers, trajectories, surrounding environment information (e.g., intersection information, vehicle information, road information, etc.), and / or other information.

[0190] The infotainment SoC 930 may include GPU functionality. The infotainment SoC 930 may communicate with other devices, systems, and / or components of the vehicle 900 via a bus 902 (e.g., a CAN bus, Ethernet, etc.). In some examples, the infotainment SoC 930 may be coupled to a supervisory MCU so that in the event of a failure of a main controller 936 (e.g., a main and / or backup computer of the vehicle 900), the GPU of the infotainment system may perform some self-driving functions. In such an example, the infotainment SoC 930 may place the vehicle 900 in a driver safety parking mode as described herein.

[0191] The vehicle 900 may further include an instrument cluster 932 (e.g., a digital instrument panel, an electronic instrument cluster, a digital instrument panel, etc.). The instrument cluster 932 may include a controller and / or a supercomputer (e.g., a separate controller or a supercomputer). The instrument cluster 932 may include a set of instruments, such as a speedometer, a fuel level, an oil pressure, a tachometer, an odometer, a turn indicator, a shift position indicator, a seat belt warning light, a parking brake warning light, an engine fault light, an airbag (SRS) system information, a lighting control, a safety system control, navigation information, and the like. In some examples, information may be displayed and / or shared between the infotainment SoC 930 and the instrument cluster 932. In other words, the instrument cluster 932 may be included as part of the infotainment SoC 930, or vice versa.

[0192] Fig.9D For a cloud-based server and Fig.9A 900. System 976 may include a server 978, a network 990, and a vehicle including the vehicle 900. The server 978 may include a plurality of GPUs 984 (A) -984 (H) (collectively referred to herein as GPUs 984), PCIe switches 982 (A) -982 (H) (collectively referred to herein as PCIe switches 982), and / or CPUs 980 (A) -980 (B) (collectively referred to herein as CPUs 980). The GPUs 984, CPUs 980, and PCIe switches may be interconnected with high-speed interconnects and / or PCIe connections 986 such as, for example and without limitation, the NVLink interface 988 developed by NVIDIA. In some examples, the GPUs 984 are connected via NVLink and / or NVSwitch SoCs, and the GPUs 984 and PCIe switches 982 are connected via PCIe interconnects. Although eight GPUs 984, two CPUs 980, and two PCIe switches are illustrated, this is not intended to be limiting. Depending on the embodiment, each of the servers 978 may include any number of GPUs 984, CPUs 980, and / or PCIe switches. For example, each of the servers 978 may include eight, sixteen, thirty-two, and / or more GPUs 984.

[0193] Server 978 may receive image data over network 990 and from a vehicle, the image data representing images showing unexpected or changed road conditions, such as recently begun road work. Server 978 may transmit neural network 992, updated neural network 992, and / or map information 994, including information about traffic and road conditions, over network 990 and to the vehicle. Updates to map information 994 may include updates to HD map 922, such as information about construction sites, potholes, curves, flooding, or other obstacles. In some examples, neural network 992, updated neural network 992, and / or map information 994 may have been generated from new training and / or data received from any number of vehicles in the environment and / or based on experience from training performed at a data center (e.g., using server 978 and / or other servers).

[0194] Server 978 can be used to train a machine learning model (e.g., a neural network) based on training data. The training data can be generated by the vehicle, and / or can be generated in a simulation (e.g., using a game engine). In some examples, the training data is labeled (e.g., when the neural network benefits from supervised learning) and / or undergoes other preprocessing, while in other examples, the training data is not labeled and / or preprocessed (e.g., when the neural network does not require supervised learning). Training can be performed according to any one or more categories of machine learning techniques, including but not limited to: categories such as supervised training, semi-supervised training, unsupervised training, self-learning, reinforcement learning, joint learning, transfer learning, feature learning (including main components and cluster analysis), multilinear subspace learning, manifold learning, representation learning (including alternate dictionary learning), rule-based machine learning, anomaly detection, and any variants or combinations thereof. Once the machine learning model is trained, the machine learning model can be used by the vehicle (e.g., transmitted to the vehicle via network 990), and / or the machine learning model can be used by server 978 to remotely monitor the vehicle.

