CN111837163A - System and method for vehicle wheel detection - Google Patents

Abstract

A system and method for vehicle wheel detection is disclosed. Particular embodiments may be configured to: receiving training image data from a training image data collection system; obtaining ground truth data corresponding to the training image data; performing a training phase to train one or more classifiers to process images in the training image data to detect vehicle wheel objects in the images in the training image data; receiving operational image data from an image data collection system associated with an autonomous vehicle; and performing an operational phase comprising applying the trained one or more classifiers to extract vehicle wheel objects from the operational image data and generating vehicle wheel object data.

Description

System and method for vehicle wheel detection

priority patent application

This document claims priority to US Non-Provisional Patent Application Serial No. 15/917,331, filed March 9, 2018, entitled "SYSTEM AND METHOD FOR VEHICLE WHEELDETECTION," which is incorporated herein by reference in its entirety. This article claims priority to US Non-Provisional Patent Application Serial No. 15/456,219, filed March 10, 2017, entitled "SYSTEM AND METHOD FOR SEMANTICSEGMENTATION USING DENSE UPSAMPLING CONVOLUTION (DUC)," which is incorporated by reference in its entirety. into this article. This article claims priority to US Non-Provisional Patent Application Serial No. 15/456,294, filed March 10, 2017, entitled "SYSTEM AND METHOD FOR SEMANTIC SEGMENTATION USING HYBRID DILATED CONVOLUTION (HDC)", which is incorporated by reference in its entirety. into this article. The disclosures of the cited patent applications are considered part of the disclosure of this application and are incorporated herein by reference in their entirety.

technical field

This patent document relates generally to tools (systems, apparatus, methods, computer program products, etc.) for image processing, vehicle control systems, and autonomous driving systems, and more particularly, but not by way of limitation, to a system for vehicle wheel detection and method.

Background technique

In autonomous driving systems, the successful perception and prediction of the surrounding driving environment and traffic participants is critical to making correct and safe decisions regarding control of autonomous or managed vehicles. In the existing literature and applications in visual perception, techniques such as object recognition, two-dimensional (2D) object detection, and 2D scene understanding (or semantic segmentation) have been extensively studied and used. These visual perception techniques have been successfully applied for use with autonomous or managed vehicles with the help of rapidly advancing deep learning techniques and computing power, such as graphics processing units [GPUs]. However, compared to these 2D perception methods, less research has been done on full three-dimensional (3D) perception techniques because of the difficulty in obtaining reliable ground-truth data and the difficulty in properly training 3D models. For example, correctly annotating 3D bounding boxes for 3D object detection requires accurate measurement of extrinsic and intrinsic camera parameters and motion of autonomous or managed vehicles, which is often difficult or impossible to achieve. Even if ground truth data is available, 3D models are difficult to train because the amount of training data is limited and measurements are inaccurate. Therefore, in these visual perception applications, less expensive and less performant alternative solutions have been used.

Therefore, an efficient system for detecting and analyzing vehicle wheels is necessary.

SUMMARY OF THE INVENTION

Vehicle wheels are important features for determining the exact position and attitude of a moving vehicle. Vehicle posture may include vehicle heading, orientation, speed, acceleration, and the like. However, the use of vehicle wheel features for vehicle control is often overlooked in existing literature and applications in computer vision and autonomous driving. In various example embodiments disclosed herein, a system and method for vehicle wheel detection using image segmentation is provided. In an example embodiment, the system includes three components: 1) data collection and annotation, 2) model training using deep convolutional neural networks, and 3) real-time model inference. To take advantage of state-of-the-art deep learning models and training strategies, the various example embodiments disclosed herein formulate the wheel detection problem as a two-class segmentation task and train on deep neural networks that excel at multi-class semantic segmentation problems. Test results show that the system disclosed in this paper can successfully detect vehicle wheel features in real-time in complex driving scenarios. The various example embodiments disclosed herein may be used in various applications such as 3D vehicle pose estimation and vehicle lane distance estimation, among others.

Vehicle wheels can be used for vehicle characterization for at least three reasons: 1) Perceptions and predictions of other traffic participants are primarily about their trajectories on the road surface, where wheels can provide the best measure because They are the parts of the vehicle that are closest to the road surface; 2) the wheels can provide a reliable estimate of the vehicle's pose, since vehicles typically have four or more wheels as reference points; 3) the wheels are conceptually easy to detect because of their The shape and position in the vehicle are uniform. When we obtain accurate segmentation analysis of wheel features for a given vehicle, we can obtain or infer valuable vehicle information such as pose, position, intent, and trajectory. This vehicle information can provide great benefits to perception, localization, and planning systems for autonomous driving.

In one example aspect, a system includes: a data processor; and an autonomous vehicle wheel detection system executable by the data processor, the autonomous vehicle wheel detection system configured to perform autonomous vehicle wheel detection operations. The autonomous vehicle wheel detection operation is configured to: receive training image data from a training image data collection system; obtain ground truth data corresponding to the training image data; perform a training phase to train one or more classifiers to process the data in the training image data to detect vehicle wheel objects in the images in the training image data; receive operational image data from an image data collection system associated with the autonomous vehicle; and perform an operational phase that includes one or more of the trained A classifier is applied to extract wheel object data.

In another aspect, a method is disclosed for: obtaining ground truth data corresponding to training image data; performing a training phase to train one or more classifiers to process images in the training image data to detecting vehicle wheel objects in images in the training image data; receiving operational image data from an image data collection system associated with the autonomous vehicle; and performing an operational phase that includes applying the trained one or more classifiers to Vehicle wheel objects are extracted from the operation image data, and vehicle wheel object data is generated.

In another aspect, a non-transitory machine may employ a storage medium with instructions that, when executed by the machine, cause the machine to: receive training image data from a training image data collection system; obtain ground truth data corresponding to the training image data; performing a training phase to train one or more classifiers to process images in the training image data to detect vehicle wheel objects in the images in the training image data; receiving operational image data from an image data collection system associated with the autonomous vehicle and performing an operational phase comprising applying the trained one or more classifiers to extract vehicle wheel objects from operational image data and generating vehicle wheel object data.

These and other aspects are disclosed herein.

Description of drawings

In the figures of the accompanying drawings, various embodiments are illustrated by way of example and not by way of limitation, wherein:

1 illustrates a block diagram of an example ecosystem in which an in-vehicle image processing module of an example embodiment may be implemented;

Figure 2 illustrates the image acquired from the camera (upper image) and its corresponding wheel annotation results (lower image);

FIG. 3 illustrates an offline training phase (first phase) used to configure or train an autonomous vehicle wheel detection system and a classifier therein in an example embodiment;

Figure 4 (bottom half image) illustrates an example ground truth label map that may be used to train a segmentation model according to example embodiments; Figure 4 (top half image) also illustrates the original example image combined with ground truth hybrid visualization;

5 illustrates a second stage of operational use or simulated use of the autonomous vehicle wheel detection system in an example embodiment;

Figure 6 (bottom half of the image) illustrates an example predicted label map using the trained segmentation model using the example image of Figure 4 and other training images to train the segmentation model; Figure 6 (top half of the image) also illustrates A hybrid visualization of the original example image combined with the prediction results;

Figure 7 (bottom image) illustrates another example ground truth label map that may be used to train a segmentation model according to an example embodiment; Figure 7 (top image) also illustrates the original example image with ground truth Combined hybrid visualization;

Figure 8 (bottom half of the image) illustrates an example predicted label map using the trained segmentation model using the example image of Figure 7 as well as other training images; Figure 8 (top half of the image) also illustrates A hybrid visualization of the original example images combined with the predicted results.

Figure 9 (bottom image) illustrates yet another example ground truth label map that may be used to train a segmentation model according to example embodiments; Figure 9 (top image) also illustrates the original example image with ground truth Combined hybrid visualization;

Figure 10 (bottom half of the image) illustrates an example predicted label map using a trained segmentation model trained with the example image of Figure 9 and other training images; Figure 10 (top half of the image) also illustrates A hybrid visualization of the original example images combined with the predicted results.

11 is a process flow diagram illustrating an example embodiment of a system and method for vehicle wheel detection; and

12 shows an illustration of a machine in the form of an example of a computer system within which a set of instructions, when executed, can cause the machine to perform any one or more of the methods discussed herein.

Where possible, the same reference numbers have been used to refer to the same elements that are common to the figures. It is contemplated that elements disclosed in one embodiment can be used to advantage in other embodiments without specific recitation.

Detailed ways

In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of various embodiments. It is to be understood that other embodiments may be utilized and structural changes may be made without departing from the scope of the disclosed subject matter. Any combination of the following features and elements is contemplated to implement and practice the present disclosure.

In this specification, common or similar features may be denoted by common reference numerals. As used herein, "exemplary" may indicate an example, implementation, or aspect, and should not be construed as limiting or indicating a preference or preferred implementation.

