Vehicle parking test method, parking abnormity management method and computer equipment

Abstract

The invention provides a vehicle parking test method, a parking abnormity management method and computer equipment, and the vehicle parking test method comprises the steps: generating a visual interface according to the perception information of a target vehicle in the parking driving process, the visual interface comprises a panoramic image sub-interface for displaying a panoramic image of the target vehicle and an electronic map sub-interface for displaying mapping information of the panoramic image of the target vehicle, and generating an abnormal object file according to abnormal information under the condition that the abnormal object and the abnormal information of the abnormal object are determined according to the visual interface, and generating an abnormal detection video according to the abnormal object file so as to obtain a first parking perception test result of the target vehicle according to the abnormal detection video. Thus, the abnormal object can be determined more visually based on the visual interface, then the abnormal detection video is obtained, vehicle parking problem analysis can be performed more visually, the parking perception test result is obtained, and the perception accuracy of the vehicle can be improved more easily.

Description

Technical Field

[0001] The present application relates to the field of vehicle testing technology, and in particular to a vehicle parking test, a parking anomaly management method, and a computer device. Background Art

[0002] With the development of intelligent vehicles, parking technology has gradually evolved from traditional driver-assisted parking to intelligent parking such as assisted parking and automatic parking. Early autonomous parking methods relied on the driver observing the parking environment and making relevant judgments to achieve parking. Current intelligent parking methods rely on devices such as reversing radar and reversing cameras to perceive the parking environment, obtain information, and then perform intelligent parking based on this perception.

[0003] Whether it is assisted parking or automatic parking technology, intelligent parking technology relies on vehicle perception technology to realize parking environment perception. If the perception information is inaccurate, it will cause safety hazards when the driver performs assisted parking based on the perception information, or cause safety hazards when the vehicle performs automatic parking based on the perception information.

[0004] Therefore, it is necessary to test parking technology and obtain test results on perception accuracy. This allows developers to analyze problems based on these test results and optimize parking technology. The key issue is how to test parking technology and obtain more intuitive perception accuracy test results. This allows developers to more intuitively analyze parking problems, identify anomalies, and optimize parking technology to improve vehicle perception accuracy. Summary of the Invention

[0005] The embodiments of the present application provide a vehicle parking test, a parking anomaly management method, and a computer device, which can more accurately display the perception information of the vehicle parking test and obtain more intuitive test results. Based on the more intuitive test results, it is possible to more intuitively analyze vehicle parking problems, thereby finding anomalies, optimizing vehicle parking technology, and improving vehicle perception accuracy.

[0006] To solve the above technical problems, in a first aspect, an embodiment of the present application provides a vehicle parking test method, the method comprising: obtaining perception information of a target vehicle during parking; generating a visualization interface based on the perception information, and displaying the visualization interface, the visualization interface comprising a panoramic image sub-interface and an electronic map sub-interface, the panoramic image sub-interface displays a panoramic image of the target vehicle, and the electronic map sub-interface displays mapping information of the panoramic image of the target vehicle; when an abnormal object and abnormal information corresponding to the abnormal object are determined based on the visualization interface, an abnormal object file is generated based on the abnormal information corresponding to the abnormal object; and an abnormal detection video is generated based on the abnormal object file, so as to obtain a first parking perception test result of the target vehicle based on the abnormal detection video.

[0007] Using the above technical solution, a panoramic image sub-interface for displaying panoramic images and an electronic map sub-interface for displaying panoramic image mapping information are generated based on the perception information obtained by the target vehicle during parking. Abnormal objects and abnormal information about the abnormal objects are determined based on the panoramic image sub-interface and the electronic map sub-interface. An abnormal object file is generated based on the abnormal information of the abnormal objects. An abnormality detection video is generated based on the abnormal object file. A first parking perception test result for the target vehicle is obtained based on the abnormality detection video. Thus, determining abnormal objects based on the visual interface allows for more intuitive identification of abnormal objects. Furthermore, generating an abnormality detection video based on the abnormal object file allows for more intuitive analysis of vehicle parking issues, further improving vehicle perception accuracy.

[0008] In a possible implementation of the first aspect above, the perception information includes vehicle surrounding environment information and vehicle position information, and a visualization interface is generated based on the perception information, including: obtaining a panoramic image based on the vehicle surrounding environment information to generate a panoramic image sub-interface; generating an electronic map sub-interface within a preset area based on the vehicle position information and the panoramic image.