[0195] In some examples, server 978 can receive data from the vehicle and apply the data to the latest real-time neural network for real-time intelligent reasoning. Server 978 may include a deep learning supercomputer and / or a dedicated AI computer powered by GPU 984, such as DGX and DGX Station machines developed by NVIDIA. However, in some examples, server 978 may include a deep learning infrastructure of a data center powered only by CPUs.

[0196] The deep learning infrastructure of server 978 may be capable of rapid real-time inference, and may use this capability to assess and verify the health of the processors, software, and / or associated hardware in vehicle 900. For example, the deep learning infrastructure may receive periodic updates from vehicle 900, such as a sequence of images and / or objects located in the sequence of images that vehicle 900 has located (e.g., via computer vision and / or other machine learning object classification techniques). The deep learning infrastructure may run its own neural network to identify objects and compare them to the objects identified by vehicle 900, and if the results do not match and the infrastructure concludes that the AI ​​in vehicle 900 has failed, then server 978 may transmit a signal to vehicle 900 instructing the fail-safe computer of vehicle 900 to take control, notify passengers, and complete a safe parking maneuver.

[0197] For reasoning, the server 978 may include a GPU 984 and one or more programmable reasoning accelerators (e.g., NVIDIA's TensorRT). The combination of GPU-powered servers and reasoning acceleration can make real-time responses possible. In other examples, such as when performance is not so important, CPU, FPGA, and other processor-powered servers can be used for reasoning.

[0198] Example computing device

[0199] Fig.10 1 is a block diagram of an example computing device 1000 suitable for implementing some embodiments of the present disclosure. The computing device 1000 may include an interconnect system 1002 that directly or indirectly couples the following devices: a memory 1004, one or more central processing units (CPUs) 1006, one or more graphics processing units (GPUs) 1008, a communication interface 1010, an input / output (I / O) port 1012, an input / output component 1014, a power supply 1016, one or more presentation components 1018 (e.g., a display), and one or more logic units 1020. In at least one embodiment, one or more computing devices 1000 may include one or more virtual machines (VMs), and / or any of their components may include virtual components (e.g., virtual hardware components). For non-limiting examples, one or more of the GPUs 1008 may include one or more vGPUs, one or more of the CPUs 1006 may include one or more vCPUs, and / or one or more of the logic units 1020 may include one or more virtual logic units. As such, one or more computing devices 1000 may include discrete components (eg, a full GPU dedicated to computing device 1000 ), virtual components (eg, a portion of a GPU dedicated to computing device 1000 ), or a combination thereof.

[0200] although Fig.10 The various blocks of are shown as being connected via an interconnect system 1002 having lines, but this is not intended to be limiting and is merely for clarity. For example, in some embodiments, a presentation component 1018 such as a display device may be considered an I / O component 1014 (e.g., if the display is a touch screen). As another example, CPU 1006 and / or GPU 1008 may include memory (e.g., memory 1004 may represent a storage device in addition to the memory of GPU 1008, CPU 1006, and / or other components). In other words, Fig.10 The computing devices described herein are illustrative only. No distinction is made between categories such as "workstations," "servers," "laptops," "desktops," "tablets," "client devices," "mobile devices," "handheld devices," "game consoles," "electronic control units (ECUs)," "virtual reality systems," and / or other device or system types, as all are considered Fig.10 within the range of computing devices.

[0201] The interconnection system 1002 may represent one or more links or buses, such as an address bus, a data bus, a control bus, or a combination thereof. The interconnection system 1002 may include one or more bus or link types, such as an industry standard architecture (ISA) bus, an extended industry standard architecture (EISA) bus, a video electronics standard association (VESA) bus, a peripheral component interconnect (PCI) bus, a peripheral component interconnect express (PCIe) bus, and / or another type of bus or link. In some embodiments, there is a direct connection between components. For example, the CPU 1006 may be directly connected to the memory 1004. In addition, the CPU 1006 may be directly connected to the GPU 1008. In the case where there is a direct or point-to-point connection between components, the interconnection system 1002 may include a PCIe link to perform the connection. In these examples, the computing device 1000 does not need to include a PCI bus.

[0202] Memory 1004 may include any of a variety of computer-readable media. Computer-readable media may be any available media that can be accessed by computing device 1000. Computer-readable media may include volatile and nonvolatile media and removable and non-removable media. By way of example and not limitation, computer-readable media may include computer storage media and communication media.