Currently, autonomous vehicles face several technical limitations that hinder their interaction and adaptability with the real world.

Current autonomous vehicle technology is often reactive—that is, decisions are based on current conditions or states. For example, autonomous vehicles can be programmed to make an emergency stop when an object is detected in the middle of the road. However, current autonomous vehicle technology has a limited ability to determine the likelihood of being hit from behind or the likelihood of a chain collision on the highway due to rapid braking.

Furthermore, current technology does not know how to make real-world judgment calls. Various objects on the road require different judgments based on the environment and current conditions. For example, turning to avoid a cardboard box poses an unnecessary danger to autonomous vehicles and other drivers. Turning, on the other hand, is a must to avoid hitting someone in the middle of the road. The judgment call changes based on road conditions, the trajectory of other vehicles, the speed of the ego vehicle, and the speed and direction of the other vehicles.

Additionally, current technology is not suitable for environments with other human drivers. When reacting to changes in traffic patterns, autonomous vehicles must be able to predict the behavior of other drivers or pedestrians. One goal of accepting autonomous vehicles in real life is to behave in a way that allows for appropriate interaction with other human drivers and vehicles. Human drivers typically make traffic decisions based on predictable human responses that do not necessarily favor machine rules. In other words, there is a technical problem with autonomous vehicles: current autonomous vehicles behave too much like machines. This behavior can lead to accidents because other drivers cannot anticipate certain actions performed by the autonomous vehicle.

In addition to other solutions, this article provides technical solutions to the above problems. For example, efficient systems for detecting and analyzing vehicle wheels are used to generate vehicle wheel object data, and vehicle wheel based image data collection systems. Analyzing vehicle wheels makes ego vehicle trajectory decisions and other autonomous vehicle judgments more human-like, reducing problems for passengers, surrounding vehicles, and pedestrians. Accordingly, the present disclosure provides, among other solutions, an efficient system for detecting and analyzing vehicle wheels as a solution to the above problems.

As described in various example embodiments, systems and methods for vehicle wheel detection are described herein. The example embodiments disclosed herein may be used in the context of an in-vehicle control system 150 in the vehicle ecosystem 101 . In one example embodiment, the onboard control system 150 with the image processing module 200 residing in the vehicle 105 may be configured as the architecture and ecosystem 101 illustrated in FIG. 1 . However, it will be apparent to those of ordinary skill in the art that the image processing module 200 described and claimed herein may also be implemented, configured, and used in various other applications and systems.

Referring now to FIG. 1 , a block diagram illustrates an exemplary ecosystem 101 in which in-vehicle control system 150 and image processing module 200 in an exemplary embodiment may be implemented. These components are described in more detail below. Ecosystem 101 includes various systems and components that can generate and/or deliver one or more sources of information/data and related services to onboard control system 150 and image processing module 200, which The processing module 200 may be installed in the vehicle 105 . For example, a camera installed in vehicle 105 as one of the devices of vehicle subsystem 140 may generate images and timing data that may be received by onboard control system 150 . The onboard control system 150 and the image processing module 200 executing therein may receive this image and timing data input. As described in more detail below, the image processing module 200 may process the image input and extract object features that may be used by the autonomous vehicle control subsystem as another subsystem of the vehicle subsystem 140 . For example, an autonomous vehicle control subsystem can use real-time extracted object features to safely and efficiently navigate and control the vehicle 105 through a real-world driving environment, while avoiding obstacles and safely controlling the vehicle.

In the example embodiments described herein, the onboard control system 150 may be in data communication with a plurality of vehicle subsystems 140 , all of which may reside in the user's vehicle 105 . A vehicle subsystem interface 141 is provided to facilitate data communication between the onboard control system 150 and a plurality of vehicle subsystems 140 . Onboard control system 150 may be configured to include data processor 171 to execute image processing module 200 for processing image data received from one or more vehicle subsystems 140 . Data processor 171 may be combined with data storage device 172 as part of computing system 170 in vehicle control system 150 . Data storage device 172 may be used to store data, processing parameters, and data processing instructions. A processing module interface 165 may be provided to facilitate data communication between the data processor 171 and the image processing module 200 . In various example embodiments, multiple processing modules configured similarly to image processing module 200 may be provided for execution by data processor 171 . As shown by the dashed line in FIG. 1 , the image processing module 200 may be integrated into the vehicle-mounted control system 150 , optionally downloaded to the vehicle-mounted control system 150 , or deployed separately from the vehicle-mounted control system 150 .

The in-vehicle control system 150 may be configured to receive data from the wide area network 120 and network resources 122 connected thereto, or to transmit data to the wide area network 120 and network resources 122 connected thereto. In-vehicle network enabled device 130 and/or user mobile device 132 may be used to communicate via network 120 . The network-enabled device 131 may be used by the in-vehicle control system 150 to facilitate data communication between the in-vehicle control system 150 and the network 120 via the in-vehicle network-enabled device 130 . Similarly, user mobile device interface 133 may be used by in-vehicle control system 150 to facilitate data communication between in-vehicle control system 150 and network 120 via user mobile device 132 . In this manner, the in-vehicle control system 150 may gain real-time access to the network resources 122 via the network 120 . Network resources 122 may be used to obtain processing modules to be executed by data processor 171, data content for training internal neural networks, system parameters, or other data.

Ecosystem 101 may include wide area data network 120 . The network 120 represents one or more conventional wide area data networks, such as the Internet, cellular telephone networks, satellite networks, pager networks, wireless broadcast networks, gaming networks, WiFi networks, peer-to-peer networks, Voice over IP (VoIP) networks, and the like. One or more of these networks 120 may be used to connect user or client systems with network resources 122 (such as websites, servers, central control sites, etc.). The network resources 122 may generate and/or distribute data, which may be received in the vehicle 105 via the in-vehicle network-enabled device 130 or the user mobile device 132 . The network resource 122 may also host a network cloud service that may support functionality used to compute or assist in processing image input or image input analysis. Antennas may be used to connect onboard control system 150 and image processing module 200 to data network 120 via cellular, satellite, radio, or other conventional signal receiving mechanisms. Such cellular data networks are currently available (eg Verizon ^™ , AT&T ^™ , T-Mobile ^™ , etc.). Such satellite-based data or content networks are also currently available (eg SiriusXM ^™ , HughesNet ^™ , etc.). Conventional broadcast networks (such as AM/FM radio networks, pager networks, UHF networks, gaming networks, WiFi networks, peer-to-peer networks, Voice over IP (VoIP) networks, etc.) are also well known. Accordingly, as described in more detail below, the in-vehicle control system 150 and the image processing module 200 may receive network-based data or content via the in-vehicle network-enabled device interface 131, which may be used to communicate with The in-vehicle network enabled device 130 is connected to the network 120 . In this manner, the in-vehicle control system 150 and image processing module 200 can support various networkable in-vehicle devices and systems from within the vehicle 105 .

As shown in FIG. 1 , onboard control system 150 and image processing module 200 may also receive data, image processing control parameters, and training content from user mobile devices 132 , which may be located within or near vehicle 105 . User mobile device 132 may represent standard mobile devices such as cellular phones, smart phones, personal digital assistants (PDAs), MP3 players, tablet computing devices (eg, iPad ^™ ), laptop computers, CD players, and may be in-vehicle Control system 150 and image processing module 200 generate, receive and/or communicate data, image processing control parameters and other mobile devices with content. As shown in FIG. 1 , the mobile device 132 may also be in data communication with the network cloud 120 . Mobile devices 132 may obtain data and content via network 120 from mobile devices 132 their own internal memory components or from network resources 122 . Additionally, the mobile devices 132 themselves may include GPS data receivers, accelerometers, WiFi triangulation, or other geographic location sensors or components in the mobile device that may be used to determine the user's real-time geographic location (via the mobile device) at any time. In any event, onboard control system 150 and image processing module 200 may receive data from mobile device 132 as shown in FIG. 1 .

Still referring to FIG. 1 , an example embodiment of the ecosystem 101 may include a vehicle operating subsystem 140 . For embodiments implemented in vehicle 105, many standard vehicles include operating subsystems (such as electronic control units (ECUs) that support monitoring/control subsystems for the engine, brakes, transmission, electrical system, emissions system, interior environment, etc. )). For example, data signals communicated from the vehicle operating subsystem 140 (eg, the ECU of the vehicle 105 ) to the onboard control system 150 via the vehicle subsystem interface 141 may include information about the status of one or more components or subsystems of the vehicle 105 . In particular, data signals that may be communicated from the vehicle operating subsystem 140 to the controller area network (CAN) bus of the vehicle 105 may be received and processed by the onboard control system 150 via the vehicle subsystem interface 141 . Embodiments of the systems and methods described herein may be used with substantially any mechanized system (including, but not limited to, industrial equipment, boats, trucks, machinery, or automobiles) using a CAN bus or similar data communication bus as defined herein; Thus, the term "vehicle" as used herein may include any such mechanized system. Embodiments of the systems and methods described herein may also be used with any system that employs some form of network data communication; however, such network communication is not required.