[0009] By adopting the above technical solution, a panoramic image sub-interface is generated based on the vehicle's surrounding environment information, and an electronic map sub-interface within a preset area is generated based on the vehicle's position information and the panoramic image. This can obtain a more comprehensive display result of perception information, which is more conducive to perception anomaly analysis.

[0010] In a possible implementation of the first aspect above, determining the abnormal object and the abnormal information corresponding to the abnormal object according to the visualization interface includes: receiving the abnormal marking operation performed by the user according to the visualization interface, and determining the abnormal object and the abnormal information corresponding to the abnormal object according to the abnormal marking operation.

[0011] In a possible implementation of the first aspect above, receiving an abnormal marking operation performed by a user according to a visual interface includes: displaying a marking interface according to a marking trigger operation performed by the user through the visual interface; and receiving an abnormal marking operation performed by the user on the marking interface.

[0012] By adopting the above technical solution, the user can directly perform abnormal marking operations on the visual interface, which can more intuitively determine the abnormal object and the corresponding abnormal information, and can more accurately perform perception abnormality analysis.

[0013] In a possible implementation of the first aspect above, obtaining a first parking perception test result of the target vehicle based on the abnormality detection video includes: sending the abnormality detection video to a corresponding user so that the user performs an abnormality detection analysis based on the abnormality detection video to obtain the first parking perception test result of the target vehicle; or directly performing an abnormality detection analysis based on the abnormality detection video to obtain the first parking perception test result of the target vehicle.

[0014] By adopting the above technical solution, the first parking perception test result of the target vehicle is obtained based on the abnormality detection video, which can obtain the parking perception test result more intuitively and conveniently.

[0015] In a possible implementation of the first aspect above, the exception information of the exception object includes test information, target obstacle, exception type, problem description, video length, test package and test log path.

[0016] In a possible implementation of the first aspect, the exception object file is a comma-separated value file.

[0017] In a possible implementation of the first aspect above, the method further includes: fusing the panoramic image sub-interface and the electronic map sub-interface to obtain and display an auxiliary parking image for controlling the target vehicle to park in the target parking space based on the auxiliary parking image; determining parking result information of the target vehicle parking in the target parking space; and obtaining a second parking perception test result of the target vehicle based on the parking result information.

[0018] By adopting the above technical solution, the test vehicle can fully conduct intelligent parking tests by obtaining parking result information of the assisted parking according to the assisted parking image.

[0019] In a possible implementation of the first aspect above, the method further includes: determining perception position-related information of the target vehicle and the target obstacle when the target vehicle is located at any target position, the perception position-related information including multiple first position information of the target obstacle when the target vehicle is located at each target position obtained based on the perception algorithm and second position information of the target obstacle determined based on the distance information between the target vehicle and the target obstacle when the target vehicle is located at each target position obtained based on manual measurement; and obtaining a third parking perception test result of the target vehicle based on the multiple first position information and the second position information.

[0020] By adopting the above technical solution and testing the position information of obstacles perceived by the target vehicle, the vehicle's perception technology can be better optimized.

[0021] In a possible implementation of the first aspect above, multiple first position information of the target obstacle when the target vehicle is located at each target position is obtained based on the perception algorithm, including: determining the target obstacle area in the panoramic image sub-interface based on a deep learning model; detecting the target obstacle area to obtain multiple first position information of the target obstacle.

[0022] In a possible implementation of the first aspect above, when the target obstacle includes the corner points of the target parking space, the method also includes obtaining the distance information between the target vehicle and the corner points of the target parking space when the target vehicle is located at the target position in the following manner: when the target vehicle is located at the target position, a coordinate system is established with the center point of the rear axle of the target vehicle as the origin, the forward direction of the target vehicle as the x-axis, and the direction perpendicular to the x-axis as the y-axis; the coordinate information of the left rear wheel and the coordinate information of the right rear wheel of the target vehicle are determined; the distance information between the left rear wheel of the target vehicle and the first corner point of the target parking space, as well as the distance information between the right rear wheel of the target vehicle and the first corner point of the target parking space are determined; and the distance information between the left rear wheel or the right rear wheel and the other corner points of the target parking space except the first corner point is determined.