[0203] Computer storage media may include volatile and nonvolatile media and / or removable and non-removable media implemented in any method or technology for storing information such as computer-readable instructions, data structures, program modules, and / or other data types. For example, memory 1004 may store computer-readable instructions (e.g., representing programs and / or program elements, such as an operating system). Computer storage media may include, but are not limited to, RAM, ROM, EEPROM, flash memory or other storage technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by computing device 1000. As used herein, computer storage media does not include the signals themselves.

[0204] Computer storage media may include computer readable instructions, data structures, program modules, and / or other data types in a modulated data signal such as a carrier wave or other transmission mechanism, and include any information delivery media. The term "modulated data signal" may refer to a signal that has one or more of its characteristics set or changed in such a way that information is encoded into the signal. By way of example and not limitation, computer storage media may include wired media such as a wired network or a direct wired connection, and wireless media such as sound, RF, infrared, and other wireless media. Any combination of the above should also be included within the scope of computer readable media.

[0205] The CPU 1006 may be configured to execute at least some of the computer-readable instructions so as to control one or more components of the computing device 1000 to perform one or more of the methods and / or processes described herein. Each of the CPUs 1006 may include one or more cores (e.g., one, two, four, eight, twenty-eight, seventy-two, etc.) capable of simultaneously processing a large number of software threads. The CPU 1006 may include any type of processor, and may include different types of processors, depending on the type of computing device 1000 implemented (e.g., a processor with fewer cores for mobile devices and a processor with more cores for servers). For example, depending on the type of computing device 1000, the processor may be an Advanced RISC Machine (ARM) processor implemented using Reduced Instruction Set Computing (RISC) or an x86 processor implemented using Complex Instruction Set Computing (CISC). The computing device 1000 may also include one or more CPUs 1006 in addition to one or more microprocessors or supplementary coprocessors such as math coprocessors.

[0206] In addition to or as an alternative to CPU 1006, one or more GPUs 1008 may be configured to execute at least some of the computer-readable instructions to control one or more components of computing device 1000 to perform one or more of the methods and / or processes described herein. One or more GPUs 1008 may be integrated GPUs (e.g., with one or more CPUs 1006) and / or one or more GPUs 1008 may be discrete GPUs. In an embodiment, one or more GPUs 1008 may be coprocessors of one or more CPUs 1006. Computing device 1000 may use GPU 1008 to render graphics (e.g., 3D graphics) or perform general purpose computing. For example, one or more GPUs 1008 may be used for general purpose computing (GPGPU) on GPUs. One or more GPUs 1008 may include hundreds of thousands of cores capable of processing hundreds of thousands of software threads simultaneously. GPU 1008 may generate pixel data for outputting an image in response to a rendering command (e.g., a rendering command from CPU 1006 received via a host interface). GPU 1008 may include graphics memory, such as display memory, for storing pixel data or any other suitable data, such as GPGPU data. Display memory may be included as part of memory 1004. One or more GPUs 1008 may include two or more GPUs operating in parallel (e.g., via a link). The link may connect the GPUs directly (e.g., using NVLINK) or may connect the GPUs through a switch (e.g., using NVSwitch). When combined together, each GPU 1008 may generate pixel data or GPGPU data for different parts of the output or different outputs (e.g., a first GPU for a first image and a second GPU for a second image). Each GPU may include its own memory or may share memory with other GPUs.

[0207] In addition to or as an alternative to the CPU 1006 and / or the GPU 1008, the logic unit 1020 may be configured to execute at least some of the computer-readable instructions to control one or more components of the computing device 1000 to perform one or more of the methods and / or processes described herein. In an embodiment, the CPU 1006, the GPU 1008, and / or the logic unit 1020 may perform any combination of methods, processes, and / or portions thereof separately or jointly. The one or more logic units 1020 may be a part of and / or integrated into one or more of the CPU 1006 and / or the GPU 1008, and / or the one or more logic units 1020 may be a discrete component or otherwise external to the CPU 1006 and / or the GPU 1008. In an embodiment, the one or more logic units 1020 may be a coprocessor of the one or more CPUs 1006 and / or the one or more GPUs 1008.

