Vehicle testing method and computer readable storage medium

Abstract

The application discloses a vehicle testing method and a computer readable storage medium. The method is applied to a vehicle testing system, and the system comprises a target vehicle. The method comprises the following steps: acquiring a test case, wherein the test case is used to represent a functional test requirement corresponding to the target vehicle; generating a virtual test scene based on the test case, wherein the virtual test scene is used to perform a functional test on the target vehicle; generating a target video stream according to the virtual test scene, wherein the image definition of the target video stream is less than a preset definition threshold; and sending the target video stream to the target vehicle. The application solves the technical problem of low test efficiency and test accuracy of the vehicle testing method provided in the related art.

Description

Technical Field

[0001] This application relates to the fields of automotive electronics and autonomous driving testing technology, and more specifically, to a vehicle testing method and a computer-readable storage medium. Background Technology

[0002] With the development of autonomous driving technology, the image quality of forward-facing cameras in adverse weather conditions such as rain, snow, ice, and fog directly impacts vehicle safety. Water condensation on the lens cover leads to blurred images, potentially causing malfunctions in intelligent driving functions such as automatic emergency braking and lane keeping assist. While related technologies often employ passive hydrophobic coatings or simple heating wires to mitigate fogging, a systematic verification method for anti-fog heating functions is lacking. Real-world vehicle testing is heavily constrained by natural weather conditions, resulting in low scenario repeatability and poor testing efficiency. Furthermore, while traditional hardware-in-the-loop testing can construct virtual scenarios, it typically only injects idealized perception signals, failing to assess the actual effect of heating control on image recovery and the vehicle's closed-loop response.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides a vehicle testing method and a computer-readable storage medium to at least solve the technical problems of low testing efficiency and low testing accuracy in vehicle testing methods provided in the related art.

[0005] According to one aspect of the embodiments of this application, a vehicle testing method is provided. The method is applied to a vehicle testing system, which includes a target vehicle. The method includes: acquiring test cases, wherein the test cases represent functional testing requirements corresponding to the target vehicle; generating a virtual test scenario based on the test cases, wherein the virtual test scenario is used to perform functional testing on the target vehicle; generating a target video stream based on the virtual test scenario, wherein the image clarity of the target video stream is less than a preset clarity threshold; and sending the target video stream to the target vehicle.

[0006] Optionally, generating the target video stream based on the virtual test scenario includes: generating an initial video stream based on the virtual test scenario, wherein the image clarity of the initial video stream is greater than or equal to a preset clarity threshold; configuring virtual test parameters based on the virtual test scenario; and rendering the initial video stream according to the virtual test parameters to obtain the target video stream.

[0007] Optionally, rendering the initial video stream based on virtual test parameters to obtain the target video stream includes: determining the target fogging parameters based on the virtual test parameters and a preset fogging model; and rendering the initial video stream based on the target fogging parameters to obtain the target video stream.

[0008] Optionally, the system further includes: an injection board for sending the target video stream to the target vehicle, including: converting the target video stream to a different format using the injection board to obtain a target test signal; and sending the target test signal to the target vehicle.

[0009] Optionally, the vehicle control method in this application embodiment further includes: receiving operating state parameters corresponding to the target vehicle, wherein the operating state parameters include real-time pose information corresponding to the target vehicle; updating the initial pose information corresponding to the target vehicle based on the real-time pose information to obtain target pose information, wherein the initial pose information is determined based on a virtual vehicle model, and the virtual vehicle model is generated based on the attribute information corresponding to the target vehicle.

[0010] Optionally, the vehicle control method in this application embodiment further includes: analyzing and processing the target video stream and operating status data to obtain analysis results; and determining test results based on the analysis results.

[0011] According to another aspect of the embodiments of this application, another vehicle testing method is also provided. The method is applied to a vehicle testing system, which includes a testing device. The method includes: receiving a target video stream, wherein the target video stream is generated based on a virtual test scenario, the image clarity of the target video stream is less than a preset clarity threshold, and the virtual test scenario is generated based on test cases; generating vehicle control commands based on the target video stream; adjusting the operating state of the target vehicle according to the vehicle control commands to obtain operating state parameters of the target vehicle; and sending the operating state parameters of the target vehicle to the testing device.

[0012] Optionally, generating vehicle control commands based on the target video stream includes: determining the obstacle's operating state based on the target video stream; and responding to the determination based on the obstacle's operating state that the expected collision time between the obstacle and the target vehicle is less than or equal to a preset time threshold, generating a braking request so that the target vehicle performs emergency braking based on the braking request, thereby obtaining a braking result.

[0013] Optionally, the vehicle control method in this application embodiment further includes: determining the fog thickness corresponding to the image acquisition component of the target vehicle based on the target video stream, wherein the fog thickness is used to determine the fog state corresponding to the image acquisition component; controlling the heating control module in the image acquisition component to be in the on state in response to the fog thickness being greater than a preset thickness threshold; or, controlling the heating control module in the image acquisition component to be in the off state in response to the fog thickness being less than or equal to the preset thickness threshold.

[0014] According to another aspect of the embodiments of this application, a vehicle testing apparatus is also provided. The apparatus includes: an acquisition module for acquiring test cases, wherein the test cases represent functional testing requirements corresponding to a target vehicle; a first generation module for generating a virtual test scenario based on the test cases, wherein the virtual test scenario is used to perform functional testing on the target vehicle; a second generation module for generating a target video stream according to the virtual test scenario, wherein the image clarity of the target video stream is less than a preset clarity threshold; and a first sending module for sending the target video stream to the target vehicle.

[0015] Optionally, the second generation module is further configured to: generate an initial video stream based on the virtual test scenario, wherein the image clarity of the initial video stream is greater than or equal to a preset clarity threshold; configure virtual test parameters based on the virtual test scenario; and render the initial video stream according to the virtual test parameters to obtain a target video stream.

[0016] Optionally, the second generation module is further configured to: determine the target fogging parameters based on the virtual test parameters and the preset fogging model; and render the initial video stream based on the target fogging parameters to obtain the target video stream.

[0017] Optionally, the first sending module is further configured to: convert the target video stream into a format using an injection board to obtain a target test signal; and send the target test signal to the target vehicle.

[0018] Optionally, the vehicle control device in this application embodiment further includes: a first receiving module, configured to receive operating status parameters corresponding to the target vehicle, wherein the operating status parameters include real-time pose information corresponding to the target vehicle; and a first processing module, configured to update the initial pose information corresponding to the target vehicle based on the real-time pose information to obtain target pose information, wherein the initial pose information is determined based on a virtual vehicle model, and the virtual vehicle model is generated based on the attribute information corresponding to the target vehicle.

[0019] Optionally, the vehicle control device in this embodiment further includes: a second processing module for analyzing and processing the target video stream and operating status data to obtain analysis results; and a first determining module for determining test results based on the analysis results.

[0020] According to another aspect of the embodiments of this application, another vehicle testing device is also provided. The device includes: a second receiving module for receiving a target video stream, wherein the target video stream is generated based on a virtual test scenario, the image clarity of the target video stream is less than a preset clarity threshold, and the virtual test scenario is generated based on test cases; a third generating module for generating vehicle control commands based on the target video stream; a third processing module for adjusting the operating state of the target vehicle according to the vehicle control commands to obtain operating state parameters of the target vehicle; and a second sending module for sending the operating state parameters of the target vehicle to the testing device.