[0023] In a possible implementation of the first aspect above, the first position information is first coordinate information, and the second position information is second coordinate information. The third parking perception test result of the target vehicle is obtained based on the multiple first position information and the second position information, including: determining multiple first differences between the first numerical values ​​corresponding to the first direction in the multiple first coordinate information and the second numerical values ​​corresponding to the second direction in the second coordinate information, and determining a minimum difference, a maximum difference, an average value of the first differences, and a first target difference at a preset ratio after sorting the multiple first differences in ascending order; and determining the minimum difference, the maximum difference, the average value of the second differences, and the second target difference at a preset ratio after sorting the multiple second differences in ascending order; and obtaining the third parking perception test result of the target vehicle based on the target obstacle, the target position, and the minimum difference, the maximum difference, the average value of the first differences, the minimum difference, the maximum difference, the average value of the second differences, and the second target difference of the first target difference and the second differences.

[0024] In a possible implementation of the first aspect above, the method further includes: determining whether the parking environment of the target vehicle complies with specifications based on a building information model.

[0025] In a second aspect, the implementation of the present application also discloses a vehicle parking management method, including: determining a parking perception test result, the parking perception test result including a first parking perception test result and a second parking perception test result, the first parking perception test result and the second parking perception test result being obtained based on the vehicle parking test method provided in the first aspect above; adjusting the parking strategy of the target vehicle according to the parking test result.

[0026] By adopting the above technical solution and adjusting the parking strategy of the target vehicle according to the parking test results, the vehicle parking technology can be optimized and the user experience can be improved.

[0027] In a third aspect, the implementation of the present application further discloses a computer device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory, so that the computer device implements the vehicle parking test method provided by any one of the implementations of the first aspect above, or implements the vehicle parking management method provided by the second aspect above.

[0028] In a fourth aspect, the implementation of the present application further discloses a computer-readable storage medium, which stores a computer program. The computer program can be executed by a computer device to implement the vehicle parking test method provided by any implementation of the first aspect above, or to implement the vehicle parking management method provided by the second aspect above.

[0029] In a fifth aspect, the implementation of the present application further discloses a computer program product, including a computer program. When the computer program is executed by a computer device, it implements the vehicle parking test method provided by any one of the implementation methods of the first aspect above, or implements the vehicle parking management method provided by the second aspect above. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings used in the description of the implementation methods.

[0031] Figure 1 A schematic diagram of a process flow of a vehicle parking test method provided by an embodiment of the present invention;

[0032] Figure 2 A schematic diagram of a visualization interface provided by an embodiment of the present invention;

[0033] Figure 3 A schematic diagram of a dot-marking interface provided by an embodiment of the present invention;

[0034] Figure 4 A schematic diagram of an abnormal object file provided by an embodiment of the present invention;

[0035] Figure 5 A schematic diagram of another flow chart of a vehicle parking test method provided by an embodiment of the present invention;

[0036] Figure 6 A schematic diagram of the perception distance test principle provided by an embodiment of the present invention;

[0037] Figure 7 A schematic diagram of distance information between a target vehicle and a target parking space provided by an embodiment of the present invention;

[0038] Figure 8 A schematic diagram of a third parking perception test result provided by an embodiment of the present invention;

[0039] Figure 9 A schematic diagram of a process flow of a vehicle parking management method provided by an embodiment of the present invention;

[0040] Figure 10 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0041] As mentioned previously, parking technology needs to be tested to obtain test results on perception accuracy. This allows developers to analyze issues based on these test results and optimize the technology. Of paramount importance is how to test parking technology and obtain more intuitive perception accuracy test results, allowing developers to more intuitively analyze parking issues, identify anomalies, and optimize parking technology to improve perception accuracy.

[0042] Based on this, the present application provides a vehicle parking test method that generates a visual interface based on the perception information of the vehicle during parking, identifies abnormal objects in the visual interface and the abnormal information corresponding to the abnormal objects, generates an abnormal object file, generates an abnormality detection video based on the abnormal object file, and then obtains the vehicle parking perception test results based on the abnormality detection video. In this way, the visual interface can more intuitively analyze vehicle parking problems and identify abnormal points, and the abnormality detection video can facilitate developers to more intuitively optimize vehicle parking.

[0043] like Figure 1 As shown, the vehicle parking test method provided by the implementation of this application specifically includes the following steps.