[0208] Examples of logic unit 1020 include one or more processing cores and / or components thereof, such as a data processing unit (DPU), a tensor core (TC), a tensor processing unit (TPU), a pixel vision core (PVC), a vision processing unit (VPU), a graphics processing cluster (GPC), a texture processing cluster (TPC), a streaming multiprocessor (SM), a tree traversal unit (TTU), an artificial intelligence accelerator (AIA), a deep learning accelerator (DLA), an arithmetic logic unit (ALU), an application specific integrated circuit (ASIC), a floating point unit (FPU), an input / output (I / O) element, a peripheral component interconnect (PCI) or a peripheral component interconnect express (PCIe) element, etc.

[0209] The communication interface 1010 may include one or more receivers, transmitters, and / or transceivers that enable the computing device 1000 to communicate with other computing devices via an electronic communication network, including wired and / or wireless communications. The communication interface 1010 may include components and functions that enable communication over any of a number of different networks, such as wireless networks (e.g., Wi-Fi, Z-wave, Bluetooth, Bluetooth LE, ZigBee, etc.), wired networks (e.g., communicating over Ethernet or InfiniBand), low power wide area networks (e.g., LoRaWAN, SigFox, etc.), and / or the Internet. In one or more embodiments, the one or more logic units 1020 and / or the communication interface 1010 may include one or more data processing units (DPUs) to transmit data received over a network and / or over the interconnect system 1002 directly to (e.g., memory) one or more GPUs 1008.

[0210] I / O ports 1012 can enable computing device 1000 to be logically coupled to other devices including I / O components 1014, presentation components 1018, and / or other components, some of which can be built into (e.g., integrated into) computing device 1000. Illustrative I / O components 1014 include microphones, mice, keyboards, joysticks, game pads, game controllers, satellite dishes, scanners, printers, wireless devices, and the like. I / O components 1014 can provide a natural user interface (NUI) that processes air gestures, voice, or other physiological inputs generated by a user. In some instances, the input can be transmitted to an appropriate network element for further processing. The NUI can implement any combination of voice recognition, stylus recognition, facial recognition, biometric recognition, gesture recognition on and adjacent to the screen, air gestures, head and eye tracking, and touch recognition associated with the display of computing device 1000 (as described in more detail below). Computing device 1000 may include a depth camera such as a stereo camera system, an infrared camera system, an RGB camera system, touch screen technology, and combinations of these for gesture detection and recognition. Additionally, computing device 1000 may include an accelerometer or gyroscope to enable motion detection (e.g., as part of an inertial measurement unit (IMU)). In some examples, the output of the accelerometer or gyroscope may be used by computing device 1000 to render immersive augmented reality or virtual reality.

[0211] The power supply 1016 may include a hardwired power supply, a battery power supply, or a combination thereof. The power supply 1016 may provide power to the computing device 1000 to enable the components of the computing device 1000 to operate.

[0212] The presentation component 1018 may include a display (e.g., a monitor, a touch screen, a television screen, a head-up display (HUD), other display types, or a combination thereof), a speaker, and / or other presentation components. The presentation component 1018 may receive data from other components (e.g., GPU 1008, CPU 1006, DPU, etc.) and output the data (e.g., as an image, video, sound, etc.).

[0213] Sample Data Center

[0214] Fig.11 An example data center 1100 that can be used in at least one embodiment of the present disclosure is shown. The data center 1100 can include a data center infrastructure layer 1110, a framework layer 1120, a software layer 1130, and / or an application layer 1140.

[0215] like Fig.11As shown, the data center infrastructure layer 1110 may include a resource coordinator 1112, grouped computing resources 1114, and node computing resources ("node CRs") 1116(1)-1116(N), where "N" represents any complete positive integer. In at least one embodiment, the node CRs 1116(1)-1116(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 or graphics processing units (GPUs), etc.), memory devices (e.g., dynamic read-only memories), storage devices (e.g., solid-state or disk drives), network input / output ("NW I / O") devices, network switches, virtual machines ("VMs"), power modules and / or cooling modules, etc. In some embodiments, one or more of the node CRs 1116(1)-1116(N) may correspond to a server having one or more of the above-mentioned computing resources. Furthermore, in some embodiments, nodes CR1116(1)-11161(N) may include one or more virtual components, such as vGPU, vCPU, etc., and / or one or more of nodes CR1116(1)-1116(N) may correspond to a virtual machine (VM).

