Intelligent driving function test method and device of vehicle, electronic equipment and medium

Abstract

The application relates to the technical field of intelligent driving of vehicles, in particular to an intelligent driving function testing method and device of a vehicle, an electronic device and a medium, wherein the method comprises the following steps: acquiring real scene data and video data of a target test scene collected by a vehicle; performing data back-annotation on the real scene data and the video data respectively by using a preset data back-annotation strategy, obtaining a plurality of scene data frames and a plurality of video data frames of each target test scene, restoring the target test scene by using the plurality of scene data frames, and judging whether the target intelligent driving function is qualified according to a virtual response of the vehicle under the target test scene and a real response obtained from the video data frames. Therefore, the problems that a method of road testing in related technologies consumes a large amount of cost and has a certain danger, and a simulation mode of collecting can data cannot simulate the response of the vehicle when facing complex scenes, so that some functions cannot be verified and the like are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent driving of vehicles, and in particular relates to an intelligent driving function testing method and device for vehicles, an electronic device and a medium. BACKGROUND

[0002] Traditional intelligent driving testing methods are mainly two kinds: one is road testing, which needs to be carried out on-site in real vehicles every time a new function is generated; the other is irregular road testing, which collects can data and then sends the collected data through can signals for simulation. The method does not have more visualized display, and many functions that require a large number of vehicles cannot be verified.

[0003] However, the cost of driving function testing through road testing in the related art is high, and if the maturity of intelligent driving technology is low, road testing is also dangerous. In addition, the method of collecting can data for simulation cannot simulate the reaction of the vehicle when it faces complex scenes, and some functions cannot be verified. SUMMARY

[0004] The present application provides an intelligent driving function testing method and device for vehicles, an electronic device and a medium to solve the problem that the method of collecting can data for simulation in the related art does not have more visualized display and cannot simulate the reaction of the vehicle when it faces complex scenes, resulting in that some functions cannot be verified.

[0005] The first aspect of the present application provides an intelligent driving function testing method for vehicles, comprising the following steps: obtaining real scene data of at least one target test scene collected by a vehicle and real video data in a collection process; using a preset data back-annotation strategy to respectively back-annotate the real scene data and the real video data, to obtain a plurality of scene data frames and a plurality of video data frames of each target test scene, using the plurality of scene data frames to restore the each target test scene, and using the plurality of video data frames to determine a real reaction state of the vehicle in the each target test scene; performing simulation testing on a target intelligent driving function in the each target test scene, to obtain a virtual reaction state of the vehicle in the each target test scene, and determining that the target intelligent driving function is qualified when the virtual reaction state of the vehicle in any target test scene is consistent with the real reaction state, otherwise the target intelligent driving function is unqualified.

[0006] According to the technical means, the preset data playback strategy is used to perform data playback on the scene data and the video data of the vehicle in the driving process, real-time effects are displayed on the software, the target test scene is obtained by restoring, and the virtual reaction of the vehicle in the target test scene and the real reaction obtained from the vehicle video data are used to determine the problems in the driving process of the vehicle. Compared with the road test required in the past each test of intelligent driving, a large amount of manpower and material resources are saved, various scenes encountered in the intelligent driving process of the vehicle can be truly reflected, and the driving risk is greatly reduced.

[0007] Optionally, in an embodiment of the present application, the data playback strategy is used to perform data playback on the real scene data and the real video data respectively, and a plurality of scene data frames and a plurality of video data frames of each target test scene are obtained, including: using a preset data playback tool to perform synchronous processing on the real scene data and the real video data, and obtaining the plurality of scene data frames and the plurality of video data frames of each target test scene.

[0008] According to the technical means, the data playback tool is used to obtain a plurality of data frames of the collected road test data and the video data, real-time viewing of data parameters of each frame can be realized, and the reaction of the vehicle in different frames can be viewed through the video.

[0009] Optionally, in an embodiment of the present application, the plurality of scene data frames are used to restore the each target test scene, including: using a preset scene restoration tool to pre-process the plurality of scene data frames to obtain a plurality of pre-processed data frames, and performing scene rendering on the plurality of pre-processed data frames to restore the each target test scene.

[0010] According to the technical means, the scene data is processed by using the restoration tool, and the target test scene is restored by using the rendered scene effect, so that the simulation test of the target intelligent driving function is realized.