[0044] S100: Acquire perception information of the target vehicle during parking.

[0045] S200, generating a visualization interface based on the perception information and displaying the visualization interface, the visualization interface including a panoramic image sub-interface and an electronic map sub-interface, the panoramic image sub-interface displays a panoramic image of the target vehicle, and the electronic map sub-interface displays mapping information of the panoramic image of the target vehicle.

[0046] S300 , when an abnormal object and abnormal information corresponding to the abnormal object are determined according to the visual interface, an abnormal object file is generated according to the abnormal information corresponding to the abnormal object.

[0047] S400: Generate an abnormality detection video according to the abnormal object file, so as to obtain a first parking perception test result of the target vehicle according to the abnormality detection video.

[0048] First, step S100 is executed to obtain perception information of the target vehicle during parking, wherein the perception information includes vehicle surrounding environment information and vehicle position information.

[0049] The vehicle's surrounding environment information is captured by the vehicle's 360-degree panoramic camera. The vehicle's position information is obtained by a vehicle positioning module, which can specifically be a high-precision positioning module.

[0050] Next, step S200 is executed to generate a visualization interface according to the perception information and display the visualization interface.

[0051] like Figure 2 As shown, the visualization interface includes panoramic image sub-interfaces (B, D, F) and electronic map sub-interfaces (A, C, E).

[0052] Among them, the panoramic image sub-interface displays the panoramic image of the target vehicle, such as Figure 2 As shown, the panoramic image includes a panoramic picture obtained based on the captured picture, as well as vehicles, obstacles and parking spaces in the panoramic picture.

[0053] The electronic map sub-interface displays the mapping information of the target vehicle's panoramic image, such as Figure 2 As shown, the mapping information includes vehicles, obstacles, and parking space numbers, parking space corner coordinates, etc. It also includes vehicle driving trajectory information.

[0054] The electronic map sub-interface also displays other alternative parking spaces beyond the panoramic image range, expanding the range of parking space selection and improving the user experience.

[0055] In the implementation of the present application, a visualization interface is generated based on the perception information, including: obtaining a panoramic image based on the vehicle's surrounding environment information to generate a panoramic image sub-interface, and generating an electronic map sub-interface within a preset area based on the vehicle's position information and the panoramic image.

[0056] Exemplarily, a panoramic image of the target vehicle is displayed, and the parking space, each corner point of the parking space, the parking space number, and obstacles in the panoramic image are marked and displayed to form a panoramic image sub-interface.

[0057] Furthermore, according to the vehicle position information and the panoramic image corresponding to the vehicle, the vehicle and the panoramic image are filled and mapped, and the incomplete parking spaces in the panoramic image are completed to generate an electronic map sub-interface. Figure 2 As shown, A is a single-frame display interface, and C is a fusion display interface generated by mapping fusion based on the F image.

[0058] Next, step S300 is executed. When the abnormal object and the abnormal information corresponding to the abnormal object are determined according to the visual interface, an abnormal object file is generated according to the abnormal information corresponding to the abnormal object.

[0059] In the implementation of the present application, determining the abnormal object and the abnormal information corresponding to the abnormal object according to the visual interface includes: receiving the abnormal marking operation performed by the user according to the visual interface, and determining the abnormal object and the abnormal information corresponding to the abnormal object according to the abnormal marking operation.

[0060] The exception information of the exception object includes test time, test object, exception type, problem description, video length, test package and test log path.

[0061] Furthermore, receiving an abnormal marking operation performed by the user according to the visual interface includes: displaying the marking interface according to the marking trigger operation performed by the user through the visual interface; and receiving the abnormal marking operation performed by the user on the marking interface.

[0062] For example, when the user determines that an object is displayed incorrectly based on the visual interface, he can click on the corresponding area to perform an abnormal point trigger operation, and then jump to the following example: Figure 3 The dot interface shown automatically fills in the time corresponding to the panoramic image and the mapping information of the panoramic image in the visual interface, generates the test time, and determines the test object corresponding to the user's click area, and automatically fills in the test object. Of course, when the test object is filled in incorrectly, the user can modify it and obtain the corresponding log / bag package path. The user selects the exception type and video length and fills in the problem description. Of course, if Figure 3 As shown, users can also delete and copy abnormal information.

[0063] Of course, users can also add new data, import historical data, describe test data, visualize test data, and save data.