[0216] In at least one embodiment, the grouped computing resources 1114 may include a separate grouping of node CR1116 housed in one or more racks (not shown), or many racks housed in a data center at different geographical locations (also not shown). The separate grouping of node CR1116 in the grouped computing resources 1114 may include grouped computing, network, memory or storage resources that can be configured or allocated to support one or more workloads. In at least one embodiment, several node CR1116 including CPU, GPU, DPU and / or other processors can be grouped in one or more racks to provide computing resources to support one or more workloads. One or more racks may also include any number of power modules, cooling modules and / or network switches in any combination.

[0217] Resource coordinator 1122 may configure or otherwise control one or more nodes CR 1116(1)-1116(N) and / or grouped computing resources 1114. In at least one embodiment, resource coordinator 1122 may include a software design infrastructure ("SDI") management entity for data center 1100. Resource coordinator 1122 may include hardware, software, or some combination thereof.

[0218] In at least one embodiment, Fig.11As shown, the framework layer 1120 may include a job scheduler 1133, a configuration manager 1134, a resource manager 1136, and / or a distributed file system 1138. The framework layer 1120 may include a framework that supports software 1132 of the software layer 1130 and / or one or more applications 1142 of the application layer 1140. The software 1132 or the application 1142 may include network-based service software or applications, such as those provided by Amazon Web Services, Google Cloud, and Microsoft Azure. The framework layer 1120 may be, but is not limited to, a type of free and open source software network application framework (such as Apache SparkTM (hereinafter referred to as "Spark")) that can utilize the distributed file system 1138 for large-scale data processing (e.g., "big data"). In at least one embodiment, the job scheduler 1133 may include a Spark driver to facilitate scheduling workloads supported by different layers of the data center 1100. Configuration manager 1134 may be capable of configuring different layers, such as software layer 1130 and framework layer 1120 (which includes Spark and distributed file system 1138 for supporting large-scale data processing). Resource manager 1136 may be capable of managing clustered or grouped computing resources mapped to distributed file system 1138 and job scheduler 1133 or allocated to support distributed file system 1138 and job scheduler 1133. In at least one embodiment, clustered or grouped computing resources may include grouped computing resources 1114 at data center infrastructure layer 1110. Resource manager 1136 may coordinate with resource coordinator 1112 to manage these mapped or allocated computing resources.

[0219] In at least one embodiment, the software 1132 included in the software layer 1130 may include software used by at least a portion of the node CRs 1116(1)-1116(N), the grouped computing resources 1114, and / or the distributed file system 1138 of the framework layer 1120. The 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.

[0220] In at least one embodiment, the applications 1142 included in the application layer 1140 may include one or more types of applications used by at least a portion of the node CRs 1116(1)-1116(N), the grouped computing resources 1114, and / or the distributed file system 1138 of the framework layer 1120. The one or more types of applications may include, but are not limited to, any number of genomic applications, cognitive computing, and machine learning applications, including training or inference software, machine learning framework software (e.g., PyTorch, TensorFlow, Caffe, etc.), and / or other machine learning applications used in conjunction with one or more embodiments.

[0221] In at least one embodiment, any of configuration manager 1134, resource manager 1136, and resource coordinator 1112 can implement any number and type of self-modification actions based on any amount and type of data acquired in any technically feasible manner. The self-modification actions can save a data center operator of data center 1100 from making potentially poor configuration decisions and potentially avoiding underutilized and / or poorly performing portions of the data center.

[0222] According to one or more embodiments described herein, data center 1100 may include tools, services, software, or other resources to train one or more machine learning models or use one or more machine learning models to predict or infer information. For example, the (one or more) machine learning models may be trained by calculating weight parameters according to a neural network architecture using the software and / or computing resources described above with respect to data center 1100. In at least one embodiment, a trained or deployed machine learning model corresponding to one or more neural networks may be used to infer or predict information using the resources described above with respect to data center 1100 using weight parameters calculated by one or more training techniques, such as, but not limited to, those described herein.