[0021] Optionally, the third generation module is further configured to: determine the obstacle's operating state based on the target video stream; and, in response to the determination based on the obstacle's operating state that the expected collision time between the obstacle and the target vehicle is less than or equal to a preset time threshold, generate a braking request so that the target vehicle performs emergency braking based on the braking request, thereby obtaining a braking result.

[0022] Optionally, the vehicle control device in this embodiment further includes: a second determining module, configured to determine the fog thickness corresponding to the image acquisition component of the target vehicle based on the target video stream, wherein the fog thickness is used to determine the fog state corresponding to the image acquisition component; a first controlling module, configured to control the heating control module in the image acquisition component to be in an on state in response to the fog thickness being greater than a preset thickness threshold; and a second controlling module, configured to control the heating control module in the image acquisition component to be in a off state in response to the fog thickness being less than or equal to the preset thickness threshold.

[0023] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the storage medium is located to execute the vehicle testing method of the embodiments of this application.

[0024] In this embodiment, test cases are obtained, which represent the functional testing requirements of the target vehicle. Then, a virtual test scenario is generated based on the test cases. The virtual test scenario is used to perform functional testing on the target vehicle. A target video stream is then generated based on the virtual test scenario, where the image clarity of the target video stream is less than a preset clarity threshold. Finally, the target video stream is sent to the target vehicle. This achieves the goal of realistically reproducing the visual degradation effect of severe weather under experimental conditions, thereby improving the technical effect of testing efficiency and accuracy. This solves the technical problem of low testing efficiency and low testing accuracy in the vehicle testing methods provided in related technologies. Attached Figure Description

[0025] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0026] Figure 1 This is a flowchart of a vehicle testing method according to one embodiment of this application;

[0027] Figure 2 This is a schematic diagram of a vehicle testing system according to one embodiment of this application;

[0028] Figure 3 This is a flowchart of another vehicle testing method according to one embodiment of this application;

[0029] Figure 4 This is a structural block diagram of a vehicle testing device according to one embodiment of this application;

[0030] Figure 5 This is a structural block diagram of another vehicle testing device according to one embodiment of this application. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] With the rapid development of autonomous driving technology, the forward-facing camera, as a core perception component, directly determines the safety of key functions such as automatic emergency braking and lane keeping. However, in adverse weather conditions such as rain, snow, ice, or fog, water vapor or frost easily condenses on the lens cover, leading to blurred images, loss of features, and ultimately, failure of intelligent driving functions.

[0034] Currently, verification of camera anti-fogging capabilities mainly relies on real-vehicle road tests or simple hardware-in-the-loop tests. Real-vehicle tests are greatly limited by natural weather conditions, making scenario reproduction difficult, inefficient, and costly. Traditional vehicle-in-the-loop simulation tests typically only inject idealized perception signals into the controller, lacking access to the actual camera assembly and heating actuators. This makes it impossible to simulate real fogging degradation effects or assess the actual impact of heating control strategies on image recovery and the vehicle's closed-loop response.

[0035] Therefore, the relevant vehicle testing methods still suffer from technical problems such as low testing efficiency and low testing accuracy.

[0036] According to an embodiment of this application, a method embodiment for vehicle testing is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0037] This method embodiment can be executed in an electronic device or similar computing device that includes memory and a processor. Taking operation on a computer terminal as an example, the computer terminal may include one or more processors (processors may include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), digital signal processing (DSP) chips, microcontroller units (MCUs), field-programmable gate arrays (FPGAs), neural network processors (NPUs), tensor processors (TPUs), artificial intelligence (AI) type processors, etc.) and memory for storing data. Optionally, the computer terminal may also include transmission devices, input / output devices, and display devices for communication functions. Those skilled in the art will understand that the above structural description is merely illustrative and does not limit the structure of the computer terminal. For example, the computer terminal may include more or fewer components than described above, or have a different configuration than described above.

[0038] The memory can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the vehicle testing method in this embodiment. The processor executes various functional applications and data processing by running the computer program stored in the memory, thereby implementing the aforementioned vehicle testing method. The memory may include high-speed random access memory (RAM) and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks (LANs), mobile communication networks, and combinations thereof.

[0039] The transmission device is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the mobile terminal's communication provider. In one example, the transmission device includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0040] Display devices can be, for example, touchscreen liquid crystal displays (LCDs) and touch displays (also referred to as "touchscreens" or "touch displays"). The LCD allows users to interact with the user interface of the mobile terminal. In some embodiments, the mobile terminal has a graphical user interface (GUI), which allows users to interact with the GUI through finger contact and / or gestures on a touch-sensitive surface. Optional human-computer interaction functions include: creating web pages, drawing, word processing, creating electronic documents, playing games, video conferencing, instant messaging, sending and receiving emails, call interfaces, playing digital video, playing digital music, and / or web browsing, etc. Executable instructions for performing the above human-computer interaction functions are configured / stored in one or more processor-executable computer program products or readable storage media.

[0041] Figure 1 This is a flowchart of a vehicle testing method according to one embodiment of this application. The method is applied to a vehicle testing system, which includes: a target vehicle, such as... Figure 1 As shown, the method includes the following steps:

[0042] Step S11: Obtain test cases, wherein the test cases are used to represent the functional test requirements corresponding to the target vehicle;

[0043] Step S12: Generate a virtual test scenario based on the test cases, wherein the virtual test scenario is used to perform functional testing on the target vehicle;

[0044] Step S13: Generate a target video stream based on the virtual test scenario, wherein the image clarity of the target video stream is less than a preset clarity threshold.

[0045] Step S14: Send the target video stream to the target vehicle.

[0046] The aforementioned vehicle testing system refers to the integrated hardware and software environment used for functional verification of a target vehicle. For example... Figure 2 As shown, Figure 2This is a schematic diagram of a vehicle testing system according to one embodiment of this application. The system includes a target vehicle, i.e., the actual vehicle to be tested, which includes a front-view camera assembly, a Controller Area Network (CAN) network, and vehicle actuators. The system also includes a host computer, a slave computer, a real-time system, an injection board, and an inertial navigation system. Specifically, the slave computer runs scene simulation software, which is responsible for generating virtual test scene information including virtual road environment, traffic participants, and environmental parameters, and rendering a target video stream with superimposed degradation effects based on a fogging physical model. The injection board converts the target video stream generated by the slave computer into an electrical signal recognizable by the front-view camera assembly and connects it to the video input terminal of the front-view camera assembly under test. The front-view camera assembly under test contains an image sensor and a heating control module. After receiving the target video stream, it generates vehicle control commands through internal perception algorithms and heating control logic, and sends the vehicle control commands through the vehicle CAN network. The vehicle actuators receive vehicle control commands transmitted via the vehicle's CAN network. The driver executes actual physical actions such as braking, steering, or driving to change the target vehicle's operating state and performs functional responses to adjust the vehicle's posture. The inertial navigation system (INS) measures and collects the target vehicle's real-time posture and motion state, transmitting the operating state parameters to the real-time system. The real-time system is responsible for high-speed data acquisition, hardware synchronization, and closed-loop feedback calculation. It forwards the operating state parameters provided by the INS to the scenario simulation software in the lower-level computer, which updates the position of the main vehicle in the virtual scene in real time, thus forming a complete closed-loop test environment that includes virtual scene generation, sensor signal injection, real vehicle execution, and data feedback. The upper-level computer monitors the entire test process, stores test data, configures test parameters, and displays key curves in real time to support offline playback.