[0064] When the user clicks to save the data, the following Figure 4 The exception object file shown.

[0065] In the implementation of this application, the exception object file is a comma-separated values ​​file (CSV file for short).

[0066] like Figure 4 As shown, the CSV file includes exception information of the exception object.

[0067] Next, step S400 is executed to generate an abnormality detection video according to the abnormal object file, so as to obtain a first parking perception test result of the target vehicle according to the abnormality detection video.

[0068] In one implementation of the present application, obtaining a first parking perception test result of a target vehicle based on an abnormality detection video includes: sending the abnormality detection video to a corresponding user so that the user performs an abnormality detection analysis based on the abnormality detection video to obtain the first parking perception test result of the target vehicle.

[0069] Exemplarily, an anomaly detection video of each abnormal object is generated based on the test time, test object, problem description, video length, and bag package / log path in the abnormal object file, so that developers (i.e., users) can intuitively study the anomaly detection video to determine the parking perception problem of the target vehicle (as an example of the first parking perception test result).

[0070] The anomaly detection video file name includes information such as the test object, anomaly type, and problem description. For example, the anomaly detection video file name is [wall_wall missed detection_corner wall not detected 3_8815.mp4].

[0071] In another implementation of the present application, obtaining a first parking perception test result of the target vehicle based on the abnormality detection video includes: directly performing an abnormality detection analysis based on the abnormality detection video to obtain the first parking perception test result of the target vehicle.

[0072] Exemplarily, an anomaly detection tool is used to perform an anomaly detection analysis based on the anomaly detection video to identify abnormal points to obtain parking perception problems of the target vehicle (as an example of the first parking perception test result).

[0073] The implementation method of this application designs a problem discovery tool for visualizing parking scene perception results. This tool generates a visualization interface based on vehicle perception information, displays the vehicle perception information on the vehicle's large screen, and demonstrates the entire process of a fully automatic parking scenario, that is, the entire process from the start of parking to the vehicle parking in the target parking space. A tool for recording and archiving real-time parking scene perception problems is also designed to record abnormal information of abnormal objects identified by the user and generate corresponding abnormal object files. This allows an abnormality detection video to be generated based on the abnormal object file, and then, based on the abnormality detection video, a first parking perception test result is obtained. In this way, based on the visualization interface, abnormal object analysis can be intuitively performed, and based on the abnormality detection video, parking test analysis can be more intuitively performed to obtain the parking perception test result.

[0074] like Figure 5 As shown, in another implementation of the present application, the vehicle parking test method provided in the implementation of the present application also includes the following steps.

[0075] S500 , performing fusion processing on the panoramic image sub-interface and the electronic map sub-interface to obtain and display an auxiliary parking image for controlling a target vehicle to park in a target parking space according to the auxiliary parking image.

[0076] S600: Determine parking result information of the target vehicle parking in the target parking space.

[0077] S700: Obtain a second parking perception test result of the target vehicle according to the parking result information.

[0078] In the implementation of the present application, the panoramic image sub-interface and the electronic map sub-interface are displayed superimposed as an automatic parking image (i.e., an auxiliary parking image), so that the target vehicle can park in the target parking space according to the auxiliary parking image, and the parking result information of the target vehicle parking in the target parking space is determined, and then the second parking perception test result of the target vehicle is determined according to the parking result information.

[0079] Among them, the parking result information includes the current position information of the target vehicle and the current panoramic image information. The second parking perception test results include whether the target vehicle is completely parked in the target parking space, the target vehicle is not completely parked in the target parking space, the target vehicle is parked in the wrong parking space, etc.

[0080] Alternatively, the parking result information is the coordinate information of the four corner points of the target vehicle and the target parking space, so as to determine the second parking perception result of the target vehicle according to the coordinate information of the target vehicle and the coordinate information of the four corner points.

[0081] Furthermore, in assisted parking scenarios, the vehicle needs to sense the distance to the target obstacle in order to plan the parking path in real time based on the sensed distance information. Therefore, the distance information sensed by the target vehicle needs to be tested.

[0082] For example, a target vehicle's distance perception to the corners of a parking space can be tested in an underground garage to determine if the distance information it perceives to the corners of the parking space is accurate. Another example is a target vehicle's distance perception to various obstacles in an empty lot to determine if the distance information it perceives to the obstacles is accurate.