[0223] In at least one embodiment, the data center 1100 may use a CPU, an application-specific integrated circuit (ASIC), a GPU, an FPGA, and / or other hardware (or virtual computing resources corresponding thereto) to perform training and / or inference using the above resources. In addition, one or more software and / or hardware resources described above may be configured to allow a user to train or perform services that infer information, such as image recognition, speech recognition, or other artificial intelligence services.

[0224] Example network environment

[0225] A network environment suitable for implementing embodiments of the present disclosure may include one or more client devices, servers, network attached storage (NAS), other backend devices, and / or other device types. The client devices, servers, and / or other device types (e.g., each device) may be configured to communicate with the client device, server, or other device types. Fig.10 The computing device 1000 of the embodiment of the present invention may be implemented on one or more instances of the computing device 1000 - for example, each device may include similar components, features and / or functions of the computing device 1000. In addition, in the case of implementing a backend device (e.g., a server, NAS, etc.), the backend device may be included as part of the data center 1100, and the example of the data center 1100 is described in this article. Fig.11 Describe in more detail.

[0226] The components of the network environment can communicate with each other through a network, which can be wired, wireless, or both. The network can include multiple networks, or one of multiple networks. For example, the network can include one or more wide area networks (WANs), one or more local area networks (LANs), one or more public networks, such as the Internet and / or a public switched telephone network (PSTN), and / or one or more private networks. In the case where the network includes a wireless telecommunications network, components such as base stations, communication towers, or even access points (and other components) can provide wireless connections.

[0227] Compatible network environments may include one or more peer-to-peer network environments (in which case the server may not be included in the network environment) and one or more client-server network environments (in which case one or more servers may be included in the network environment). In a peer-to-peer network environment, the functionality described herein with respect to the server may be implemented on any number of client devices.

[0228] In at least one embodiment, the network environment may include one or more cloud-based network environments, distributed computing environments, combinations thereof, and the like. A cloud-based network environment may include a framework layer, a job scheduler, a resource manager, and a distributed file system implemented on one or more servers, which may include one or more core network servers and / or edge servers. The framework layer may include a framework for supporting software at the software layer and / or one or more applications at the application layer. The software or application may include network-based service software or application programs, respectively. In an embodiment, one or more client devices may use network-based service software or application programs (e.g., by accessing the service software and / or application programs via one or more application programming interfaces (APIs)). The framework layer may be, but is not limited to, a type of free and open source software network application framework, such as a distributed file system that may be used for large-scale data processing (e.g., "big data").

[0229] A cloud-based network environment can provide cloud computing and / or cloud storage that performs any combination of the computing and / or data storage functions (or one or more portions thereof) described herein. Any of these various functions can be distributed across multiple locations of a central or core server (e.g., one or more data centers that can be distributed across a state, region, country, global, etc.). If the connection to a user (e.g., a client device) is relatively close to an edge server, the core server can assign at least a portion of the functionality to the edge server. A cloud-based network environment can be private (e.g., limited to a single organization), public (e.g., available to many organizations), and / or a combination thereof (e.g., a hybrid cloud environment).

[0230] The client device may include Fig.10 At least some of the components, features, and functionality of the described example computing device 1000. By way of example and not limitation, the client device may be embodied as a personal computer (PC), a laptop computer, a mobile device, a smart phone, a tablet computer, a smart watch, a wearable computer, a personal digital assistant (PDA), an MP3 player, a virtual reality headset, a global positioning system (GPS) or device, a video player, a camera, a surveillance device or system, a vehicle, a vessel, an aircraft, a virtual machine, a drone, a robot, a handheld communication device, a hospital device, a gaming device or system, an entertainment system, an in-vehicle computer system, an embedded system controller, a remote control, an appliance, a consumer electronic device, a workstation, an edge device, any combination of the devices described, or any other suitable device.

[0231] The present disclosure may be described in the general context of machine-usable instructions or computer codes executed by a computer or other machine such as a personal digital assistant or other handheld device, including computer-executable instructions such as program modules. Typically, program modules including routines, programs, objects, components, data structures, etc. refer to codes that perform specific tasks or implement specific abstract data types. The present disclosure may be practiced in a variety of system configurations, including handheld devices, consumer electronics, general-purpose computers, more specialized computing devices, etc. The present disclosure may also be practiced in a distributed computing environment in which tasks are performed by remote processing devices linked through a communication network.