[0011] Optionally, in an embodiment of the present application, the plurality of video data frames are used to determine the real reaction state of the vehicle in each target test scene, including: using a preset data playback tool to set a start frame and an end frame of the plurality of video data frames; playing a driving video of each target test scene according to the start frame and the end frame, and identifying the content of the driving video to determine the real reaction state of the vehicle in the each target test scene.

[0012] According to the technical means, the starting frame and the ending frame can be set, the data playback tool can send data between the two frames in a loop, and the key scene can be played in a loop, so that the reaction of the vehicle in the current scene can be determined more accurately.

[0013] The second aspect of the application provides a device for testing intelligent driving function of a vehicle, comprising: an acquisition module configured to acquire real scene data of at least one target test scene collected by the vehicle and real video data collected in a process; a processing module configured to perform data playback on the real scene data and the real video data respectively by using a preset data playback strategy, to obtain a plurality of scene data frames and a plurality of video data frames of each target test scene, restore the each target test scene by using the plurality of scene data frames, and determine a real reaction state of the vehicle in the each target test scene by using the plurality of video data frames; and a test module configured to perform simulation test on a target intelligent driving function in the each target test scene, to obtain a virtual reaction state of the vehicle in the each target test scene, and determine that the target intelligent driving function is qualified when the virtual reaction state of the vehicle in any target test scene is consistent with the real reaction state, and otherwise, the target intelligent driving function is unqualified.

[0014] Optionally, in an embodiment of the application, the processing module is further configured to perform synchronous processing on the real scene data and the real video data by using a preset data playback tool, to obtain the plurality of scene data frames and the plurality of video data frames of each target test scene.

[0015] Optionally, in an embodiment of the application, the processing module is further configured to perform preprocessing on the plurality of scene data frames by using a preset scene restoration tool, to obtain a plurality of preprocessed data frames, and perform scene rendering on the plurality of preprocessed data frames to restore the each target test scene.

[0016] Optionally, in an embodiment of the application, the processing module is further configured to set a starting frame and an ending frame of the plurality of video data frames by using a preset data playback tool; play driving video of each target test scene according to the starting frame and the ending frame, and identify content of the driving video to determine the real reaction state of the vehicle in the each target test scene.

[0017] The third aspect of the application provides a vehicle, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for testing intelligent driving function of a vehicle as described in the above embodiments.

[0018] The fourth aspect of the present application provides a computer readable storage medium, which stores a computer program. The program is executed by a processor to implement the intelligent driving function test method of the vehicle as described in the above embodiments.

[0019] Therefore, the present application has at least the following beneficial effects:

[0020] 1. The embodiments of the present application can use the preset data playback strategy to perform data playback on the scene data and video data of the vehicle during driving, display real-time effects on the software, restore the target test scene, and determine the problems of the vehicle during driving according to the virtual response of the vehicle under the target test scene and the real response obtained from the vehicle video data. Compared with the past road test for testing intelligent driving function, the present application saves a large amount of manpower and material resources, and can truly reflect various scenes encountered by the vehicle during intelligent driving, thereby greatly reducing the risk of driving.

[0021] 2. The embodiments of the present application can use the data playback tool to obtain a plurality of data frames of the collected road test data and video data, which can not only realize real-time viewing of the data parameters of each frame, but also realize viewing of the response of the vehicle under different frames through the video.

[0022] 3. The embodiments of the present application can use the restoration tool to process the scene data, and restore the target test scene through the rendered scene effect, thereby realizing the simulation test of the target intelligent driving function.

[0023] 4. The embodiments of the present application can set the start frame and the end frame, and the data playback tool will cyclically send the data between the two frames to cyclically play the key scene, thereby determining the response of the vehicle under the current scene.

[0024] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0025] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, including the accompanying drawings, wherein:

[0026] Figure 1 A flowchart of an intelligent driving function test method of a vehicle according to an embodiment of the present application is provided.

[0027] Figure 2 A flowchart of collecting real scene data and video data according to an embodiment of the present application is provided.

[0028] Figure 3 A parameter diagram of road test data and video data collected by a data playback tool according to an embodiment of the present application is provided.

[0029] Figure 4 A schematic diagram of a cycle sending function of a data back-annotation tool according to an embodiment of the application is shown in FIG. 6;

[0030] Figure 5 A schematic diagram of a progress bar function of a data back-annotation tool according to an embodiment of the application is shown in FIG. 7;

[0031] Figure 6 A comprehensive simulation schematic diagram of a scene restoration tool according to an embodiment of the application is shown in FIG. 8;

[0032] Figure 7 A block schematic diagram of an intelligent driving function testing device of a vehicle according to an embodiment of the application is shown in FIG. 9;

[0033] Figure 8 A structural schematic diagram of a vehicle according to an embodiment of the application is shown in FIG. 10.