[0083] Currently, the industry generally uses a Remote Traffic Microwave Sensor (RT) to measure the distance between a target vehicle and a target obstacle. Parking perception test results are derived from the distance information sensed by the target vehicle and the distance information obtained by the RT. However, this equipment uses the Global Positioning System (GPS) for positioning. However, when parking in underground garages, the GPS signal is poor and cannot be obtained. Therefore, RT testing is not applicable in underground garages.

[0084] Furthermore, existing technologies have been used to improve signal strength in underground garages by installing signal adapters. This is then used to measure the distance between the target vehicle and the target obstacle using an RT device. However, signal adapters are complex and expensive to install, and due to limited signal coverage, only a few parking spaces can be tested. Furthermore, because distance sensing relies on the signal coverage of the signal adapters, poor signal coverage can lead to measurement accuracy errors.

[0085] Based on this, the implementation method of the present application provides a vehicle parking test method for testing the perception distance of a target vehicle to a target obstacle, including determining the perception position-related information of the target vehicle and the target obstacle when the target vehicle is located at any target position, the perception position-related information including multiple first position information of the target obstacle when the target vehicle is located at each target position obtained based on a perception algorithm and second position information of the target obstacle determined based on the distance information between the target vehicle and the target obstacle when the target vehicle is located at each target position obtained based on manual measurement. Based on the multiple first position information and the second position information, a third parking perception test result of the target vehicle is obtained.

[0086] In the implementation of the present application, when parking is performed, when the target vehicle is located at the target position, it also senses the first coordinate information of the target obstacle (as an example of the first position information). It is necessary to determine the second coordinate information of the target obstacle (as an example of the second position information) based on the manually measured distance information between the target vehicle and the target obstacle. The first coordinate information sensed by the target vehicle is tested based on the second coordinate information to obtain a third parking perception test result, so as to determine the accuracy of the target vehicle's perception of the distance to the target obstacle on the x-axis and y-axis based on the third parking perception test result.

[0087] Among them, a coordinate system is established with the center of the rear axle of the target vehicle as the origin, the forward direction of the target vehicle as the x-axis, and the direction perpendicular to the x-axis as the y-axis. When the target vehicle is at the target position, the distance of the target vehicle relative to the target obstacle in the x-axis direction and the distance of the target vehicle relative to the target obstacle in the y-axis direction are obtained, so that the first coordinate information of the target obstacle when the target vehicle is at the target position is obtained based on the distance in the x-axis direction and the distance in the y-axis direction.

[0088] In the implementation of the present application, multiple first coordinate information of the target vehicle and the target obstacle when the target vehicle is located at each target position is obtained based on the perception algorithm.

[0089] First, the target obstacle area in the panoramic image sub-interface is determined based on the deep learning model, and a coordinate system is established with the center of the vehicle's rear axle as the origin. The target obstacle area is detected to obtain multiple first coordinate information (x, y) of the target obstacle when the target vehicle is at the target position.

[0090] Exemplarily, the image in the panoramic imaging sub-interface during multiple tests is analyzed based on an image recognition model (as an example of a deep learning model) to obtain the target obstacle area, and the coordinates of the target obstacle are identified based on the perception algorithm to obtain the first coordinate information of the corresponding target obstacle.

[0091] Furthermore, in the implementation of the present application, when the target obstacle includes the corner points of the target parking space, the distance information between the target vehicle and the corner points of the target parking space when the target vehicle is located at the target position is obtained in the following manner: when the target vehicle is located at the target position, a coordinate system is established with the center point of the rear axle of the target vehicle as the origin, the forward direction of the target vehicle as the x-axis, and the direction perpendicular to the x-axis as the y-axis; the coordinate information of the left rear wheel and the right rear wheel of the target vehicle are determined, and based on manual measurement, the distance information between the left rear wheel of the target vehicle and the first corner point of the target parking space, the distance information between the right rear wheel of the target vehicle and the first corner point of the target parking space, and the distance information between the left rear wheel / right rear wheel of the target vehicle and other corner points of the target parking space except the first corner point are obtained.

[0092] Exemplarily, a coordinate system is established with the center point of the rear axle of the vehicle as the origin O, the vehicle's forward direction as the x-axis, and the direction perpendicular to the x-axis as the y-axis.