Still referring to FIG. 1 , the example embodiment of the ecosystem 101 and the vehicle operating subsystems 140 therein may include various vehicle subsystems that support the operation of the vehicle 105 . Typically, for example, the vehicle 105 may take the form of a car, truck, motorcycle, bus, boat, airplane, helicopter, lawn mower, bulldozer, snowmobile, aircraft, recreational vehicle, amusement park vehicle, farm equipment, construction equipment , trams, golf carts, trains and carts. Other vehicles are also possible. The vehicle 105 may be configured to operate fully or partially in an autonomous mode. For example, the vehicle 105 may control itself in an autonomous mode and may be operable to determine the current state of the vehicle and its environment, determine the predicted behavior of at least one other vehicle in the environment, determine that the predicted behavior may be performed with the at least one other vehicle The likelihood corresponds to a confidence level, and the vehicle 105 is controlled based on the determined information. When in autonomous mode, the vehicle 105 may be configured to operate without human interaction.

Vehicle 105 may include various vehicle subsystems, such as vehicle drive subsystem 142 , vehicle sensor subsystem 144 , vehicle control subsystem 146 , and occupant interface subsystem 148 . As mentioned above, the vehicle 105 may also include the onboard control system 150 , the computing system 170 and the image processing module 200 . The vehicle 105 may include more or fewer subsystems, and each subsystem may include multiple elements. Further, each of the subsystems and elements of the vehicle 105 may be interconnected. Accordingly, one or more of the described functions of the vehicle 105 may be divided into additional functional or physical components, or combined into fewer functional or physical components. In some other examples, additional functional and physical components may be added to the example illustrated by FIG. 1 . The vehicle drive subsystem 142 may include components operable to provide powered motion for the vehicle 105 . In an example embodiment, the vehicle drive subsystem 142 may include an engine or electric motor, wheels/tires, a transmission, electrical subsystems, and a power source. The engine or electric motor may be an internal combustion engine, an electric motor, a steam engine, a fuel cell engine, a propane engine, or any combination of other types of engines or electric motors. In some example embodiments, the engine may be configured to convert the power source into mechanical energy. In some example embodiments, the vehicle drive subsystem 142 may include various types of engines or electric motors. For example, a gas-electric hybrid vehicle may include a gasoline engine and an electric motor. Other examples are possible. The wheels of the vehicle 105 may be standard tires. The wheels of the vehicle 105 may be configured in various forms, including, for example, a unicycle, bicycle, tricycle, or four-wheel form (such as on a car or truck). Other wheel geometries are possible, such as those including six or more wheels. Any combination of wheels of the vehicle 105 may be operable to rotate differently relative to the other wheels. A wheel may represent at least one wheel fixedly attached to the transmission and at least one tire coupled to a rim of the wheel, which rim may contact a drive surface. The wheel may comprise a combination of metal and rubber or another combination of materials. The transmission may include elements operable to transmit mechanical power from the engine to the wheels. To this end, the transmission may include a gearbox, clutches, differentials and driveshafts. The transmission may also include other elements. The drive shaft may include one or more axles that may be coupled to one or more wheels. The electrical system may include elements operable to transmit and control electrical signals in the vehicle 105 . These electrical signals may be used to activate lights, servos, motors, and other electrically driven or controlled devices of the vehicle 105 . A power source may refer to an energy source that can fully or partially power an engine or electric motor. That is, the engine or electric motor may be configured to convert the power source into mechanical energy. Examples of power sources include: gasoline, diesel, other petroleum-based fuels, propane, other compressed gas-based fuels, ethanol, fuel cells, solar panels, batteries, and other electrical power sources. Additionally or alternatively, the power source may include any combination of fuel tanks, batteries, capacitors, or flywheels. The power source may also provide energy to other subsystems of the vehicle 105 .

The vehicle sensor subsystem 144 may include several sensors configured to sense information about the environment or conditions of the vehicle 105 . For example, the vehicle sensor subsystem 144 may include an inertial measurement unit (IMU), a global positioning system (GPS) transceiver, a RADAR unit, a laser rangefinder/LIDAR unit, and one or more cameras or image capture devices. The vehicle sensor subsystem 144 may also include sensors configured to monitor internal systems of the vehicle 105 (eg, O2 monitor, fuel gauge, engine oil temperature). Other sensors are also possible. One or more of the sensors included in the vehicle sensor subsystem 144 may be configured to be individually or collectively actuated to modify the position, orientation, or both of the one or more sensors.

The IMU may include any combination of sensors (eg, accelerometers and gyroscopes) configured to sense changes in position and orientation of the vehicle 105 based on inertial acceleration. The GPS transceiver may be any sensor configured to estimate the geographic location of the vehicle 105 . To this end, the GPS transceiver may include a receiver/transmitter operable to provide information about the position of the vehicle 105 relative to the earth. A RADAR unit may represent a system that utilizes radio signals to sense objects within the local environment of the vehicle 105 . In some embodiments, in addition to sensing objects, the RADAR unit may be configured to sense the speed and heading of objects in the vicinity of the vehicle 105 . A laser rangefinder or LIDAR unit may be any sensor configured to use a laser to sense objects in the environment in which the vehicle 105 is located. In an example embodiment, a laser rangefinder/LIDAR unit may include one or more laser sources, laser scanners, and one or more detectors, among other system components. The laser rangefinder/LIDAR unit may be configured to operate in coherent (eg using heterodyne detection) or incoherent detection mode. The cameras may include one or more devices configured to capture multiple images of the environment of the vehicle 105 . The camera can be a still image camera or a motion video camera.

The vehicle control subsystem 146 may be configured to control the operation of the vehicle 105 and its components. Accordingly, the vehicle control subsystem 146 may include various elements such as steering units, dampers, braking units, navigation units, and autonomous control units.

The steering unit may represent any combination of mechanisms operable to adjust the heading of the vehicle 105 . The damper may be configured to control, for example, the operating speed of the engine, and in turn, the speed of the vehicle 105 . The braking unit may include any combination of mechanisms configured to decelerate the vehicle 105 . The braking unit can use friction to slow down the wheel in a standard way. In other embodiments, the braking unit may convert the kinetic energy of the wheels into electrical current. The braking unit may also take other forms. The navigation unit may be any system configured to determine the driving path or route of the vehicle 105 . The navigation unit may also be configured to dynamically update the driving path while the vehicle 105 is operating. In some embodiments, the navigation unit may be configured to combine data from the image processing module 200 , the GPS transceiver, and one or more predetermined maps to determine the driving path of the vehicle 105 . The autonomous control unit may represent a control system configured to identify, evaluate, and avoid or otherwise overcome potential obstacles in the environment of the vehicle 105 . Typically, the autonomous control unit may be configured to control the operation of the vehicle 105 without a driver or to provide driver assistance while controlling the vehicle 105 . In some embodiments, the autonomous control unit may be configured to combine data from the image processing module 200 , GPS transceiver, RADAR, LIDAR, cameras, and other vehicle subsystems to determine the driving path or trajectory of the vehicle 105 . Additionally or alternatively, the vehicle control subsystem 146 may include components other than those shown and described.

在一些实施例中，无线通信系统可以直接与设备进行通信，例如使用红外链路、

或

在本公开的语境中，其他无线协议(诸如各种车辆通信系统)是可能的。例如，无线通信系统可以包括一个或多个专用短距离通信(DSRC)设备，该一个或多个专用短距离通信(DSRC)设备可以包括车辆和/或路边站之间的公共或私有数据通信。The occupant interface subsystem 148 may be configured to allow interaction between the vehicle 105 and external sensors, other vehicles, other computer systems, and/or an occupant or user of the vehicle 105 . For example, the occupant interface subsystem 148 may include standard visual display devices (eg, plasma displays, liquid crystal displays (LCDs), touch screen displays, heads-up displays, etc.), speakers or other audio output devices, microphones or other audio input devices, navigation interfaces, and An interface for controlling the interior environment of the vehicle 105 (eg, temperature, fans, etc.). In an example embodiment, the occupant interface subsystem 148 may provide, for example, a means for a user/occupant of the vehicle 105 to interact with other vehicle subsystems. The visual display device may provide information to a user of the vehicle 105 . The user interface device may also be operable to accept input from a user via a touch screen. The touch screen may be configured to sense at least one of the position and movement of the user's finger via capacitive sensing, resistive sensing or surface acoustic wave processes, among other possibilities. The touchscreen may be capable of sensing finger movement in a direction parallel to or planar to the touchscreen surface, in a direction perpendicular to the touchscreen surface, or both, and may also be capable of sensing level of stress. The touch screen may be formed of one or more translucent or transparent insulating layers and one or more translucent or transparent conductive layers. Touchscreens can also take other forms. In other examples, the occupant interface subsystem 148 may provide the vehicle 105 with means for communicating with devices within its environment. The microphone may be configured to receive audio (eg, voice commands or other audio input) from the user of the vehicle 105 . Similarly, speakers may be configured to output audio to a user of vehicle 105 . In one example embodiment, the occupant interface subsystem 148 may be configured to wirelessly communicate with one or more devices, either directly or via a communication network. For example, the wireless communication system may use 3G cellular communication (such as CDMA, EVDO, GSM/GPRS) or 4G cellular communication (such as WiMAX or LTE). Alternatively, the wireless communication system may communicate with a wireless local area network (WLAN), eg using

In some embodiments, the wireless communication system may communicate directly with the device, such as using an infrared link,

or

In the context of this disclosure, other wireless protocols, such as various vehicle communication systems, are possible. For example, a wireless communication system may include one or more dedicated short-range communication (DSRC) devices that may include public or private data communications between vehicles and/or roadside stations .