[0034] Legend: acquisition module - 100, processing module - 200, testing module - 300, memory - 801, processor - 802, communication interface - 803. DETAILED DESCRIPTION

[0035] Embodiments of the application are described in detail below with reference to the accompanying drawings, examples of which are shown in the drawings, in which the same or similar notations represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present application, and cannot be understood as limiting the present application.

[0036] The intelligent driving function testing method, device, vehicle and storage medium of a vehicle according to the embodiments of the application are described below with reference to the accompanying drawings. In view of the problems mentioned in the above background art, the present application provides an intelligent driving function testing method of a vehicle, in which a preset data back-annotation strategy is used to perform data back-annotation on scene data and video data of the vehicle during driving, to display real-time effects on software, to restore target test scenes, and to determine problems occurring during driving of the vehicle according to virtual responses of the vehicle under the target test scenes and real responses obtained from the video data of the vehicle. Compared with the conventional method of testing intelligent driving functions by road testing, the present application saves a large amount of manpower and material resources, and can truly reflect various scenes encountered by the vehicle during intelligent driving, thereby greatly reducing the risk of driving. Thus, the present application solves the problems of the related art, such as the consumption of a large amount of cost, the certain danger, and the inability to simulate the responses of the vehicle in complex scenes by collecting can data for simulation, resulting in the failure to verify some functions.

[0037] Specifically, Figure 1This is a flowchart illustrating a method for testing the intelligent driving function of a vehicle, as provided in an embodiment of this application.

[0038] like Figure 1 As shown, the testing method for the intelligent driving function of this vehicle includes the following steps:

[0039] In step S101, real scene data of at least one target test scenario collected by the vehicle and real video data during the collection process are acquired.

[0040] To accurately reflect the various behaviors of the vehicle under test, embodiments of this application require acquiring real-world scene data and video data during vehicle operation. This process necessitates on-road data collection. Figure 2 As shown, in this embodiment of the application, data is collected at different locations according to the scenario to be tested. Road scene data can be collected through radar, cameras and other equipment, and video data at that time can be collected through cameras.

[0041] In step S102, a preset data back-injection strategy is used to back-inject real scene data and real video data respectively to obtain multiple scene data frames and multiple video data frames for each target test scenario. The multiple scene data frames are used to reconstruct each target test scenario, and the multiple video data frames are used to determine the actual reaction state of the vehicle under each target test scenario.

[0042] Specifically, the embodiments of this application can use a preset data back-injection strategy to back-inject scene data and video data of the vehicle during driving, perform theoretical analysis on the data, determine the actual reaction state of the vehicle under the test scenario, and display the real-time effect on the software and reconstruct the target test scenario, which has a more vivid visualization display.

[0043] In one embodiment of this application, a preset data back-injection strategy is used to perform data back-injection on real scene data and real video data respectively to obtain multiple scene data frames and multiple video data frames for each target test scene. This includes: using a preset data back-injection tool to synchronously process real scene data and real video data to obtain multiple scene data frames and multiple video data frames for each target test scene.

[0044] The preset data injection tool can be determined according to the actual situation and is not specifically limited.

[0045] Specifically, such as Figure 3As shown, this embodiment of the application can use a data back-injection tool to synchronously process collected road scene data and video data, and then send the processed data to a scene restoration tool via UDP or other methods. During the processing of road scene data, the size of the road scene data frames can be obtained, the sending interval and port number can be controlled, and the sending method can be set. If the operation is performed on a single computer, the destination address needs to be set to the current computer's IP address or 127.0.0.1, and the destination port needs to be set to the port agreed upon with the scene restoration tool. These processes can also be pre-defined in a configuration file. When processing video data, the image of each frame of the video can be obtained, and then edited, such as adding timestamps and watermarks, before playing it frame by frame.

[0046] In one embodiment of this application, each target test scene is reconstructed using multiple scene data frames, including: preprocessing multiple scene data frames using a preset scene reconstruction tool to obtain multiple preprocessed data frames, and rendering the multiple preprocessed data frames to reconstruct each target test scene.