[0047] The target vehicle mentioned above refers to the actual physical vehicle to be tested in this embodiment of the application. The target vehicle includes a forward-facing camera assembly, a vehicle CAN network, and actuators. The forward-facing camera assembly includes an image sensor and a lens heating film module, used to receive injected video signals and execute perception algorithms and heating control logic. The vehicle CAN network is used to transmit perception results, control commands, and vehicle status information. The actuators include a braking system, a steering system, and a drive system, used to complete actual actions according to controller commands and generate measurable motion responses.

[0048] The aforementioned perception algorithm refers to the software program deployed in the control unit within the front-view camera assembly, used for image data processing, feature extraction, and target recognition. The aforementioned heating control logic refers to the software program or control strategy within the front-view camera assembly used to manage the working state of the lens heating film module. This logic determines whether fogging has occurred on the lens surface and the level of fogging based on the analysis results of the target video stream, such as the degree of image blurring, the severity of fogging, or externally provided environmental parameters such as humidity and temperature. When image clarity is detected to be below a preset standard or environmental parameters exceed a set threshold, the heating control logic generates a heating command, controlling the heating film module to power on and increase the lens surface temperature, accelerating water vapor evaporation. When image clarity is detected to be restored or environmental parameters are detected to be improved, the heating control logic stops heating or reduces the heating power.

[0049] The test cases described above represent a dataset representing the functional testing requirements for the target vehicle. Each test case defines specific test scenario parameters, such as environmental parameters, traffic participant models, and test triggering conditions. Environmental parameters may include, but are not limited to, temperature, humidity, and wind speed; traffic participant models may include, but are not limited to, the speed, position, and trajectory of pedestrians or vehicles; and test triggering conditions may include, but are not limited to, the expected collision time threshold. Test cases can be used to clearly define the types of intelligent driving functions to be verified and the evaluation criteria.

[0050] The aforementioned functional test requirements specify the concrete functional indicators and safety requirements that the target vehicle needs to verify in a particular test scenario. These requirements define the boundary conditions of the test, including environmental conditions, dynamic scenario elements, and the expected system response. For example, environmental conditions could be a foggy state at 0°C and 95% relative humidity; dynamic scenario elements could be a vehicle speed of 30 km / h and a pedestrian crossing speed of 1.5 m / s; and the expected system response could be triggering automatic emergency braking when the estimated collision time is less than 2.5 seconds. These functional test requirements serve as the basis for generating virtual test scenarios and evaluating test results.

[0051] The aforementioned virtual test scenario represents a digital 3D environment constructed using scene simulation software, used for functional testing of a target vehicle. The virtual test scenario includes a road model, a traffic participant model, and an environmental parameter model. In the virtual test scenario, traffic participants, such as pedestrians, have preset movement trajectories and speeds. Environmental parameters define meteorological conditions, such as temperature and humidity. Based on a fogging physics model, the virtual test scenario can calculate the degree of fogging on the lens surface according to environmental parameters and perform degradation rendering on the scene image to generate visual input simulating real severe weather conditions.

[0052] The aforementioned target video stream represents a sequence of video signals generated by the simulation rendering engine based on a virtual test scenario to simulate the imaging effects of a camera under real fog or contamination conditions. The target video stream is a key data carrier connecting the virtual simulation environment with real physical hardware. Its generation process combines a fog physics model with computer graphics rendering technology, aiming to realistically reproduce visual perception input under adverse weather conditions.

[0053] The aforementioned image sharpness represents the richness of detail and the sharpness of edge contours in a video frame, and is typically used to quantify the quality of visual perception signals. In this embodiment, an image sharpness less than a preset sharpness threshold indicates that the video stream exhibits significant blurring, noise, or decreased contrast. This state corresponds to the image degradation effect caused by fogging, icing, or dirt on the lens surface in the real world.

[0054] The aforementioned preset sharpness threshold represents a quantitative standard for defining the boundary between normal imaging quality and degraded imaging quality under adverse weather conditions. This threshold is set based on a fogging physics model and the imaging characteristics of a real camera in foggy environments. When the image sharpness of the target video stream is lower than this threshold, it indicates that the video signal has simulated the optical scattering and blurring effects caused by water condensation on the lens surface. The preset sharpness threshold serves as a key indicator for determining whether the test scenario meets the "fog conditions," ensuring that the video stream injected into the actual forward-looking camera assembly can accurately reflect the impact of adverse weather on the visual perception algorithm.

[0055] For example, when obtaining test cases, this application embodiment reads pre-set test data from the test management system to determine the environmental parameters and scenario elements of this test.

[0056] For example, when generating a virtual test scenario based on test cases, the scenario simulation software instantiates a three-dimensional road model, sets the behavioral logic of traffic participants, and loads the corresponding meteorological and physical model according to the read test cases, thereby constructing a digital test environment consistent with the test requirements.

[0057] For example, a target video stream is generated based on a virtual test scenario. This can be understood as the rendering engine calculating the impact of environmental parameters on imaging based on a fog physics model when rendering virtual scene images, performing degradation processing such as blurring and scattering on clear images, and generating a simulated video signal with image clarity lower than a preset clarity threshold.

[0058] For example, when the target video stream is sent to the target vehicle, this application embodiment converts the generated target video stream into an electrical signal through a hardware injection interface and transmits it to the front-view camera assembly of the target vehicle in real time, so that the camera receives simulated severe weather visual input.

[0059] Based on the above steps S11 to S14, this embodiment of the application obtains test cases, wherein the test cases are used to represent the functional test requirements corresponding to the target vehicle, and then generates a virtual test scenario based on the test cases, wherein the virtual test scenario is used to perform functional tests on the target vehicle, and then generates a target video stream according to the virtual test scenario, wherein the image clarity corresponding to the target video stream is less than a preset clarity threshold, and finally sends the target video stream to the target vehicle, thereby achieving the purpose of realistically reproducing the visual degradation effect of severe weather under experimental conditions, thereby achieving the technical effect of improving test efficiency and test accuracy, and thus solving the technical problem of low test efficiency and test accuracy in the vehicle test methods provided in related technologies.

[0060] Optionally, in step S13, generating the target video stream based on the virtual test scenario includes:

[0061] Step S131: Generate an initial video stream based on the virtual test scenario, wherein the image clarity of the initial video stream is greater than or equal to a preset clarity threshold.

[0062] Step S132: Configure virtual test parameters based on the virtual test scenario;

[0063] Step S133: Render the initial video stream according to the virtual test parameters to obtain the target video stream.

[0064] The aforementioned initial video stream represents the original visual signal sequence directly rendered by scene simulation software based on the road model, traffic participants, and basic environmental elements in the virtual test scene.

[0065] The virtual test parameters mentioned above represent configuration data used to control the degree of image degradation, including ambient temperature, relative humidity, oncoming wind speed, and correlation coefficients in the fogging physical model. These parameters determine the severity of fogging on the lens surface.

[0066] The rendering process described above refers to the use of computer graphics algorithms to transform image pixels in the initial video stream according to virtual test parameters to simulate specific physical effects. This process typically includes operations such as convolutional blurring, contrast adjustment, noise overlay, and color shifting, aiming to transform a sharp virtual scene image into a blurred image with specific degradation characteristics.