Many or all of the functions of the vehicle 105 may be controlled by the computing system 170 . Computing system 170 may include at least one data processor 171 (the at least one data processor 171 may include at least one microprocessor) that executes processing instructions stored in a non-transitory computer-readable medium, such as data storage device 172 . Computing system 170 may also represent multiple computing devices that may be used to control individual components or subsystems of vehicle 105 in a distributed fashion. In some embodiments, the data storage device 172 may include processing instructions (eg, program logic) executable by the data processor 171 to perform various functions of the vehicle 105 , including those described herein in connection with the figures. Data storage device 172 may also include other instructions including instructions to transmit data to one or more of vehicle drive subsystem 142 , vehicle sensor subsystem 144 , vehicle control subsystem 146 , occupant interface subsystem 148 , Receive data from, interact with, or control the one or more subsystems.

In addition to processing instructions, data storage device 172 may store data such as image processing parameters, training data, road maps and route information, and other information. The vehicle 105 and computing system 170 may use such information during operation of the vehicle 105 in autonomous, semi-autonomous, and/or manual modes.

The vehicle 105 may include a user interface for providing information to or receiving information from a user or occupant of the vehicle 105 . The user interface may control or enable control of the content and layout of interactive images that may be displayed on the display device. Further, the user interface may include one or more input/output devices within the crew interface subsystem 148, such as display devices, speakers, microphones, or wireless communication systems.

Computing system 170 may control functions of vehicle 105 based on inputs received from various vehicle subsystems (eg, vehicle drive subsystem 142 , vehicle sensor subsystem 144 , and vehicle control subsystem 146 ) and from occupant interface subsystem 148 . For example, the computing system 170 may use input from the vehicle control subsystem 146 to control the steering unit to avoid obstacles detected by the vehicle sensor subsystem 144 and the image processing module 200, move in a controlled manner, or follow based on the image processing The path or trajectory of the output generated by the module 200 . In an example embodiment, the computing system 170 may be operable to provide control over many aspects of the vehicle 105 and its subsystems.

Although FIG. 1 shows various components of vehicle 105 (eg, vehicle subsystem 140 , computing system 170 , data storage device 172 , and image processing module 200 ) as being integrated into vehicle 105 , one or more of these components Components may be installed separately from or associated with the vehicle 105 . For example, the data storage device 172 may exist partially or completely separate from the vehicle 105 . Accordingly, the vehicle 105 may be provided in the form of equipment elements that may be located separately or together. The device elements that make up the vehicle 105 may be communicatively coupled together in a wired or wireless manner.

Additionally, the onboard control system 150 as described above may obtain other data and/or content (referred to herein as auxiliary data) from local and/or remote sources. As described herein, auxiliary data may be used to enhance, modify, or train the operation of image processing module 200 based on various factors, including: the environment in which the user is operating the vehicle (eg, location of the vehicle, designated destination , direction of travel, speed, time of day, status of the vehicle, etc.) and various other data available from these various sources (local and remote).

In certain embodiments, the onboard control system 150 and the image processing module 200 may be implemented as onboard components of the vehicle 105 . In various example embodiments, the onboard control system 150 and the image processing module 200 in data communication therewith may be implemented as integrated components or as separate components. In an example embodiment, software components of the in-vehicle control system 150 and/or the image processing module 200 may be dynamically upgraded, modified and/or enhanced using data connections to the mobile device 132 and/or network resources 122 via the network 120 . The in-vehicle control system 150 may periodically query the mobile device 132 or network resource 122 for updates, or may push updates to the in-vehicle control system 150 .

System and method for vehicle wheel detection

In various example embodiments disclosed herein, a system and method for vehicle wheel detection using image segmentation is provided. In an example embodiment, the system includes three components: 1) data collection and annotation, 2) model training using deep convolutional neural networks, and 3) real-time model inference. To take advantage of state-of-the-art deep learning models and training strategies, the various example embodiments disclosed herein formulate the wheel detection problem as a two-class segmentation task and train on deep neural networks that excel at multi-class semantic segmentation problems. When the system obtains an accurate segmentation analysis of wheel features for a given vehicle, the system can obtain or infer valuable vehicle information such as pose, position, intent, and trajectory. This vehicle information can provide great benefits to perception, localization, and planning systems for autonomous driving. In the various example embodiments described herein, components of a vehicle wheel detection system are described below.

Data collection and annotation

In various example embodiments, the wheel segmentation problem can be defined in different ways, such as 1) a bounding box regression problem that only requires the locations of the four corners of a rectangular bounding box; 2) a problem that requires pixel-level labeling of the wheel region A semantic segmentation problem or 3) an instance segmentation problem that requires assigning a different instance identifier number (ID) to each individual wheel. The example embodiments described herein provide an efficient and suitable annotation paradigm for all possible tasks. Since vehicle wheels typically share similar visible shapes, such as circles or ellipses, the processing performed by the example embodiment transforms the vehicle wheel annotation task into a contour annotation task. That is, example embodiments may be configured to identify and render contour lines or contours around each vehicle wheel detected in the input image. From vehicle wheel profiles, example embodiments may be configured to generate corresponding bounding boxes by extracting extrema for all four directions (up, down, left, right) for each wheel profile and generating corresponding bounding boxes from these Detect bounding boxes. Additionally, example embodiments may be configured to obtain semantic segmentation labels corresponding to vehicle wheel contours by filling in interior regions defined by wheel contours. Finally, example embodiments may also obtain vehicle wheel instance labels by counting the number of closed vehicle wheel profiles and generating a different instance identifier number (ID) for each instance of the vehicle wheel detected in the input image. Accordingly, example embodiments may generate various information based on vehicle wheel profiles identified in input images. Important: Contouring vehicle wheels is very easy for human labelers, helping us efficiently build large machine learning training datasets. Accordingly, machine learning techniques may be used to enable example embodiments to collect raw training image data and train machine learning models to identify and annotate vehicle wheel contours in input images. Example embodiments may then generate the various information described above based on the identified vehicle wheel profiles. A sample raw input image and vehicle wheel contour labeling results produced by an example embodiment are shown in FIG. 2 .

Figure 2 illustrates the raw input image acquired from the camera of the autonomous vehicle (Figure 2, upper image) and the corresponding vehicle wheel outline marking or annotation results produced by an example embodiment (Figure 2, lower image in opposite colors) ). The dashed arrows shown in Figure 2 were added to highlight the association between each instance of the vehicle wheel outline annotation and the portion of the original input image where the vehicle wheel outline annotation was derived. As described in more detail below, the trained machine learning model can be used to generate vehicle wheel outline annotations from raw input images. Such contour-level vehicle wheel annotations, as implemented by example embodiments disclosed herein, provide several important benefits, including allowing for the transformation of detected vehicle wheel object information into any desired format.

model training

In example embodiments described herein, supervised learning methods may be used to classify objects, object features, and object relationships captured in a set of input images. Supervised learning methods include the process of training a classifier or model using a set of training data or test data in an offline training phase. Example embodiments may train one or more machine learning classifiers on many static training images by requiring predefined features and manually annotated labels for each object (eg, vehicle wheel) in the input image. Additionally, example embodiments may train machine learning classifiers on sequences of training images. After the training phase, the trained machine learning classifier can be used in the second phase (operation or inference phase) to receive real-time images and effectively and efficiently detect the wheel features of each wheel in the received images . The training and operational use of machine learning classifiers in example embodiments are described in more detail below.