[0047] The preset scene restoration tool can be selected according to the actual situation and is not specifically limited.

[0048] It is understood that the embodiments of this application may employ an event-triggered mechanism. After receiving data sent by the data back-injection tool, the entire 3D road scene information can be reconstructed based on the data, such as... Figure 4 As shown, combined with Figure 3 The videos show various problems that arise in intelligent driving. They also allow for data processing, such as filtering to prevent excessive jitter when rendering targets and lane lines, coordinate system transformation, and warning sound filtering.

[0049] It should be noted that the scene restoration tool in this embodiment requires the UDP listening port number to be set, and this port number must be consistent with the agreement of the data injection tool. Below are some simple setting functions of the scene restoration tool in this embodiment, such as... Figure 4 As shown, you can also view the current frame rate and whether the high-precision map is online. The main function of the tool is to render the car's state in the current frame. You can observe the car's reaction in the current scene through the rendered scene effects. At the same time, you can manipulate the data in the background for adjustment and verification. Combined with the video playback in the data back-injection tool, you can conduct some experiments.

[0050] In an embodiment of the present application, the real reaction state of the vehicle in each target test scene is determined by using a plurality of video data frames, including: setting the starting frame and the ending frame of the plurality of video data frames by using a preset data playback tool; playing the driving video of each target test scene according to the starting frame and the ending frame, and identifying the content of the driving video to determine the real reaction state of the vehicle in each target test scene.

[0051] As shown in Figure 5 , the embodiment of the present application can use the loop sending function of the data playback tool. After checking the function, the starting frame and the ending frame can be set. The data playback tool will send the data between the two frames in a loop, and the key scenes will be played in a loop to determine the reaction of the vehicle in the current scene. At the same time, the video will also be played in a loop in the time corresponding to the two frames, which is very useful when special scenes need to be repeatedly viewed.

[0052] As another possible implementation, as shown in Figure 6 , the embodiment of the present application can use the progress bar function of the data playback tool. The right side of the progress bar is the current frame number. By sliding the progress bar, the data and video of the specified frame can be viewed.

[0053] In step S103, the target intelligent driving function is simulated and tested in each target test scene to obtain the virtual reaction state of the vehicle in each target test scene. When the virtual reaction state of the vehicle in any target test scene is consistent with the real reaction state, it is determined that the test of the target intelligent driving function is qualified, otherwise the test is unqualified.

[0054] It can be understood that the embodiment of the present application can use the above-mentioned software tool to restore the target test scene, and determine the test qualification of the target intelligent driving function according to the virtual reaction of the vehicle in the target test scene and the real reaction obtained from the vehicle video data. While saving the cost of manpower and material resources, the scene can be restored truly, greatly reducing the risk of driving. It can also simulate the data of the scene that has not been encountered, and itself has the characteristics of small code amount and simple operation.

[0055] According to the intelligent driving function test method of the vehicle provided in the embodiment of the present application, the preset data playback strategy is used to perform data playback on the scene data and the video data of the vehicle in the driving process, the real-time effect is displayed on the software, the target test scene is obtained by restoring, and the virtual response of the vehicle in the target test scene and the real response obtained from the vehicle video data are used to determine the problems in the driving process of the vehicle. Compared with the road test required in the past each time of testing the intelligent driving function, a large amount of manpower and material resources is saved, and various scenes encountered in the intelligent driving process of the vehicle can be truly reflected, and the driving risk is greatly reduced. Therefore, the problems that the related art adopts the road test method and a large amount of cost is consumed, the method has a certain risk, and the reaction of the vehicle in the face of complex scenes cannot be simulated through the simulation method of collecting can data, and some functions cannot be verified are solved.

[0056] Secondly, a vehicle intelligent driving function test device according to an embodiment of the present application is described with reference to the accompanying drawings.

[0057] Figure 7 is a block schematic diagram of a vehicle intelligent driving function test device according to an embodiment of the present application.

[0058] As Figure 7 shown, the vehicle intelligent driving function test device 10 includes an acquisition module 100, a processing module 200, and a test module 300.