[0067] When generating a target video stream based on a virtual test scenario, an initial video stream is first generated based on the virtual test scenario. The image clarity of the initial video stream is greater than or equal to a preset clarity threshold. For example, after loading the virtual test scenario, the scene simulation software first renders a clear, high-contrast standard 3D scene image based on geometric optics principles without applying any environmental degradation filters, generating an initial video stream. This provides a clean image data source for subsequently adding severe weather effects.

[0068] Then, virtual test parameters are configured based on the virtual test scenario. For example, the system reads the environmental conditions defined in the test case, such as ambient temperature, relative humidity, and oncoming wind speed, and inputs the above physical parameters into the fogging physical model to calculate the specific values ​​used to simulate the thickness and distribution of water fog on the lens surface, thereby determining the set of parameters required for image degradation processing.

[0069] The initial video stream is then rendered based on the virtual test parameters to obtain the target video stream. For example, in this embodiment, the calculated virtual test parameters are used to blur, reduce contrast, and distort the color of each frame in the initial video stream using an image algorithm. This simulates the scattering effect of light passing through water mist, ultimately generating a blurred video sequence with image clarity less than a preset clarity threshold, i.e., the target video stream.

[0070] For example, blurring algorithms typically employ convolution operations such as Gaussian blur, motion blur, or bokeh blur. By calculating a weighted average or integral within the pixel's neighborhood, they simulate the scattering effect of light passing through water mist, thereby reducing the spatial frequency details of the image. Contrast adjustment algorithms reduce the difference between bright and dark areas by stretching or compressing the image's histogram distribution, simulating the weakening effect of fog on light contrast. Color distortion algorithms adjust the image's hue, saturation, and brightness channels to simulate the absorption and scattering of specific wavelengths of light by water mist, resulting in color casts or fading in the image.

[0071] Based on the above steps S131 to S133, this embodiment of the application first generates a clear initial video stream, and then performs targeted image degradation rendering according to the configured environmental parameters. This achieves the technical effect of accurately reproducing the visual degradation effect of severe weather under experimental conditions, thereby providing a realistic test input for subsequently sending the target video stream to the target vehicle to verify the heating response and intelligent driving function performance of the real camera assembly under fog conditions.

[0072] Optionally, in step S133, the initial video stream is rendered according to the virtual test parameters to obtain the target video stream, including:

[0073] Step S1331: Determine the target fogging parameters based on the virtual test parameters and the preset fogging model;

[0074] Step S1332: Render the initial video stream based on the target fogging parameters to obtain the target video stream.

[0075] The aforementioned preset fogging model represents a mathematical model constructed based on the principles of physical optics. It describes the correspondence between meteorological conditions such as ambient temperature, relative humidity, and wind speed, and the thickness, distribution density, and optical scattering characteristics of water mist on the lens surface. This model transforms abstract environmental parameters into visualized image degradation parameters, and is the core basis for achieving realistic fogging effects in the embodiments of this application.

[0076] The aforementioned target fogging parameters represent a set of specific values ​​calculated by the preset fogging model based on virtual test parameters, including but not limited to blur radius, contrast attenuation coefficient, and color offset. These parameters determine the degree and form of image degradation in the initial video stream.

[0077] When rendering the initial video stream based on virtual test parameters to obtain the target video stream, the target fogging parameters are determined according to the virtual test parameters and the preset fogging model. For example, the scene simulation software reads data such as ambient temperature, relative humidity, and oncoming wind speed from the virtual test parameters, inputs them into the preset fogging model for physical calculations, and thus obtains target fogging parameters that can accurately reflect the severity of fogging on the lens surface under the current environmental conditions, providing precise control indicators for subsequent image rendering.

[0078] The initial video stream is rendered based on the target fogging parameters to obtain the target video stream. For example, in this embodiment, the determined target fogging parameters are used to perform spatial blurring, contrast compression, and color distortion processing on each frame of the initial video stream using image algorithms. This simulates the scattering effect of light passing through a fog layer, ultimately generating a blurred video sequence with image clarity lower than a preset clarity threshold, i.e., the target video stream.

[0079] Based on the above steps S1331 to S1332, this embodiment of the application determines the target fogging parameters according to the virtual test parameters and the preset fogging model, and renders the initial video stream based on the target fogging parameters. This achieves the technical effect of accurately reproducing the visual degradation effect of severe weather under experimental conditions, thereby realizing the purpose of generating a target video stream that realistically simulates fogging conditions. It provides a standardized test input for verifying the functional performance of a real forward-looking camera assembly in complex environments.

[0080] Optionally, the system further includes: an injection board, wherein in step S14, sending the target video stream to the target vehicle includes:

[0081] Step S141: Convert the target video stream to a new format using the injection board to obtain the target test signal;

[0082] Step S142: Send the target test signal to the target vehicle.

[0083] The aforementioned injection board represents a dedicated electronic device used to connect the simulation system with real sensor hardware, featuring high-speed data processing and signal interface adaptation capabilities.

[0084] The aforementioned format conversion refers to the process of converting the data structure, encoding protocol, and electrical characteristics of a digital video stream into electrical signals that conform to a specific hardware interface standard. In the embodiments of this application, this process involves converting digital video data generated by a lower-level machine based on computer graphics rendering, such as image frames in Red, Green, Blue (RGB) or Luminance, Chrominance U, Chrominance V (YUV) format, into standard video interface protocol signals supported by the front-view camera assembly, such as Mobile Industry Processor Interface (MIPI) analog signals, Low Voltage Differential Signaling (LVDS), or Composite Video Blank and Sync (CVBS) signals, through a video encoding chip or FPGA logic circuit injected into the board.

[0085] The aforementioned target test signal represents the electrical signal sequence after being processed by the injection board. This signal conforms to the input specifications of the target vehicle's front-view camera assembly in terms of electrical characteristics and communication protocol, but in terms of content, it carries image information converted from the target video stream.

[0086] When sending the target video stream to the target vehicle, this embodiment first converts the target video stream format using an injection board to obtain a target test signal. For example, the injection board receives digital video stream data output from the lower-level scene simulation software, identifies the encoding format and frame rate of the video stream, and converts it into a standard analog or digital video electrical signal, such as MIPI, LVDS, or CVBS signal, that can be recognized by the front-view camera assembly through internal hardware circuitry, thereby generating the target test signal.

[0087] The target test signal is then sent to the target vehicle. For example, the target test signal output from the injection board is connected to the video input interface of the front-view camera assembly of the target vehicle via a physical cable, so that the real front-view camera assembly can receive and decode the signal, thereby realizing the perception input of the virtual test scene at the hardware level.

[0088] Based on the above steps S141 to S142, this embodiment of the application converts the target video stream into a format by injecting a board to obtain a target test signal, and sends the target test signal to the target vehicle. This achieves the technical effect of seamlessly integrating virtual simulation data into real sensor hardware in an experimental environment, thereby realizing the purpose of injecting specific harsh visual inputs without changing the hardware structure of the real vehicle. This provides a physical connection basis for subsequent verification of the heating control and perception algorithm of the real camera assembly under fogging conditions.

[0089] Optionally, the vehicle control method in this application embodiment further includes:

[0090] Step S211: Receive the operating status parameters corresponding to the target vehicle, wherein the operating status parameters include the real-time pose information corresponding to the target vehicle.

[0091] Step S212: Update the initial pose information corresponding to the target vehicle based on the real-time pose information to obtain the target pose information. The initial pose information is determined based on the virtual vehicle model, and the virtual vehicle model is generated based on the attribute information corresponding to the target vehicle.