Referring now to FIG. 3 , example embodiments disclosed herein may be used in the context of an autonomous vehicle wheel detection system 210 for an autonomous vehicle. As described above, the autonomous vehicle wheel detection system 210 may be included in or executed by the image processing module 200 as described above. The autonomous vehicle wheel detection system 210 may include one or more vehicle wheel object contour classifiers 211, which may correspond to the machine learning classifiers described herein. Other types of classifiers or models can be used equivalently. Figure 3 illustrates the offline training phase (first phase) used to configure or train the autonomous in an example embodiment based on the training image data collection system 201 representing the ground truth and the manual annotation data collection system 203 Vehicle wheel detection system 210 and classifier 211 therein. In an example embodiment, the training image data collection system 201 may be used to collect sensory data for training with the training image data or to configure processing parameters for the autonomous vehicle wheel detection system 210 . As described in more detail below for example embodiments, after the initial training phase, the autonomous vehicle wheel detection system 210 may be used in an operational, inference, or simulation phase (second phase) to Image feature predictions and wheel profile feature detections are generated from the received image data, and based on the training received by the autonomous vehicle wheel detection system 210 during the initial offline training phase.

Referring again to FIG. 3, the training image data collection system 201 may include an array of perceptual information collection devices or sensors, which may include image generation devices (eg, cameras), radiation stimulated emission light amplification (laser) devices, light detection and ranging ( LIDAR) equipment, global positioning system (GPS) equipment, sound navigation and ranging (sonar) equipment, radio detection and ranging (radar) equipment, etc. Perceptual information collected by information collection devices at various traffic locations may include traffic or vehicle image data, road data, environmental data, distance data from LIDAR or radar devices, and data collected from data located near a particular road (eg, the monitored location) The information of the system 201 collects other sensor information received by the device. Additionally, the data collection system 201 may include information collection devices installed in moving test vehicles that navigate through predetermined routes in environments or locations of interest. Some portions of the ground truth data may also be collected by the data collection system 201 .

To increase the size and improve the variance of the training image dataset, the data collection system 201 can collect images from wide-angle and telephoto cameras mounted on the vehicle in the following broad driving scenarios: local, highway, sunny, cloudy, urban , villages, bridges, deserts, etc. The training image dataset can be divided into a training dataset for model training and a test dataset for model evaluation.

The image data collection system 201 may collect actual images of vehicles, moving or static objects, road features, environmental features, and corresponding ground truth data in different scenarios. Different scenarios can correspond to different locations, different traffic patterns, different environmental conditions, etc. The image data and other sensory data and ground truth data collected by the data collection system 201 reflect actual real-world traffic information related to locations or routes, scenes, vehicles or objects being monitored. Using the standard capabilities of well-known data collection devices, the collected traffic and vehicle image data and other sensory or sensor data can be wirelessly transferred (or otherwise transferred) to a data processor of a standard computing system, where the data is processed On the server, the image data collection system 201 may be implemented. Alternatively, the collected traffic and vehicle image data and other sensory or sensor data may be stored in a memory device located at the monitored location or in a test vehicle, and then passed to a data processor of a standard computing system.

As shown in FIG. 3 , a manual annotation data collection system 203 is provided to apply labels to features found in training images collected by the data collection system 201 . These training images can be analyzed by human labelers or an automated process to manually define labels or classifications for each of the features identified in the training images. The manually applied data may also include object relationship information including the state of each object in the training image data frame. For example, a manual labeler can draw the outlines of vehicle wheel objects detected in a dataset of training images. Likewise, manually annotated image labels and object relationship information may represent ground truth data corresponding to training images from image data collection system 201 . These feature labels or ground truth data may be provided to the autonomous vehicle wheel detection system 210 as part of the offline training phase described in more detail below.

Traffic and vehicle image data collected or computed by the training image data collection system 201 for training, as well as other sensory or sensor data, feature label data, and ground truth data, and object or feature labels generated by the manual annotation data collection system 203 may be used , to generate training data that can be processed by the autonomous vehicle wheel detection system 210 during the offline training phase. For example, as is well known, classifiers, models, neural networks, and other machine learning systems can be trained during the training phase to produce configured outputs based on training data provided to the classifiers, models, neural networks, or other machine learning systems. As described in more detail below, the training data provided by the image data collection system 201 and the manual annotation data collection system 203 may be used to train the autonomous vehicle wheel detection system 210 and the classifier 211 therein to determine the The vehicle wheel profile feature corresponding to the identified object (eg wheel). The offline training phase of the autonomous vehicle wheel detection system 210 is described in more detail below.

Example embodiments may train and use machine learning classifiers during vehicle wheel detection. These machine learning classifiers are represented in FIG. 3 as vehicle wheel object contour classifier 211 . In an example embodiment, the vehicle wheel object contour classifier 211 may be trained using images from a training image dataset. In this manner, the vehicle wheel object contour classifier 211 can effectively and efficiently detect vehicle wheel characteristics for each vehicle from a set of input images. The training of the vehicle wheel object contour classifier 211 in an example embodiment is described in more detail below.

Referring now to Figure 4 (upper image), this figure illustrates a hybrid visualization of the original example raw training image combined with the ground truth. FIG. 4 illustrates sample training images that may be used by example embodiments to train a vehicle wheel object contour classifier 211 to process the training images. The original training image may be one of the training images provided to the autonomous vehicle wheel detection system 210 by the training image data collection system 201 as described above. Training image data from the original training images may be collected and provided to an autonomous vehicle wheel detection system 210 where features of the original training images may be extracted. Semantic segmentation or similar processes can be used for feature extraction. As is well known, feature extraction can provide pixel-level object labels and bounding boxes for each feature or object identified in image data. In many cases, the features or objects identified in the image data will correspond to vehicle wheel objects. Likewise, vehicle wheel objects in the input training images can be extracted and represented with labels and bounding boxes. The bounding box can be represented as a rectangular box whose size corresponds to the outline of the extracted vehicle wheel object. Additionally, object-level contour detection of each vehicle wheel object may also be performed using known techniques. Thus, for each received training image, the autonomous vehicle wheel detection system 210 may obtain or generate vehicle wheel object detection data represented by labels and bounding boxes as well as object-level contour detection for each vehicle wheel object instance in the training image . Referring now to FIG. 4 (lower half of the image), this figure illustrates an example ground truth label map that may be used to train a segmentation model according to example embodiments.

Since the exact shape and exact location of vehicle wheels provide more information than bounding boxes, example embodiments may employ a semantic segmentation framework for the vehicle wheel detection task, which also does not Overcomplicated. A formal definition of the problem can be described as follows:

Given a raw input RGB (red/green/blue) image I,

output a label map R with the same size as I

where the vehicle wheel pixel is marked as 1

And the background pixels are marked as 0.

Example embodiments may generate a ground truth to mitigate potential data imbalance issues by filling in the interior area defined by the vehicle wheel contours and performing dilation to obtain more positive training samples (eg, wheel objects).

Example embodiments may use a fully convolutional neural network (FCN) as a machine learning model trained for a vehicle wheel object contour detection task as described herein. The general form of FCN has been widely used for pixel-level image-to-image learning tasks. In an example embodiment, an FCN trained for a vehicle wheel object contour detection task (eg, a machine learning model) may be tailored to include semantics using dense upsampling convolution (DUC) as described in the above-cited related patent applications Segmentation and Semantic Segmentation Using Hybrid Dilated Convolution (HDC). For more complex multi-class scene parsing tasks, FCNs for vehicle wheel object contour detection tasks can be pre-trained, so the learned features can speed up the training process. Since the image background includes many more pixels than the image foreground (eg, vehicle wheels), example embodiments may use a weighted multiple logistic loss function to train a machine learning model to ensure proper training and mitigate overfitting. Example embodiments may use stochastic gradient descent (SGD) to train the entire machine learning model for enough iterations to ensure convergence.

At this point, the offline training process is complete and the parameters associated with the one or more classifiers 211 have been appropriately adjusted to enable the one or more classifiers 211 to adequately detect vehicle object wheel features corresponding to the input image data. After being trained by the offline training process as described above, one or more classifiers 211 with their appropriately adjusted parameters can be deployed in the operation, inference or simulation phase (second phase) described below in connection with FIG. 5 .

reasoning

After the FCN training has converged, example embodiments may use the pretrained FCN to perform model inference in the second or operational phase. FIG. 5 illustrates a second stage of operational or simulated use of the autonomous vehicle wheel detection system 210 in the example embodiment. As shown in FIG. 5 , the autonomous vehicle wheel detection system 210 may receive real-world operational image data (including still images and image sequences) from the image data collection system 205 . The image data collection system 205 may include an array of sensory information collection devices, sensors, and/or image generation devices on or associated with the autonomous vehicle, except that the image data collection system 205 collects real-world operational image data rather than training image data Otherwise, it is similar to the perceptual information collection device of the image data collection system 201 . As described in greater detail herein, by applying one or more trained vehicle wheel object contour classifiers 211 , autonomous vehicle wheel detection system 210 may process input real-world operational image data to generate vehicle wheel object data 220 , which Vehicle wheel object data 220 may be used by other autonomous vehicle subsystems to configure or control the operation of the autonomous vehicle. Also as described above, semantic segmentation or similar processes can be used for vehicle wheel object extraction from real world image data.