[0093] like Figure 6 As shown in part (a) and Figure 6 As shown in part (b), when the vehicle body width is known, the left rear wheel R1 is located on the y-axis with coordinates (0, Vehicle width), the right rear wheel R2 is located on the y-axis, with coordinates (0, vehicle width).

[0094] Assuming that the target vehicle is located at target position 1 and the driving trajectories are shown as 1, 2, and 3, the distance d1 from the left rear wheel R1 to the corner point A of the target parking space (as an example of the first corner point) and the distance d2 from the right rear wheel to the corner point A of the target parking space are manually measured using a tape measure, and the position information of the target parking space relative to the target vehicle (for example, whether the target parking space is on the left or right side of the target vehicle) is recorded. The coordinates of the left rear wheel R1, the coordinates of the right rear wheel R2, d1, d2, and the position information of the target parking space relative to the target vehicle are recorded and stored.

[0095] Furthermore, the distance d3 from the left rear wheel R1 to the parking space corner point B (as an example of other corner points), the distance d4 from the left rear wheel R1 to the parking space corner point C (as an example of other corner points), and the distance d5 from the left rear wheel R1 to the parking space corner point D (as an example of other corner points) are manually measured and stored to generate the following: Figure 7 The distances shown are stored in the file.

[0096] like Figure 7As shown in the figure, when the target vehicle stops at a certain point (also known as the target position), for example, when the target vehicle stops at point 1, a new test data is added. The test data includes the start time, end time, bag / log path, parking type, test number, point number, target parking number, target parking position, test type, vehicle width and wheelbase, distance to point A, distance to point B, distance to point C, distance to point D, length and width of the parking space, and other information.

[0097] The start time is the time the vehicle remains at the target location, and the end time is the time the vehicle leaves the target location. The start and end times can be automatically generated based on the panoramic imagery during the test. The bag / log path records the automatically generated perception algorithm calculation results for the target vehicle during the test. The parking space type is user-selectable, for example, horizontal, vertical, or inclined. The number of tests is the number of times the target vehicle is tested for the distance from the corresponding corner point to the same target parking space when the target vehicle is at the same target location. The point is the target location number of the target vehicle. The target parking space number is the target vehicle ID number. At the same moment, the target vehicle can identify all surrounding parking spaces and record each parking space ID in the perception results. The target parking space number is the number of the parking space to be tested. The test type is the parking space corner accuracy type. Different test types call different calculation scripts. The vehicle width and wheelbase are the vehicle width and wheelbase. For the same vehicle, the vehicle width and wheelbase remain unchanged. The distance to point A is the measured distance between R1 and R2 and point A, respectively. The distance to point B is the distance between R1 and / or R2 and point B. The distance to point C is the distance between R1 and / or R2 and point C. The distance to point D is the distance between R1 and / or R2 and point D.

[0098] Furthermore, the above test data is saved to obtain a distance test file to facilitate subsequent testing.

[0099] Furthermore, during a parking perception test, as the vehicle parks into the target parking space, the perception algorithm determines the coordinate information of each corner point of the target parking space when the target vehicle is at any target position. Furthermore, because the perception software performs multiple perceptions and tests based on the perception algorithm, the first coordinate information of each corner point of the target parking space when the target vehicle is at the target position represents multiple coordinate information perceived by the perception software during each test. In this way, multiple first coordinate information for the four corner points of the target parking space (e.g., corner points A, B, C, and D) can be obtained.

[0100] Furthermore, the coordinate information of the first corner point is obtained according to the coordinate information of the left rear wheel, the coordinate information of the right rear wheel, the distance between the left rear wheel and the first corner point, and the distance between the right rear wheel and the first corner point in the stored distance test file.

[0101] like Figure 6 As shown in part (c), circle 1 is established with the left rear wheel R1 as the origin and radius d1, and circle 2 is established with the right rear wheel R2 as the origin and radius d2. Circles 1 and 2 intersect at two points. Based on the location information of the target parking space, the remaining point A is the coordinate information of the corner point A of the target parking space (as an example of the second coordinate information of the first corner point).

[0102] Furthermore, the coordinate information of each corner point is determined based on the coordinate information of the first corner point (ie, corner point A) and the distance between the left rear wheel and each corner point of the target parking space except the first corner point.