[0092] The above operating status parameters represent a comprehensive set of data reflecting the real-time motion of the target vehicle in the test environment, including the real-time pose information of the target vehicle.

[0093] The aforementioned real-time pose information represents the dynamic state data of the target vehicle in three-dimensional space, including its specific position coordinates, heading angle, pitch angle, roll angle, and speed, collected by the inertial navigation system or sensors.

[0094] The aforementioned initial pose information represents the vehicle's initial position and attitude parameters pre-set based on the virtual vehicle model.

[0095] The aforementioned target pose information represents the updated information reflecting the accurate position and attitude of the target vehicle in the virtual scene at the current moment.

[0096] The aforementioned virtual vehicle model represents a digital twin object generated based on the attribute information of the target vehicle, used to simulate the motion behavior of a real vehicle in scene simulation software.

[0097] The aforementioned attribute information represents data describing the physical characteristics and geometric dimensions of the target vehicle, including the vehicle's physical dimensions, structural parameters, and the installation position and attitude angle of the on-board sensors. For example, the vehicle's physical dimensions can be length, width, and height; structural parameters can be wheelbase and track width; on-board sensors can be forward-facing cameras; installation positions can be installation coordinates XYZ; and attitude angles can be installation pitch angle, yaw angle, and roll angle.

[0098] The aforementioned update process involves fusing real-time pose information acquired from the inertial navigation system with the initial pose information in a virtual vehicle model generated based on the attribute information corresponding to the target vehicle. This process corrects the spatial position and attitude of the virtual vehicle model at the current moment. Specifically, this process includes using a kinematic model, such as a bicycle model, to map dynamic data such as position coordinates, heading angle, longitudinal / lateral acceleration, and yaw rate from the real-time pose information to the coordinate system of the virtual vehicle model through integration or filtering algorithms. This eliminates accumulated errors and synchronizes the pose state of the virtual environment with that of the real environment.

[0099] For example, in the embodiments of this application, when receiving the operating status parameters corresponding to the target vehicle, the real-time system obtains the real-time pose information of the target vehicle during the actual test process from the inertial navigation system or other vehicle-mounted sensors through the data acquisition interface, and receives and temporarily stores the real-time pose information as part of the operating status parameters, so as to provide data input for the subsequent state synchronization of the virtual scene.

[0100] The initial pose information corresponding to the target vehicle is updated based on real-time pose information to obtain the target pose information. The initial pose information is determined based on a virtual vehicle model, which is generated based on the attribute information corresponding to the target vehicle. For example, in a vehicle-in-the-loop simulation test application scenario, the scenario simulation software receives real-time pose information from the real-time system, compares and fuses it with the initial pose information in the virtual vehicle model generated based on the attribute information corresponding to the target vehicle, and updates the spatial position and attitude of the virtual vehicle model in the virtual scene through kinematic model calculation. This generates target pose information synchronized with the real vehicle's motion state, achieving closed-loop synchronization of pose between the virtual and real environments.

[0101] In one optional embodiment, the kinematic model represents a set of mathematical equations describing the geometric motion of a vehicle and its state changes. It is typically based on a bicycle model or a more complex multibody dynamics model, used to establish a mapping between vehicle state variables and control inputs or external observations. For example, vehicle state variables may include position, attitude, velocity, acceleration, etc., while control inputs may include vehicle speed, steering angle, etc. When solving using the kinematic model, this embodiment utilizes real-time pose information such as position coordinates, heading angle, longitudinal / lateral acceleration, and yaw rate, combined with the initial pose information of the virtual vehicle model. Through integration or filtering algorithms, such as Kalman filtering, the spatial position coordinates, heading angle, pitch angle, and roll angle of the virtual vehicle model at the current moment are calculated, thereby updating the target pose information.

[0102] Based on the above steps S21 to S22, this embodiment of the application receives the operating state parameters corresponding to the target vehicle, including the real-time pose information of the target vehicle, and updates the initial pose information of the target vehicle based on the real-time pose information to obtain the target pose information. This achieves high-precision synchronization between the virtual vehicle model and the motion state of the real vehicle, ensuring that the virtual scene can reflect the pose changes of the real vehicle in real time and accurately in the vehicle-in-the-loop simulation test, thereby improving the realism of the test environment and the reliability of the test results.

[0103] Optionally, the vehicle control method in this application embodiment further includes:

[0104] Step S221: Analyze and process the target video stream and running status data to obtain the analysis results;

[0105] Step S222: Determine the test results based on the analysis results.

[0106] The aforementioned operational status data represents the vehicle's status information during the testing process, collected and recorded by the real-time system, including video stream timestamps, CAN messages, and inertial navigation pose. The CAN messages may include target lists, braking requests, braking pressure, wheel speeds, etc., while the inertial navigation pose may include latitude and longitude, heading angle, longitudinal / lateral acceleration, yaw rate, etc.

[0107] The above analysis and processing describes the technical process of temporal alignment, feature extraction, and correlation comparison of the target video stream and runtime status data.

[0108] The above analysis results indicate that the intermediate processed data obtained after correlating and comparing the target video stream and the running status data, aligning the signal timing, and extracting features are used to reflect the correspondence between the camera's perception output and the vehicle's actual response.

[0109] The above test results represent the final evaluation conclusions based on the analysis results regarding the performance of the forward-looking camera under foggy conditions, the timeliness of the automatic emergency braking function, and the effectiveness of the anti-fog heating function.

[0110] This application embodiment analyzes and processes the target video stream and operational status data to obtain analysis results. For example, the system extracts the timestamp information of the target video stream, along with the corresponding CAN message and inertial navigation pose data, from the raw data exported from the real-time system. It uses the timestamps to precisely align the video frames with vehicle control signals, such as braking requests and wheel speed changes, and combines this with the inertial navigation pose data to analyze the vehicle's actual motion state. Furthermore, it analyzes the logical correlation and time delay between the target perceived by the camera, such as a pedestrian suddenly appearing out of nowhere, and the vehicle's actual braking action, generating analysis results that include dimensions such as perception accuracy and response delay.

[0111] The test results are determined based on the analysis results. For example, based on the above analysis results, preset evaluation index thresholds are set, such as whether braking is triggered when the expected collision time is less than 2.5 seconds, whether the braking pressure reaches the expected value, and the degree of image clarity recovery after heating. The various indicators in the analysis results are compared with the thresholds to determine whether the forward-looking camera assembly is functionally qualified in a specific fogging scenario, as well as the effectiveness of the intelligent driving algorithm strategy. Finally, a quantitative conclusion of test pass or failure and a specific performance score are output.

[0112] Based on steps S221 to S222 above, this embodiment of the application analyzes and processes the target video stream and operating status data to obtain analysis results, and determines test results based on the analysis results. This realizes closed-loop data correlation and quantitative evaluation between virtual injected signals and real vehicle execution responses in vehicle-in-the-loop simulation testing. It can objectively and accurately reflect the functional performance of the forward-looking camera under fog conditions and the differences in intelligent driving algorithm strategies, providing reliable data support for controller algorithm optimization and parameter calibration.

[0113] According to another aspect of the embodiments of this application, another vehicle testing method is also provided, which is applied to a vehicle testing system, the system including: a testing device. Figure 3 This is a flowchart of another vehicle testing method according to one embodiment of this application, such as... Figure 3 As shown, the method includes the following steps:

[0114] Step S31: Receive the target video stream, wherein the target video stream is generated based on a virtual test scenario, the image clarity of the target video stream is less than a preset clarity threshold, and the virtual test scenario is generated based on test cases.