To obtain a compromise between inference speed and model accuracy, example embodiments may resize all input images to a width of 512 and a height of 288, allowing us to achieve high accuracy (recall > 0.9) while maintaining high accuracy Real-time (50HZ) performance. Examples of ground truth images and corresponding prediction results are illustrated in Figures 6-10. It can be seen that the trained models of the example embodiments under various conditions (such as different vehicle types (eg, cars, trucks, etc.), different distances (near and far), and different lighting conditions (eg, sunny days) , shade, etc.)) achieved excellent results.

Figure 6 (bottom half of the image) illustrates an example predicted label map using a trained segmentation model that was trained with the example image of Figure 4 and other training images. Figure 6 (upper image) also illustrates a hybrid visualization of the original example image combined with the predicted results.

Figure 7 (bottom image) illustrates another example ground truth label map that may be used to train a segmentation model according to example embodiments. Figure 7 (upper image) also illustrates a hybrid visualization of the original example image combined with the ground truth.

Figure 8 (bottom half of the image) illustrates an example predicted label map using a trained segmentation model trained with the example image of Figure 7 along with other training images. Figure 8 (upper image) also illustrates a hybrid visualization of the original example image combined with the predicted results.

Figure 9 (bottom image) illustrates yet another example ground truth label map that may be used to train a segmentation model according to example embodiments. Figure 9 (upper image) also illustrates a hybrid visualization of the original example image combined with the ground truth.

Figure 10 (bottom half of the image) illustrates an example predicted label map using a trained segmentation model trained with the example image of Figure 9 and other training images. Figure 10 (upper image) also illustrates a hybrid visualization of the original example image combined with the predicted results.

Using one or more trained classifiers 211, the autonomous vehicle wheel detection system 210 may process input image data to generate vehicle wheel object data 220 that may be used by other autonomous vehicle subsystems to configure or control Operation of autonomous vehicles. Accordingly, a system and method for vehicle wheel detection for autonomous vehicle control is disclosed.

Referring now to FIG. 11 , a flowchart illustrates an example embodiment of a system and method 1000 for vehicle wheel detection. The example embodiment may be configured to: receive training image data from a training image data collection system (processing block 1010); obtain ground truth data corresponding to the training image data (processing block 1020); perform a training phase to train one or more classifiers to process images in the training image data to detect vehicle wheel objects in the images in the training image data (block 1030 ); receive operational image data from an image data collection system associated with the autonomous vehicle (block 1040 ) ); and perform an operational phase that includes applying the trained classifier or classifiers to extract vehicle wheel objects from the operational image data and generate vehicle wheel object data (processing block 1050).

As used herein and unless otherwise specified, the term "mobile device" includes data signals, messages or data that can communicate with the onboard control system 150 and/or the image processing module 200 described herein for communication via any mode of data communication. Any computing or communication device that has read or write access to the content. In many cases, mobile device 132 is a hand-held portable device, such as a smart phone, mobile phone, cellular phone, tablet computer, laptop computer, display pager, radio frequency (RF) device, infrared (IR) device, global positioning device (GPS), personal digital assistants (PDAs), handheld computers, wearable computers, portable game consoles, other mobile communication and/or computing devices, or integrated devices combining one or more of the foregoing, and the like. Additionally, the mobile device 132 may be a computing device, a personal computer (PC), a multi-processor system, a microprocessor-based or programmable consumer electronic device, a network PC, a diagnostic device, provided by the vehicle 119 manufacturer or a service technician operating systems, etc., but not limited to portable devices. Mobile device 132 may receive and process data in any of a variety of data formats. Data formats may include or be configured to operate in any programming format, protocol or language, including but not limited to: JavaScript, C++, iOS, Android, and the like. As used herein and unless otherwise stated, the term "network resource" includes data signals that may communicate with the in-vehicle control system 150 and/or image processing module 200 described herein to obtain data signals communicated via any mode of inter-process or networked data communication any device, system or service that has read or write access to , messages or content. In many cases, network resource 122 is a computing platform accessible to a data network, including: client or server computers, websites, mobile devices, peer-to-peer (P2P) network nodes, and the like. Additionally, the network resource 122 may be a network application, network router, switch, bridge, gateway, diagnostic device, system operable by the vehicle 119 manufacturer or service technician or capable of executing a set of instructions (sequential or out-of-order) , the set of instructions specifies the action to be taken by the machine. Further, although only a single machine is illustrated, the term "machine" may also be understood to include individually or jointly executing a set (or sets) of instructions to perform any one or more of the methods discussed herein Any class set of machines with a method. Network resources 122 may include any of a variety of providers or processors that can transmit digital content over a network. Typically, the file format employed is Extensible Markup Language (XML), however, the various embodiments are not so limited and other file formats may be used. For example, various embodiments may support data formats other than Hypertext Markup Language (HTML)/XML or formats other than open/standard data formats. Various embodiments described herein may support any electronic file format (such as Portable Document Format (PDF), audio (eg, Moving Picture Experts Group Audio Layer 3 - MP3, etc.), video (eg MP4, etc.) any proprietary interchange format defined).

A wide area data network 120 (also referred to as a network cloud) used with network resources 122 may be configured to couple one computing or communication device with another computing or communication device. A network may be enabled to employ any form of computer-readable data or media to communicate information from one electronic device to another. Network 120 may include the Internet, such as through a universal serial bus (USB), in addition to other wide area networks (WANs), cellular telephone networks, metropolitan area networks, local area networks (LANs), other packet switched networks, circuit switched networks, direct data connections ) or an Ethernet port, other form of computer-readable medium, or any combination thereof. In addition to other wide area networks (WANs), cellular telephone networks, satellite networks, over-the-air broadcast networks, AM/FM radio networks, pager networks, UHF networks, other broadcast networks, gaming networks, WiFi networks, peer-to-peer networks, Voice over IP (VoIP) networks , Metropolitan Area Networks, Local Area Networks (LANs), other packet-switched networks, circuit-switched networks, direct data connections, the network 120 may also include the Internet, such as through a Universal Serial Bus (USB) or Ethernet port, other forms of computer read medium or any combination thereof. On an interconnected set of networks, including those based on different architectures and protocols, routers or gateways may serve as links between the networks, enabling messages to be sent between computing devices on different networks. Similarly, communication links within a network may typically include twisted pair cables, USB, Firewire, Ethernet, or coaxial cables, while communication links between networks may utilize analog or digital telephone lines, including T1, T2, T3 and T4's full or partial dedicated digital lines, Integrated Services Digital Network (ISDN), Digital Subscriber Line (DSL), wireless links including satellite links, cellular telephone links or other communications known to those of ordinary skill in the art link. In addition, remote computers and other related electronic devices may be remotely connected to the network via modems and temporary telephone links.

The network 120 may also include any of a variety of wireless sub-networks that may further overlay an independent ad hoc network or the like to provide infrastructure-oriented connectivity. Such sub-networks may include mesh networks, wireless LAN (WLAN) networks, cellular networks, and the like. The network may also include autonomous systems of terminals, gateways, routers, etc. connected by wireless radio links or wireless transceivers. These connectors can be configured to move freely and randomly and be organized arbitrarily so that the topology of the network can change rapidly. Network 120 may also employ one or more of a variety of standard wireless and/or cellular protocols or access technologies, including those set forth herein in connection with network interface 712 and network 714 depicted in the figures.

In certain embodiments, mobile device 132 and/or network resource 122 may function as a client that enables a user to access and use in-vehicle control system 150 and/or image processing module 200 to interact with one or more components of a vehicle subsystem end device. Indeed, these client devices 132 or 122 may include any computing device configured to send and receive information over a network, such as network 120 described herein. Such client devices may include mobile devices such as cellular phones, smart phones, tablet computers, display pagers, radio frequency (RF) devices, infrared (IR) devices, global positioning devices (GPS), personal digital assistants (PDAs), handheld A portable computer, a wearable computer, a gaming console, an integrated device combining one or more of the foregoing devices, and the like. Client devices may also include other computing devices, such as personal computers (PCs), multiprocessor systems, microprocessor-based or programmable consumer electronics, network PCs, and the like. Similarly, client devices can vary widely in capabilities and features. For example, a client device configured as a cell phone may have a numeric keypad and several lines of a monochrome LCD display on which only text can be displayed. In another example, a network-enabled client device may have a touch-sensitive screen, a stylus, and a color LCD display in which text and graphics may be displayed. Additionally, the network-enabled client device may include a browser application that enables the browser application to receive and send wireless application protocol messages (WAPs) and/or wired application messages, among others. In one embodiment, browser applications are enabled to employ Hypertext Markup Language (HTML), Dynamic HTML, Handheld Device Markup Language (HML), Wireless Markup Language (WML), WMLScript, JavaScript ^™ , Extensible HTML (xHTML) , Compact HTML (CHTML), etc. to display and send messages with relevant information.