[0232] As used herein, the description of "and / or" about two or more elements should be interpreted as referring to only one element or a combination of elements. For example, "element A, element B and / or element C" may include only element A, only element B, only element C, element A and element B, element A and element C, element B and element C, or elements A, B and C. In addition, "at least one of element A or element B" may include at least one of element A, at least one of element B, or at least one of element A and at least one of element B. Further, "at least one of element A and element B" may include at least one of element A, at least one of element B, or at least one of element A and at least one of element B.

[0233] The subject matter of the present disclosure is described in detail herein to meet statutory requirements. However, the description itself is not intended to limit the scope of the present disclosure. On the contrary, the inventors have contemplated that the claimed subject matter may also be embodied in other ways to include steps different from the steps described herein in conjunction with other current or future technologies or combinations of similar steps. Moreover, although the terms "step" and / or "block" may be used herein to imply different elements of the method employed, these terms should not be interpreted as implying any particular order among or between the various steps disclosed herein, unless the order of the steps is explicitly described.

Claims

1. A processor, comprising: One or more processing units, the one or more processing units being configured to: generating RGB image data for a first frame based at least on operating the image processing pipeline in an RGB imaging mode; switching to operating the image processing pipeline in an IR imaging mode to generate infrared (IR) image data for a second frame based at least on detecting that a first light intensity amount associated with the RGB image data of the first frame is less than a first intensity threshold; as well as Based at least on detecting that a second light intensity amount associated with the IR image data of the second frame exceeds a second intensity threshold, switching to operating the image processing pipeline in the RGB imaging mode.

2. The processor of claim 1, wherein the first intensity threshold for switching from the RGB imaging mode to the IR imaging mode has an intensity lower than the second intensity threshold for switching from the IR imaging mode to the RGB imaging mode.

3. A processor according to claim 1, wherein the first light intensity quantity quantifies the amount of green light in the RGB image data of the first frame, and wherein the one or more processing units are further used to: convert the image processing pipeline to operate in the IR imaging mode based at least on detecting that the amount of green light in the RGB image data of the first frame is less than the first intensity threshold.

4. The processor of claim 1 , wherein the second light intensity quantity quantifies an amount of green light in the IR image data of the second frame, wherein the one or more processing units are further configured to: convert the image processing pipeline to operate in the RGB imaging mode based at least on detecting that the amount of green light in the IR image data of the second frame exceeds the second intensity threshold.

5. A processor according to claim 1, wherein the one or more processing units are further used to: convert the image processing pipeline to operate in the RGB imaging mode based at least on detecting that the second light intensity amount exceeds the second intensity threshold and detecting that the ratio of the amount of IR light in the IR image data of the second frame to the second light intensity amount is less than a third threshold.

6. The processor of claim 1, wherein the one or more processing units are further configured to determine at least one of the first light intensity amount or the second light intensity amount based at least on averaging intensity values ​​in a specified subset of the first frame or the second frame.

7. The processor of claim 1 , wherein the one or more processing units are further configured to switch to operating the image processing pipeline in the RGB imaging mode based at least on turning off an IR emitter and subtracting IR intensity from one or more color channels.

8. The processor of claim 1 , wherein operating the image processing pipeline in the IR imaging mode comprises: Activates the IR lighting emitters and renders in grayscale.

9. The processor of claim 1, wherein the one or more processing units are further configured to: control one or more RGB / IR cameras in an occupant monitoring system.

10. The processor of claim 1, wherein the processor is included in at least one of the following: control systems for autonomous or semi-autonomous machines; Perception systems for autonomous or semi-autonomous machines; A system for performing simulation operations; Systems for performing digital twin operations; A system for performing light transport simulations; A system for performing collaborative content creation of 3D assets; Systems for performing deep learning operations; Systems for performing remote operations; A system for performing real-time streaming; Systems for generating or presenting one or more of augmented reality content, virtual reality content, or mixed reality content; Systems implemented using edge devices; Systems implemented using robots; Systems for performing conversational AI operations; A system implementing one or more language models; A system implementing one or more large language models (LLMs); Systems for generating synthetic data; Systems for generating synthetic data using AI; A system comprising one or more virtual machines VM; A system implemented at least in part in a data center; or A system implemented at least in part using cloud computing resources.