[0115] Step S32: Generate vehicle control commands based on the target video stream;

[0116] Step S33: Adjust the operating status of the target vehicle according to the vehicle control command to obtain the operating status parameters of the target vehicle.

[0117] Step S34: Send the operating status parameters corresponding to the target vehicle to the testing device.

[0118] The aforementioned testing device refers to the host computer or real-time system component used to monitor the testing process, store data, configure test parameters, and receive operating status parameters.

[0119] The aforementioned vehicle control commands refer to control signals sent through the CAN network after the perception algorithm and heating control logic inside the forward-view camera assembly process the target video stream, such as automatic emergency braking requests or heating film start / stop commands.

[0120] The above operating status represents the real-time physical motion and state performance of the target vehicle in the test environment.

[0121] The above operating status parameters represent a comprehensive data set reflecting the real-time motion of the target vehicle in the test environment, which includes real-time pose information acquired through an inertial navigation system.

[0122] The above adjustment process refers to the process by which the vehicle actuator receives the vehicle control command, performs physical actions according to the command content to change the corresponding operating state of the target vehicle, and the inertial navigation system performs real-time measurement and data acquisition of the changed operating state.

[0123] For example, in the application scenario of vehicle-in-the-loop simulation testing, when receiving the target video stream, the video signal generated by the lower-level scene simulation software is received through the injection board. This signal is a virtual scene image generated according to preset test cases, such as ghost protrusion scenarios and specific temperature and humidity parameters, and is rendered by a fog physical model, resulting in the image clarity being reduced to below a preset clarity threshold, thereby simulating the visual input under a real foggy environment.

[0124] When generating vehicle control commands based on the target video stream, it can be understood that the actual forward-facing camera assembly receives the target video stream, processes the blurred image using its internal image sensors and perception algorithms, identifies obstacles or traffic participants in the scene, and generates corresponding control commands in conjunction with heating control logic. For example, when the perception algorithm detects a pedestrian intruding and the estimated collision time is less than 2.5 seconds, it generates an automatic emergency braking request, or generates a heating film activation command based on the fogging state. These commands are output through the vehicle's CAN network.

[0125] This application embodiment adjusts the operating state of the target vehicle according to vehicle control commands to obtain the operating state parameters of the target vehicle. For example, vehicle actuators, such as the braking system and steering system, receive vehicle control commands from the forward-facing camera assembly and execute corresponding physical actions, such as generating braking force through the wheel brakes, thereby changing the motion state of the target vehicle. Simultaneously, the inertial navigation system continuously measures the pose and motion state of the target vehicle during actual testing, collecting and processing this dynamic data as the operating state parameters of the target vehicle.

[0126] The operating status parameters corresponding to the target vehicle are sent to the testing device. For example, in this embodiment, the operating status parameters corresponding to the target vehicle, including real-time pose information and CAN messages, are transmitted to the testing device via a real-time system for subsequent data recording, analysis, processing, and test result determination, forming a closed-loop feedback.

[0127] Based on steps S31 to S34 above, this embodiment of the application receives a low-resolution target video stream generated based on a virtual test scenario, generates vehicle control commands based on the video stream, adjusts the operating state of the target vehicle according to the vehicle control commands and obtains operating state parameters, and then sends the operating state parameters to the test device. This realizes a closed-loop process in vehicle-in-the-loop simulation testing, from virtual environment injection, real sensor perception, vehicle actuator response to data feedback. It can realistically reproduce test scenarios under adverse weather conditions such as fog, accurately evaluate the functional performance of the forward-looking camera and intelligent driving function in cooperation with real actuators, and improve the repeatability, efficiency and authenticity of the test.

[0128] Optionally, in step S32, generating vehicle control commands based on the target video stream includes:

[0129] Step S321: Determine the obstacle's operating status based on the target video stream;

[0130] Step S322: In response to determining that the estimated collision time between the obstacle and the target vehicle is less than or equal to a preset time threshold based on the obstacle's operating state, a braking request is generated so that the target vehicle performs emergency braking based on the braking request, and a braking result is obtained.

[0131] The obstacle operation status mentioned above represents the motion characteristics of the obstacle identified by the perception algorithm of the forward-looking camera assembly from the target video stream, including key parameters such as the obstacle's position, relative velocity, and estimated collision time. For example, the obstacle could be a pedestrian suddenly appearing out of nowhere.

[0132] The estimated collision time mentioned above represents the time required for a collision to occur, calculated based on the relative speed and distance between the target vehicle and the obstacle.

[0133] The aforementioned preset time threshold represents the critical time value used to determine whether emergency braking needs to be triggered, for example, 2.5 seconds.

[0134] The aforementioned braking request indicates that when the expected collision time meets the triggering conditions, the forward-facing camera assembly sends an automatic emergency braking signal to the electronic stability controller via the CAN bus.

[0135] The above braking results represent the actual physical braking effect produced by the actuators of the target vehicle, such as wheel brakes, in response to a braking request, including changes in braking force, wheel deceleration, and other states.

[0136] When generating vehicle control commands based on a target video stream, embodiments of this application first determine the obstacle's operating status based on the target video stream. For example, the forward-facing camera assembly receives the target video stream, processes the video frames using its internal image sensor and perception algorithm, identifies obstacles in the scene, such as pedestrians suddenly crossing, and calculates the obstacle's position, speed, and relative motion with the target vehicle, thereby extracting obstacle operating status data.

[0137] In one optional embodiment, when processing video frames using an internal image sensor and perception algorithm, the image sensor first acquires video frames from the target video stream, converting the optical image into a digital image signal. Subsequently, the perception algorithm reads this digital image signal and, through edge detection, feature point matching, or deep learning model inference, identifies the outline, position, and trajectory of obstacles from the blurred or degraded image. Based on methods such as inter-frame difference or Kalman filtering, it calculates the relative velocity and estimated collision time of the obstacles, ultimately outputting obstacle operation status data containing key information such as obstacle position, velocity, and estimated collision time.

[0138] The system responds by determining that the estimated collision time between the obstacle and the target vehicle is less than or equal to a preset time threshold based on the obstacle's operational status. It then generates a braking request, causing the target vehicle to perform emergency braking based on the request, resulting in a braking outcome. For example, the control logic of the forward-facing camera assembly compares the calculated estimated collision time with a preset time threshold, such as 2.5 seconds. When the estimated collision time is less than or equal to the preset time threshold, a collision risk is identified, and a braking request is generated and sent to the vehicle's actuators via the CAN bus. Upon receiving the braking request, the vehicle's braking system executes an emergency braking action, generating actual braking force and vehicle deceleration, thus achieving the braking result.

[0139] Based on steps S321 to S322 above, this embodiment of the application determines the obstacle's running state based on the target video stream and generates a braking request to execute emergency braking when the expected collision time is less than or equal to a preset time threshold. This achieves closed-loop verification of the response logic and triggering mechanism of the automatic emergency braking function in visual degradation scenarios such as fogging during vehicle-in-the-loop simulation testing. It can accurately evaluate the safety of the forward-looking camera perception algorithm in complex environments and the braking performance of the vehicle's actuators, improving the relevance of the test and the reliability of the functional verification.

[0140] Optionally, the vehicle control method in this application embodiment further includes:

[0141] Step S41: Determine the fog thickness corresponding to the image acquisition component of the target vehicle based on the target video stream, wherein the fog thickness is used to determine the fog state corresponding to the image acquisition component.