The client device may also include at least one client application configured to receive content or messages from another computing device via a network transmission. Client applications may include the ability to provide and receive textual content, graphical content, video content, audio content, alerts, messages, notifications, and the like. In addition, client devices may also be configured such as via Short Message Service (SMS), Direct Messaging (eg, Twitter), email, Multimedia Messaging Service (MMS), Instant Messaging (IM), Internet Relay Chat (IRC) ), mIRC, Jabber, Enhanced Messaging Service (EMS), text messaging, intelligent messaging, over-the-air (OTA) messaging, etc. to transmit and/or receive messages to and from another computing device or the like. The client device may also include a wireless application device on which the client application is configured to enable a user of the device to wirelessly send information to or receive information from network resources via the network.

Onboard control system 150 and/or image processing module 200 may be implemented using a system that enhances the security of the execution environment, thereby increasing security and reducing the risk of onboard control system 150 and/or image processing module 200 and related services being susceptible to viruses or malware the possibility of destruction. For example, the in-vehicle control system 150 and/or the image processing module 200 may be implemented using a trusted execution environment, which may ensure that sensitive data is stored, processed, and communicated in a secure manner.

12 shows an illustration of a machine in an example form of a computing system 700 within which a set of instructions, when executed and/or processing logic when activated, may cause a machine to perform the processes described herein and/or or any one or more of the claimed methods. In alternative embodiments, the machines operate as stand-alone devices, or may be connected (eg, networked) to other machines. In a networked deployment, the machine may operate as a server or client machine in a server-client network environment, or as a peer machine in a peer-to-peer (or distributed) network environment. The machine may be a personal computer (PC), laptop computer, tablet computing system, personal digital assistant (PDA), cellular phone, smart phone, network application, set-top box (STB), network router, switch or bridge or capable of executing A set of instructions (sequential or out-of-order) or any machine that activates processing logic that specifies actions to be taken by the machine. Further, although only a single machine is illustrated, the term "machine" may also be understood to include any collection of machines that individually or jointly execute a set (or sets) of instructions or processing logic, the set (or sets) of or sets) of instructions or processing logic for performing any one or more of the methods described and/or claimed herein.

IEEE 802.1lx等。本质上，网络接口712可以实际上包括或支持任何有线和/或无线通信和数据处理机制，通过该机制，信息/数据可以经由网络714在计算系统700与另一计算或通信系统之间传送。The example computing system 700 may include a data processor 702 (eg, a system-on-a-chip (SoC), general purpose processing cores, graphics cores, and optionally other processing logic) and memory 704, which may be via a bus or other data transfer systems 706 to communicate with each other. Mobile computing system 700 and/or mobile communication system 700 may also include various input/output (I/O) devices and/or interfaces 710 , such as a touch screen display, audio jack, voice interface, and optionally, network interface 712 . In an example embodiment, network interface 712 may include one or more radio transceivers configured to interface with any one or more standard wireless and/or cellular protocols or access technologies (e.g. for cellular systems, Global System for Mobile communications (GSM), General Packet Radio Service (GPRS), Enhanced Data GSM Environment (EDGE), Wideband Code Division Multiple Access (WCDMA), LTE, CDMA2000, WLAN, wireless routers ( WR) Grid etc. Second Generation (2G), 2.5 Generation, Third Generation (3G), Fourth Generation (4G) and Future Wireless Access) compatibility. The network interface 712 may also be configured for use with various other wired and/or wireless communication protocols, including TCP/IP, UDP, SIP, SMS, RTP, WAP, CDMA, TDMA, UMTS, UWB, WiFi, WiMax,

IEEE 802.1lx, etc. Essentially, network interface 712 may include or support virtually any wired and/or wireless communication and data processing mechanism by which information/data may be transferred between computing system 700 and another computing or communication system via network 714 .

Memory 704 may represent a machine-readable medium having stored thereon one or more sets of instructions, software, firmware or other instructions embodying any one or more of the methods or functions described and/or claimed herein Processing logic (eg, logic 708). Logic 708 or a portion thereof may also reside fully or at least partially within the processor 702 during execution of the logic 708 or a portion thereof by the mobile computing and/or communication system 700 . Likewise, memory 704 and processor 702 may also constitute machine-readable media. Logic 708, or a portion thereof, may also be configured to implement at least a portion of its processing logic or logic partially in hardware. Logic 708 , or a portion thereof, may also be transmitted or received over network 714 via network interface 712 . Although a machine-readable medium in example embodiments may be a single medium, the term "machine-readable medium" should be understood to include a single non-transitory medium or multiple non-transitory media that store one or more sets of instructions (eg centralized or distributed databases and/or associated caches and computing systems). The term "machine-readable medium" may also be understood to include any non-transitory medium capable of storing, encoding, or carrying for execution by a machine and to cause the machine to perform any one or more of the various embodiments A set of instructions for a method, or capable of storing, encoding, or carrying a data structure utilized by or associated with such a set of instructions. The term "machine-readable medium" may accordingly be understood to include, but not be limited to, solid-state memory, optical media, and magnetic media.

Some embodiments described herein may be captured using the following clause-based description.

A system includes a data processor and an autonomous vehicle wheel detection system executable by the data processor, the autonomous vehicle wheel detection system configured to perform autonomous vehicle wheel detection operations. The autonomous vehicle wheel detection operation is configured to: receive training image data from a training image data collection system; obtain ground truth data corresponding to the training image data; perform a training phase to train one or more classifiers to process the data in the training image data to detect vehicle wheel objects in the images in the training image data; receive operational image data from an image data collection system associated with the autonomous vehicle; and perform an operational phase that includes one or more of the trained A classifier is applied to extract wheel object data.

The system of clause 1, wherein the training stage is configured to obtain ground truth data from a manual image annotation or labeling process.

The system according to clause 1, further configured to generate a hybrid visualization of the original image combined with the ground truth.

The system of clause 1, further configured to generate a ground truth by filling in an interior area defined by the extracted contours of the vehicle wheel objects.

The system according to clause 1, further configured to use a fully convolutional neural network (FCN) as a machine learning model.

A system according to clause 1, further configured to use a fully convolutional neural network (FCN) as a machine learning model with semantic segmentation using dense upsampling convolution (DUC) and using hybrid dilated convolution (HDC) semantic segmentation.

A system according to clause 1, configured to generate an object-level contour detection for each extracted vehicle wheel object in the operational image data.

A method is disclosed for: obtaining ground truth data corresponding to training image data; performing a training phase to train one or more classifiers to process images in the training image data to detecting vehicle wheel objects in an image; receiving operational image data from an image data collection system associated with the autonomous vehicle; and performing an operational phase that includes applying the trained one or more classifiers to extract the vehicle from the operational image data Wheel object, and generate vehicle wheel object data.

A method according to clause 8, wherein the training phase includes obtaining ground truth data from a manual image annotation or labeling process.

The method of clause 8, comprising: generating a hybrid visualization of the original image combined with the ground truth.

The method of clause 8, comprising generating a ground truth by filling in an interior area defined by the extracted contours of the vehicle wheel objects.

The method according to clause 8, comprising: using a fully convolutional neural network (FCN) as a machine learning model.

A method according to clause 8, comprising: using a fully convolutional neural network (FCN) as a machine learning model with semantic segmentation using dense upsampling convolution (DUC) and semantics using hybrid dilated convolution (HDC) segmentation.

The method of clause 8, comprising generating an object-level contour detection for each extracted vehicle wheel object in the operational image data.

A non-transitory machine-usable storage medium employing instructions that, when executed by a machine, cause the machine to: receive training image data from a training image data collection system; obtain a ground surface corresponding to the training image data live data; performing a training phase to train one or more classifiers to process images in the training image data to detect vehicle wheel objects in the images in the training image data; received from an image data collection system associated with the autonomous vehicle operating on the image data; and performing an operating phase that includes applying the trained one or more classifiers to extract vehicle wheel objects from the operating image data, and generating vehicle wheel object data.

The non-transitory machine-usable storage medium of clause 15, wherein the training stage is configured to obtain ground truth data from a manual image annotation or labeling process.

The non-transitory machine-usable storage medium according to clause 15, further configured to generate a hybrid visualization of the original image combined with the ground truth.

The non-transitory machine-usable storage medium according to clause 15, further configured to generate a ground truth by filling in an interior area defined by the extracted contours of the vehicle wheel objects.

The non-transitory machine-usable storage medium according to clause 15, further configured to use a fully convolutional neural network (FCN) as a machine learning model.

The non-transitory machine-usable storage medium of clause 15, further configured to generate an object-level contour detection for each extracted vehicle wheel object in the operational image data.