[0059] The acquisition module 100 is configured to acquire real scene data of at least one target test scene collected by the vehicle and real video data in a collection process. The processing module 200 is configured to perform data playback on the real scene data and the real video data respectively by using a preset data playback strategy, to obtain a plurality of scene data frames and a plurality of video data frames of each target test scene, to restore each target test scene by using the plurality of scene data frames, and to determine a real response state of the vehicle in each target test scene by using the plurality of video data frames. The test module 300 is configured to perform simulation test on a target intelligent driving function in each target test scene, to obtain a virtual response state of the vehicle in each target test scene, and to determine that the target intelligent driving function is tested qualified when the virtual response state of the vehicle in any target test scene is consistent with the real response state, otherwise, the target intelligent driving function is tested unqualified.

[0060] In an embodiment of the present application, the processing module 200 is further configured to perform synchronous processing on the real scene data and the real video data by using a preset data playback tool, to obtain the plurality of scene data frames and the plurality of video data frames of each target test scene.

[0061] In an embodiment of the present application, the processing module 200 is further configured to pre-process the plurality of scene data frames by using a preset scene restoration tool to obtain a plurality of pre-processed data frames, and perform scene rendering on the plurality of pre-processed data frames to restore each target test scene.

[0062] In an embodiment of the present application, the processing module 200 is further configured to set a start frame and an end frame of the plurality of video data frames by using a preset data playback tool, play a driving video of each target test scene according to the start frame and the end frame, and identify the content of the driving video to determine the real reaction state of the vehicle in each target test scene.

[0063] It should be noted that the above description of the embodiments of the vehicle intelligent driving function test method also applies to the vehicle intelligent driving function test device of the embodiments, which will not be described here.

[0064] The vehicle intelligent driving function test device provided in the embodiments of the present application uses a preset data playback strategy to perform data playback on the scene data and video data of the vehicle during driving, displays real-time effects on the software, restores target test scenes, and determines problems in the driving process of the vehicle according to the virtual reaction of the vehicle in the target test scenes and the real reaction obtained from the video data of the vehicle. Compared with the past road test for testing intelligent driving function, a large amount of manpower and material resources is saved, and various scenes encountered by the vehicle during intelligent driving can be truly reflected, which greatly reduces the risk of driving. Thus, the problems of the related art, such as the consumption of a large amount of cost, certain risk, and the inability to simulate the reaction of the vehicle in complex scenes by collecting can data for simulation, resulting in the failure to verify some functions, are solved.

[0065] Figure 8 The vehicle provided in the embodiments of the present application is shown in the structural diagram. The vehicle can include:

[0066] The memory 801, the processor 802, and the computer program stored in the memory 801 and executable on the processor 802.

[0067] The processor 802 implements the vehicle intelligent driving function test method provided in the above embodiments when executing the program.

[0068] Further, the vehicle further includes:

[0069] The communication interface 803 is configured to communicate between the memory 801 and the processor 802.

[0070] The memory 801 is configured to store the computer program executable on the processor 802.

[0071] The memory 801 can include a high-speed RAM (Random Access Memory) memory, and can also include a nonvolatile memory, such as at least one disk memory.

[0072] If the memory 801, the processor 802 and the communication interface 803 are independently implemented, the communication interface 803, the memory 801 and the processor 802 can be connected to each other through a bus and complete communication between each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Figure 8 In the figure, only one thick line is used to represent, but it does not mean that there is only one bus or one type of bus.

[0073] Optionally, in a specific implementation, if the memory 801, the processor 802 and the communication interface 803 are integrated on a chip, the memory 801, the processor 802 and the communication interface 803 can complete communication between each other through an internal interface.

[0074] The processor 802 can be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0075] The embodiments of the present application also provide a computer readable storage medium, having stored thereon a computer program, which is executed by a processor to implement the above-mentioned method for testing intelligent driving function of a vehicle.

[0076] In the description of the application, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the application. In the description of the application, the illustrative description of the above terms is not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or N embodiments or examples. In addition, different embodiments or examples described in the description of the application and the features of different embodiments or examples can be combined and combined by those skilled in the art without contradiction.

[0077] In addition, the terms "first", "second" are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the application, the meaning of "N" is at least two, for example, two, three, etc., unless otherwise specifically limited.

[0078] Any process or method descriptions in flow charts or otherwise described herein can be understood as representing code modules, segments, or portions of code that include one or more executable instructions for implementing the specified logical functions or processes, and the preferred embodiments of the application include additional or fewer steps, or combinations of steps, or method segments, in different arrangements or orders, consistent with the described functions, which should be understood by those skilled in the art.