[0142] Step S42: In response to the fog thickness being greater than a preset thickness threshold, the heating control module in the image acquisition component is controlled to be turned on.

[0143] Step S43: In response to the fog thickness being less than or equal to a preset thickness threshold, the heating control module in the image acquisition component is controlled to be in the off state.

[0144] The aforementioned image acquisition component refers to the part of the front-view camera assembly that includes an image sensor, responsible for acquiring images of the external scene.

[0145] The aforementioned fog thickness refers to the physical thickness of the water mist or frost layer condensed on the lens cover surface. This parameter can reflect the cleanliness of the image acquisition components and the extent of damage to their optical performance.

[0146] The aforementioned fogging status indicates the severity level of the fogging phenomenon currently faced by the image acquisition component, which is specifically determined by the fogging thickness.

[0147] The aforementioned preset thickness threshold represents the critical thickness value used to determine whether the heating defogging function needs to be activated. This threshold is determined through experimental calibration based on the optical performance requirements of the front-view camera assembly, the hydrophobic properties of the lens cover material, the heating efficiency of the heating film module, and environmental temperature and humidity conditions. In specific vehicle-in-the-loop simulation tests, the preset thickness threshold is typically set to the critical fogging thickness that makes the image sharpness just below a preset sharpness threshold. For example, if experiments determine that when the fogging thickness on the lens cover surface reaches 0.5 to 2.0 micrometers, the image sharpness of the target video stream injected into the front-view camera assembly begins to fall below the preset sharpness threshold for normal system operation, then the preset thickness threshold can be set to specific values ​​such as 0.5 micrometers, 1.0 micrometers, or 2.0 micrometers.

[0148] The aforementioned heating control module refers to the circuit or control unit in the front-view camera assembly used to drive the lens heating film module and to control the power supply and de-energization of the heating film.

[0149] This application embodiment determines the fog thickness corresponding to the image acquisition component of the target vehicle based on the target video stream, wherein the fog thickness is used to determine the fog state corresponding to the image acquisition component. For example, the processing unit of the forward-looking camera assembly performs image quality analysis on the received target video stream. By evaluating visual degradation characteristics such as image blurring and contrast reduction, and combining this with a fog physical model, it inversely calculates the theoretical fog thickness on the current lens surface, thereby quantifying the fog state of the image acquisition component.

[0150] In response to a fog thickness exceeding a preset thickness threshold, the heating control module in the image acquisition component is activated. For example, the control logic of the front-view camera assembly compares the calculated fog thickness with the preset thickness threshold. When it determines that the fog thickness exceeds the preset thickness threshold, it indicates severe fogging that affects image quality. Subsequently, it sends an activation command to the heating control module, energizing the heating film module to heat the lens cover and evaporate the water vapor.

[0151] In response to the fog thickness being less than or equal to a preset thickness threshold, the heating control module in the image acquisition component is turned off. For example, after the image clarity is restored or the fog level is reduced, the control logic of the front-view camera assembly determines that the fog thickness has dropped to the preset thickness threshold or below, and determines that the fog state has improved to an acceptable range. Then, it sends a shutdown command to the heating control module to stop heating to save energy and prevent the lens from overheating.

[0152] Based on steps S41 to S43 above, this embodiment of the application determines the fog thickness based on the target video stream and dynamically controls the opening or closing of the heating control module according to the comparison result between the fog thickness and the preset thickness threshold. This achieves refined closed-loop control verification of the anti-fog heating function of the front-view camera, which can accurately simulate the process of the camera automatically adjusting the heating state according to the degree of fog in real scenarios, and improves the evaluation accuracy of the effectiveness of the intelligent anti-fog strategy in vehicle-in-the-loop simulation test.

[0153] For example, the vehicle testing method of this application embodiment is described using a ghost-protruding scenario in vehicle-in-the-loop simulation testing as an example. Specifically, the method includes five main steps.

[0154] First, a virtual test scenario for "ghost pedestrians" was built. A two-way, two-lane road model was created in the scenario simulation software. The virtual main vehicle was defined to travel at a constant speed of 30 km / h, and the pedestrian crossed from behind the parked van at a speed of 1.5 m / s, initially 15 meters away from the front of the main vehicle. The environmental parameters were configured as 0℃ temperature and 95% relative humidity. The scenario simulation software calculated the fog thickness on the lens surface based on the fog physical model and rendered the degraded video stream. The starting time for the image clarity to start to blur from the normal value was set to 3 seconds before the main vehicle approached the pedestrian crossing point.

[0155] Secondly, establish sensor and vehicle models. Create a virtual vehicle model based on the actual dimensions of the vehicle under test, and measure the installation coordinates, pitch angle, yaw angle, and roll angle of the forward-looking camera on the vehicle.

[0156] Next, perform hardware connection and synchronization debugging, connecting the host computer, slave computer, real-time system, injection board, camera assembly and inertial navigation system, and setting the trigger signal of the real-time system to synchronize the start time of scene simulation, video stream injection and data acquisition.

[0157] Then, the test cases are executed, the configured ghost peek test cases are loaded, the scene simulation software starts running and generates a virtual road image with superimposed fog degradation effect, which is sent to the front-view camera assembly in real time through the injection board. The camera assembly decides whether to activate the heating film according to the fog state, and transmits the target list and braking request output by the perception algorithm through the CAN bus. When the expected collision time is less than 2.5 seconds, the real vehicle performs emergency braking. The inertial navigation system collects the vehicle's pose and feeds it back to the real-time system and forwards it to the lower computer to update the position of the main vehicle in the virtual scene, realizing a virtual-real closed loop.

[0158] Finally, data post-processing and evaluation were performed. After the test, video stream timestamps, CAN messages, and inertial navigation pose data were exported from the real-time system to evaluate the camera's performance under fog conditions.

[0159] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0160] This application also provides a vehicle testing device for implementing the above embodiments and preferred embodiments, which will not be repeated hereafter. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0161] Figure 4 This is a structural block diagram of a vehicle testing device according to one embodiment of this application, such as... Figure 4 As shown, the device includes:

[0162] The acquisition module 401 is used to acquire test cases, wherein the test cases represent the functional test requirements corresponding to the target vehicle;

[0163] The first generation module 402 is used to generate virtual test scenarios based on test cases, wherein the virtual test scenarios are used to perform functional tests on the target vehicle;

[0164] The second generation module 403 is used to generate a target video stream according to the virtual test scenario, wherein the image clarity of the target video stream is less than a preset clarity threshold.

[0165] The first sending module 404 is used to send the target video stream to the target vehicle.

[0166] Optionally, the second generation module 403 is further configured to: generate an initial video stream based on the virtual test scenario, wherein the image clarity of the initial video stream is greater than or equal to a preset clarity threshold; configure virtual test parameters based on the virtual test scenario; and render the initial video stream according to the virtual test parameters to obtain a target video stream.

[0167] Optionally, the second generation module 403 is further configured to: determine the target fogging parameters based on the virtual test parameters and the preset fogging model; and render the initial video stream based on the target fogging parameters to obtain the target video stream.

[0168] Optionally, the first sending module 404 is further configured to: convert the target video stream into a format using an injection board to obtain a target test signal; and send the target test signal to the target vehicle.