The and other embodiments, modules and functional operations disclosed herein may be implemented in digital electronic circuitry or in computer software, firmware or hardware (including the structures disclosed herein and their structural equivalents) or in them in one or more combinations. The disclosed and other embodiments may be implemented as one or more computer program products, that is, computer program instructions encoded on a computer-readable medium for execution by or to control the operation of a data processing apparatus. one or more modules. The machine-readable medium may be a machine-readable storage device, a machine-readable storage substrate, a memory device, a combination of matter that affects a machine-readable propagated signal, or a combination of one or more thereof. The term "data processing apparatus" encompasses all apparatus, devices and machines for processing data, including, for example, a programmable processor, a computer, or multiple processors or computers. In addition to hardware, the apparatus may include code that creates an execution environment for the computer program in question, such as code constituting processor firmware, protocol stacks, database management systems, operating systems, or a combination of one or more of these. A propagated signal is an artificially generated signal, such as a machine-generated electrical, optical or electromagnetic signal, which is generated to encode information for transmission to a suitable receiver device.

Computer programs (also referred to as programs, software, software applications, scripts, or code) may be written in any form of programming language, including compiled or interpreted languages, and may be deployed in any form, including as a stand-alone A program is either deployed as a module, component, subroutine, or another unit suitable for use in a computing environment. Computer programs do not necessarily correspond to files in the file system. Programs may be stored in a portion of a file that holds other programs or data (such as one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple collaborative files (such as storing one or more modules, subroutines, or part of code files). A computer program can be deployed to be executed on one computer or on multiple computers located at one site or distributed among multiple sites and interconnected by a communication network.

The processes and logic flows described herein can be performed by one or more programmable processors executing one or more computer programs to perform functions by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus can also be implemented as, special purpose logic circuitry, such as an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit), such as an FPGA (field programmable gate array). ) or ASIC (Application Specific Integrated Circuit)). Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer. In general, a processor will receive instructions and data from read-only memory or random access memory, or both. The essential elements of a computer are: a processor for executing instructions and one or more memory devices for storing instructions and data. In general, a computer will also include one or more mass storage devices (eg, magnetic, magneto-optical or optical disks) for storing data, or the computer can be operatively coupled to receive data from or transfer data from the mass storage devices Give that mass storage device or do both. However, a computer need not have such a device. Computer-readable media suitable for storage of computer program instructions and data include all forms of non-volatile memory, media, and memory devices, including, for example, semiconductor memory devices (such as EPROM, EEPROM, and flash memory devices); magnetic disks (such as internal hard disk or removable disk); magneto-optical disks; and CD-ROM disks and DVD-ROM disks. The processor and memory may be supplemented by or incorporated in special purpose logic circuitry.

Although this patent document contains many details, these should not be construed as limitations on the scope of any invention or what may be claimed, but as descriptions of features that may be specific to particular embodiments of particular inventions. Certain features that are described in this patent document in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination. Furthermore, although features may be described above as functioning in certain combinations and initially even claimed as such, in some cases one or more of the claimed combinations may be deleted from the combinations feature. And the required combination can point to a sub-combination or a variation of the sub-combination.

Similarly, although operations are shown in the figures in a particular order, this should not be construed as requiring that such operations be performed in the particular order shown or in a sequential order, or that all illustrated operations are required to be performed in order to achieve the desired result. Furthermore, the separation of various system components in the embodiments described in this patent document should not be construed as requiring such separation in all embodiments.

Only a few embodiments and examples have been described, and other embodiments, enhancements and changes can be made based on what is described and illustrated in this patent document.

The descriptions of the embodiments described herein are intended to provide a general understanding of the structure of the various embodiments, and they are not intended to serve as a complete description of all elements and features of components and systems that may utilize the structures described herein. Many other embodiments will be apparent to those of ordinary skill in the art upon reviewing the description provided above. Other embodiments may be utilized and derived, such that structural and logical substitutions and changes may be made without departing from the scope of the present disclosure. The figures herein are representative only and may not be drawn to scale. Certain scales of the graph can be exaggerated, while other scales can be minimized. Accordingly, the specification and drawings are to be regarded in an illustrative rather than a restrictive sense.

Some embodiments implement functions in two or more specific interconnected hardware modules or devices, with related control and data signals communicated between and through the modules, or as part of an application specific integrated circuit. Accordingly, the example system is applicable to software implementations, firmware implementations, and hardware implementations.

The Abstract of the Disclosure is provided to enable the reader to quickly ascertain the nature of the technical disclosure. The abstract is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. In addition, in the foregoing Detailed Description, it can be appreciated that various features are grouped together in a single embodiment for the purpose of streamlining the disclosure. This approach in the disclosure should not be construed as reflecting an intention that the claimed embodiments require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive subject matter lies in less than all features of a single disclosed embodiment. Thus, the following claims are hereby incorporated into the Detailed Description, with each claim standing on its own as a separate embodiment.

While the foregoing has been directed to embodiments of the present disclosure, other and further embodiments of the present disclosure may be devised without departing from the essential scope of the present disclosure, and the scope of the present disclosure is to be determined by the appended claims.

Claims (20)

1. A system, comprising:

a data processor; and

an autonomous vehicle wheel detection system executable by the data processor, the autonomous vehicle wheel detection system configured to perform an autonomous vehicle wheel detection operation configured to:

receiving training image data from a training image data collection system;

obtaining ground truth data corresponding to the training image data;

performing a training phase to train one or more classifiers to process images in the training image data to detect vehicle wheel objects in the images in the training image data;

receiving operational image data from an image data collection system associated with an autonomous vehicle; and

performing an operational phase comprising applying the trained one or more classifiers to extract vehicle wheel objects from the operational image data and generating vehicle wheel object data.

2. The system of claim 1, wherein the training phase is configured to obtain ground truth data from a manual image annotation or tagging process.

3. The system of claim 1, further configured to generate a blended visualization of raw images combined with the ground truth.

4. The system of claim 1, further configured to generate the ground truth by filling an interior region defined by the extracted contours of the vehicle wheel object.

5. The system of claim 1, further configured to use a fully convolutional neural network (FCN) as a machine learning model.

6. The system of claim 1, further configured to use a full convolutional neural network (FCN) as a machine learning model having semantic segmentation using Dense Upsampling Convolution (DUC) and semantic segmentation using Hybrid Dilation Convolution (HDC).

7. The system of claim 1, configured to generate an object-level contour detection for each extracted vehicle wheel object in the operational image data.

8. A method, comprising:

receiving training image data from a training image data collection system;

obtaining ground truth data corresponding to the training image data;

performing a training phase to train one or more classifiers to process images in the training image data to detect vehicle wheel objects in the images of the training image data;

receiving operational image data from an image data collection system associated with an autonomous vehicle; and

performing an operational phase comprising applying the trained one or more classifiers to extract vehicle wheel objects from the operational image data and generating vehicle wheel object data.

9. The method of claim 8, wherein the training phase comprises obtaining ground truth data from a manual image annotation or tagging process.

10. The method of claim 8, comprising: generating a blended visualization of the original image combined with the ground truth.

11. The method of claim 8, comprising: generating the ground truth by filling an interior region defined by the extracted contour of the vehicle wheel object.

12. The method of claim 8, comprising: a fully convolutional neural network (FCN) is used as the machine learning model.

13. The method of claim 8, comprising: a full convolutional neural network (FCN) is used as a machine learning model with semantic segmentation using Dense Upsampling Convolution (DUC) and semantic segmentation using Hybrid Dilation Convolution (HDC).

14. The method of claim 8, comprising: generating object-level contour detection for each extracted vehicle wheel object in the operational image data.

15. A non-transitory machine-usable storage medium embodying instructions that, when executed by a machine, cause the machine to:

receiving training image data from a training image data collection system;

obtaining ground truth data corresponding to the training image data;

performing a training phase to train one or more classifiers to process images in the training image data to detect vehicle wheel objects in the images in the training image data;

receiving operational image data from an image data collection system associated with an autonomous vehicle; and is

Performing an operational phase comprising applying the trained one or more classifiers to extract vehicle wheel objects from the operational image data and generating vehicle wheel object data.

16. The non-transitory machine-usable storage medium of claim 15, wherein the training phase is configured to obtain ground truth data from a manual image annotation or tagging process.

17. The non-transitory machine-usable storage medium of claim 15, further configured to generate a blended visualization of raw images combined with the ground truth.

18. The non-transitory machine-usable storage medium of claim 15, further configured to generate the ground truth by filling an interior region defined by the extracted contour of the vehicle wheel object.

19. The non-transitory machine-usable storage medium of claim 15, further configured to use a fully convolutional neural network (FCN) as a machine learning model.

20. The non-transitory machine-usable storage medium of claim 15, further configured to generate an object-level contour detection for each extracted vehicle wheel object in the operational image data.

Images