[0079] It should be understood that parts of the application can be implemented in hardware, software, firmware or a combination thereof. In the above described embodiments, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. As in another embodiment, if implemented in hardware, any of the following technologies known in the art or their combinations can be used: discrete logic circuit with logic gate circuit for implementing logical functions on data signals, application specific integrated circuit with suitable combination of logic gate circuit, programmable gate array, field programmable gate array, etc.

[0080] Those skilled in the art of the present technology can understand that all or part of the steps carried out by the above described embodiment method can be completed by program instructions to the relevant hardware, and the program can be stored in a computer readable storage medium, which includes one or a combination of steps of the method embodiments when executed.

[0081] Although the embodiments of the present application have been shown and described above, it is understood that the above-described embodiments are exemplary and are not to be construed as limiting the present application, and that changes, modifications, substitutions and variations can be made by those skilled in the art without departing from the scope of the present application.

Claims

1. A method of testing an intelligent driving function of a vehicle, characterized by, The method comprises the following steps: obtaining real scene data and real video data of at least one target test scene collected by a vehicle; using a preset data playback strategy to perform data playback on the real scene data and the real video data respectively, to obtain a plurality of scene data frames and a plurality of video data frames of each target test scene, using the plurality of scene data frames to restore the each target test scene, and using the plurality of video data frames to determine a real reaction state of the vehicle in the each target test scene; performing simulation testing on a target intelligent driving function in the each target test scene, to obtain a virtual reaction state of the vehicle in the each target test scene, and determining that the target intelligent driving function is qualified when the virtual reaction state of the vehicle in any target test scene is consistent with the real reaction state, otherwise, determining that the target intelligent driving function is unqualified; the using of the preset data playback strategy to perform data playback on the real scene data and the real video data respectively, to obtain a plurality of scene data frames and a plurality of video data frames of each target test scene, comprises: using a preset data playback tool to perform synchronous processing on the real scene data and the real video data, to obtain a plurality of scene data frames and a plurality of video data frames of each target test scene; the using of the plurality of video data frames to determine a real reaction state of the vehicle in each target test scene, comprises: using a preset data playback tool to set a start frame and an end frame of the plurality of video data frames; playing driving video of each target test scene according to the start frame and the end frame, and identifying the content of the driving video, to determine the real reaction state of the vehicle in the each target test scene; the data playback tool cyclically sends data between two frames.

2. The method of claim 1, wherein, the using of the plurality of scene data frames to restore the each target test scene, comprises: using a preset scene restoration tool to pre-process the plurality of scene data frames, to obtain a plurality of pre-processed data frames, and performing scene rendering on the plurality of pre-processed data frames, to restore the each target test scene.

3. An intelligent driving function testing apparatus for a vehicle for performing the method according to any one of claims 1 to 2, characterized in that comprises: an obtaining module, configured to obtain real scene data and real video data of at least one target test scene collected by a vehicle; a processing module, configured to use a preset data playback strategy to perform data playback on the real scene data and the real video data respectively, to obtain a plurality of scene data frames and a plurality of video data frames of each target test scene, use the plurality of scene data frames to restore the each target test scene, and use the plurality of video data frames to determine a real reaction state of the vehicle in the each target test scene; a testing module, configured to perform simulation testing on a target intelligent driving function in the each target test scene, to obtain a virtual reaction state of the vehicle in the each target test scene, and determine that the target intelligent driving function is qualified when the virtual reaction state of the vehicle in any target test scene is consistent with the real reaction state, otherwise, determine that the target intelligent driving function is unqualified.

4. The apparatus of claim 3, wherein, the processing module is further configured to: The real scene data and the real video data are synchronously processed by using a preset data back-annotation tool, to obtain a plurality of scene data frames and a plurality of video data frames of each target test scene.

5. The apparatus of claim 3, wherein, The processing module is further configured to: The plurality of scene data frames are preprocessed by using a preset scene restoration tool to obtain a plurality of preprocessed data frames, and the plurality of preprocessed data frames are subjected to scene rendering to restore the each target test scene.

6. The apparatus of claim 4, wherein, The processing module is further configured to: The start frame and the end frame of the plurality of video data frames are set by using a preset data back-annotation tool; A driving video of each target test scene is played according to the start frame and the end frame, and the content of the driving video is identified to determine the real reaction state of the vehicle in the each target test scene.

7. An electronic device, comprising: The application further provides a computer program product, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent driving function test method of the vehicle according to any one of claims 1-2.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the intelligent driving function test method of the vehicle according to any one of claims 1-2.

Images