[0169] Optionally, the vehicle control device in this embodiment further includes: a first receiving module 405, used to receive operating status parameters corresponding to the target vehicle, wherein the operating status parameters include real-time pose information corresponding to the target vehicle; and a first processing module 406, used to update the initial pose information corresponding to the target vehicle based on the real-time pose information to obtain target pose information, wherein the initial pose information is determined based on a virtual vehicle model, and the virtual vehicle model is generated based on the attribute information corresponding to the target vehicle.

[0170] Optionally, the vehicle control device in this application embodiment further includes: a second processing module 407, used to analyze and process the target video stream and operating status data to obtain analysis results; and a first determining module 408, used to determine test results based on the analysis results.

[0171] Figure 5 This is a structural block diagram of another vehicle testing apparatus according to one embodiment of this application, such as... Figure 5 As shown, the device includes:

[0172] The second receiving module 501 is used to receive the target video stream, wherein the target video stream is generated based on a virtual test scenario, the image clarity of the target video stream is less than a preset clarity threshold, and the virtual test scenario is generated based on test cases.

[0173] The third generation module 502 is used to generate vehicle control commands based on the target video stream;

[0174] The third processing module 503 is used to adjust the operating state of the target vehicle according to the vehicle control command to obtain the operating state parameters of the target vehicle.

[0175] The second sending module 504 is used to send the operating status parameters corresponding to the target vehicle to the testing device.

[0176] Optionally, the third generation module 502 is further configured to: determine the obstacle's operating state based on the target video stream; and, in response to the determination based on the obstacle's operating state that the expected collision time between the obstacle and the target vehicle is less than or equal to a preset time threshold, generate a braking request so that the target vehicle performs emergency braking based on the braking request, thereby obtaining a braking result.

[0177] Optionally, the vehicle control device in this embodiment further includes: a second determining module 505, used to determine the fog thickness corresponding to the image acquisition component of the target vehicle based on the target video stream, wherein the fog thickness is used to determine the fog state corresponding to the image acquisition component; a first control module 506, used to control the heating control module in the image acquisition component to be in an on state in response to the fog thickness being greater than a preset thickness threshold; and a second control module 507, used to control the heating control module in the image acquisition component to be in a off state in response to the fog thickness being less than or equal to the preset thickness threshold.

[0178] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0179] According to another aspect of the embodiments of this application, an electronic device is also provided, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the vehicle testing method described above when it runs.

[0180] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0181] Step S11: Obtain test cases, wherein the test cases are used to represent the functional test requirements corresponding to the target vehicle;

[0182] Step S12: Generate a virtual test scenario based on the test cases, wherein the virtual test scenario is used to perform functional testing on the target vehicle;

[0183] Step S13: Generate a target video stream based on the virtual test scenario, wherein the image clarity of the target video stream is less than a preset clarity threshold.

[0184] Step S14: Send the target video stream to the target vehicle.

[0185] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is running, it controls the device where the storage medium is located to execute the above-described vehicle testing method.

[0186] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0187] Step S11: Obtain test cases, wherein the test cases are used to represent the functional test requirements corresponding to the target vehicle;

[0188] Step S12: Generate a virtual test scenario based on the test cases, wherein the virtual test scenario is used to perform functional testing on the target vehicle;

[0189] Step S13: Generate a target video stream based on the virtual test scenario, wherein the image clarity of the target video stream is less than a preset clarity threshold.

[0190] Step S14: Send the target video stream to the target vehicle.

[0191] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing computer programs, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0192] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements the vehicle testing method described above.

[0193] Optionally, in this embodiment, the above-mentioned computer program product can be configured as a computer program that performs the following steps:

[0194] Step S11: Obtain test cases, wherein the test cases are used to represent the functional test requirements corresponding to the target vehicle;

[0195] Step S12: Generate a virtual test scenario based on the test cases, wherein the virtual test scenario is used to perform functional testing on the target vehicle;

[0196] Step S13: Generate a target video stream based on the virtual test scenario, wherein the image clarity of the target video stream is less than a preset clarity threshold.

[0197] Step S14: Send the target video stream to the target vehicle.

[0198] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0199] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0200] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0201] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0202] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0203] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0204] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A vehicle testing method, characterized in that, Applied to a vehicle testing system, the system comprising: a target vehicle, the method comprising: Obtain test cases, wherein the test cases are used to represent the functional test requirements corresponding to the target vehicle; A virtual test scenario is generated based on the test cases, wherein the virtual test scenario is used to perform functional tests on the target vehicle; A target video stream is generated based on the virtual test scenario, wherein the image clarity of the target video stream is less than a preset clarity threshold. The target video stream is sent to the target vehicle.

2. The method according to claim 1, characterized in that, Generating the target video stream based on the virtual test scenario includes: An initial video stream is generated based on the virtual test scenario, wherein the image clarity of the initial video stream is greater than or equal to the preset clarity threshold. Configure virtual test parameters based on the virtual test scenario; The initial video stream is rendered according to the virtual test parameters to obtain the target video stream.

3. The method according to claim 2, characterized in that, The initial video stream is rendered according to the virtual test parameters to obtain the target video stream, including: Determine the target fogging parameters based on the virtual test parameters and the preset fogging model; The initial video stream is rendered based on the target fogging parameters to obtain the target video stream.

4. The method according to claim 1, characterized in that, The system further includes: an injection board, which sends the target video stream to the target vehicle, including: The target video stream is converted into a format using the injection board to obtain the target test signal; The target test signal is sent to the target vehicle.

5. The method according to claim 1, characterized in that, The method further includes: Receive the operating status parameters corresponding to the target vehicle, wherein the operating status parameters include the real-time pose information corresponding to the target vehicle; The initial pose information corresponding to the target vehicle is updated based on the real-time pose information to obtain the target pose information. The initial pose information is determined based on a virtual vehicle model, and the virtual vehicle model is generated based on the attribute information corresponding to the target vehicle.

6. The method according to claim 5, characterized in that, The method further includes: The target video stream and the running status data are analyzed and processed to obtain analysis results; The test results are determined based on the analysis results.

7. A vehicle testing method, characterized in that, Applied to a vehicle testing system, the system includes: a testing device, and the method includes: Receive a target video stream, wherein the target video stream is generated based on a virtual test scenario, the image clarity of the target video stream is less than a preset clarity threshold, and the virtual test scenario is generated based on test cases; Generate vehicle control commands based on the target video stream; The operating state of the target vehicle is adjusted according to the vehicle control command to obtain the operating state parameters of the target vehicle. The operating status parameters corresponding to the target vehicle are sent to the testing device.

8. The method according to claim 7, characterized in that, Generating the vehicle control command based on the target video stream includes: Determine the obstacle's operational status based on the target video stream; The response determines that the estimated collision time between the obstacle and the target vehicle is less than or equal to a preset time threshold based on the obstacle's operating state, and generates a braking request so that the target vehicle performs emergency braking based on the braking request, thereby obtaining a braking result.

9. The method according to claim 7, characterized in that, The method further includes: The fog thickness corresponding to the image acquisition component of the target vehicle is determined based on the target video stream, wherein the fog thickness is used to determine the fog state corresponding to the image acquisition component; In response to the fog thickness exceeding a preset thickness threshold, the heating control module in the image acquisition component is controlled to be turned on; or, In response to the fog thickness being less than or equal to the preset thickness threshold, the heating control module in the image acquisition component is controlled to be in a closed state.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the storage medium is located to perform the method according to any one of claims 1 to 9.

Images