11. A system comprising one or more processing units for switching, by an image processing pipeline, between an infrared (IR) imaging mode and an RGB imaging mode in response to different thresholds of detected light intensity depending on a switching state.

12. A system according to claim 11, wherein the intensity of a first threshold among the different thresholds of the detected light intensity for converting from the RGB imaging mode to the IR imaging mode is lower than the intensity of a corresponding threshold among the different thresholds of the detected light intensity for converting from the IR imaging mode to the RGB imaging mode.

13. A system according to claim 11, wherein the one or more processing units are also used to: convert the image processing pipeline to operate in the IR imaging mode based on at least detecting that the amount of green light in the RGB image data frame generated in the RGB imaging mode is less than a corresponding threshold value among different threshold values ​​of the detected light intensity.

14. A system according to claim 11, wherein the one or more processing units are further used to: convert the image processing pipeline to operate in the RGB imaging mode based at least on detecting that the amount of green light in the IR image data frame generated in the IR imaging mode exceeds a corresponding threshold value among different threshold values ​​of the detected light intensity.

15. The system of claim 11, wherein the one or more processing units are further configured to switch to operating the image processing pipeline in the RGB imaging mode based at least on: detecting that the amount of light intensity in an IR image data frame generated in the IR imaging mode exceeds a first corresponding threshold value among different threshold values ​​of the detected light intensity, and It is detected that a ratio of the amount of IR light in the IR image data frame to the amount of light intensity is less than a second corresponding threshold.

16. A system according to claim 11, wherein the one or more processing units are also used to at least determine the amount of the detected light intensity based on at least averaging the intensity values ​​in a specified subset of the RGB image data frames generated in the RGB imaging mode or the IR image data frames generated in the IR imaging mode.

17. The system of claim 11, wherein the one or more processing units are further configured to switch to operating the image processing pipeline in the RGB imaging mode based at least on disabling IR emitters and subtracting IR intensity from one or more color channels.

18. The system of claim 11, wherein the system is included in at least one of the following: control systems for autonomous or semi-autonomous machines; Perception systems for autonomous or semi-autonomous machines; A system for performing simulation operations; Systems for performing digital twin operations; A system for performing light transport simulations; A system for performing collaborative content creation of 3D assets; Systems for performing deep learning operations; A system for performing real-time streaming; Systems for generating or presenting one or more of augmented reality content, virtual reality content, or mixed reality content; Systems implemented using edge devices; Systems implemented using robots; Systems for performing conversational AI operations; A system implementing one or more language models; A system implementing one or more large language models (LLMs); Systems for generating synthetic data; Systems for generating synthetic data using AI; A system comprising one or more virtual machines VM; A system implemented at least in part in a data center; or A system implemented at least in part using cloud computing resources.

19. A method comprising: generating RGB image data for a first frame based at least on operating the image processing pipeline without IR illumination produced by the infrared (IR) emitter; switching to operate the image processing pipeline including the IR illumination generated by the IR emitter to generate infrared (IR) image data for a second frame based at least on detecting that a first light intensity amount associated with the RGB image data for the first frame is less than a first intensity threshold; as well as Based at least on detecting that a second light intensity amount associated with the IR image data of the second frame exceeds a second intensity threshold, transitioning to operating the image processing pipeline without the IR illumination generated by the IR emitter.

20. The method of claim 19, wherein the method is performed by at least one of: control systems for autonomous or semi-autonomous machines; Perception systems for autonomous or semi-autonomous machines; A system for performing simulation operations; Systems for performing digital twin operations; A system for performing light transport simulations; A system for performing collaborative content creation of 3D assets; Systems for performing deep learning operations; A system for performing real-time streaming; Systems for generating or presenting one or more of augmented reality content, virtual reality content, or mixed reality content; Systems implemented using edge devices; Systems implemented using robots; Systems for performing conversational AI operations; A system implementing one or more language models; A system implementing one or more large language models (LLMs); Systems for generating synthetic data; Systems for generating synthetic data using AI; A system comprising one or more virtual machines VM; A system implemented at least in part in a data center; or A system implemented at least in part using cloud computing resources.

Images