[0103] Take parking space corner point B as an example, Figure 6 As shown in part (d), when the coordinates of corner point A, the coordinates of the left rear wheel R1, and the distance from the left rear wheel R1 to the parking space corner point B are known, the coordinate information of corner point B is calculated (as an example of the second coordinate information of other corner points).

[0104] Similarly, the coordinate information of the corner point c and the corner point d (as other examples of other corner points) is obtained (as examples of second coordinate information of other corner points).

[0105] Of course, in the implementation of the present application, the coordinate information of each corner point can also be determined based on the coordinate information of the first corner point (ie, corner point A) and the distance between the right rear wheel and the other corner points of the target parking space except the first corner point.

[0106] Furthermore, in the implementation of the present application, a third parking perception test result of the target vehicle is obtained based on multiple first position information and second position information, including: determining the difference between each first position information and the second position information; and determining the minimum difference, the maximum difference, the average of the differences, and the target difference at a preset proportion after sorting the differences from small to large; the third parking perception test result of the target vehicle is obtained based on the target obstacle, target position, the minimum difference, the maximum difference, the average of the differences, and the target difference.

[0107] For example, taking the first position information as the first coordinate information and the second position information as the second coordinate information as an example, when the target vehicle is parking in the target parking space, the perception algorithm based on the perception software will calculate multiple first coordinate information of the four corner points of the target parking space when the target vehicle is at any target position.

[0108] When the target vehicle is located at the corresponding target position, the distances between the left rear wheel and the right rear wheel of the vehicle relative to the corner point A, as well as the distances between the left rear wheel and the corner points B, C, and D are manually measured to generate a distance storage file. Based on the distances between the left rear wheel and the right rear wheel of the target vehicle at the corresponding target position relative to the first corner point of the target parking space in the distance storage file, the second coordinate information of the corner point A when the target vehicle is located at the target position is determined based on the method described above, and the second coordinate information of the corner points B, C, and D when the target vehicle is located at the target position is determined based on the method described above.

[0109] For the same target location and the same target parking space, multiple first differences between the numerical values ​​(first numerical values) corresponding to the x-axis (as an example of the first direction) in the multiple first coordinate information and the second coordinate information are determined, as well as the minimum difference, maximum difference, average of the first differences, and a first target difference at a preset proportional position after sorting the first differences in ascending order. Furthermore, multiple differences between the numerical values ​​(second numerical values) corresponding to the y-axis in the multiple first coordinate information and the second coordinate information are determined, as well as the minimum difference, maximum difference, average of the differences, and a second target difference at a preset proportional position after sorting the differences in ascending order.

[0110] The third parking perception test result is obtained based on the target obstacle, target position, and the minimum difference, maximum difference, difference average and first target difference in the first difference corresponding to the x-axis, and the minimum difference, maximum difference, difference average and second target difference in the second difference corresponding to the y-axis.

[0111] like Figure 8 As shown, taking the value corresponding to the x-axis as an example, based on the test, the distance test results of the target vehicle at different target positions (such as point 1, point 2, point 3, point 4, point 5) relative to the corner points of the target vehicle (such as corner point A (corner_a), corner point B (corner_b), corner point C (corner_c), corner point D (corner_d)) in the x-axis direction are obtained.

[0112] Wherein, min(m) is the minimum value of the difference in the x-axis direction between the first coordinate information and the second coordinate information obtained based on the perception algorithm during multiple tests. max(m) is the maximum value of the difference in the x-axis direction between the first coordinate information and the second coordinate information obtained based on the perception algorithm. mean(m) is the average value of the difference in the x-axis direction between the first coordinate information and the second coordinate information obtained based on the perception algorithm. std2 is the value of the difference in the x-axis direction between the first coordinate information and the second coordinate information obtained based on the perception algorithm, which is sorted from small to large and is within a preset range. The preset range can specifically be the value at the 95th percentile position of the sorted difference. Of course, the preset range can be adjusted according to actual needs, for example, it can be accurate to 95.44%.

[0113] For example, for point 1, min (m) is the minimum difference (0.0152) between the first coordinate information of corner point A (corner_a) obtained by the perception algorithm and the second coordinate information of corner point A (corner_a) obtained by manually measuring the distance to corner point A (corner_a) when the target vehicle is at point 1 during the parking test. Max (m) is the maximum difference (0.2011) between the first coordinate information of corner point A (corner_a) obtained by the perception algorithm and the second coordinate information of corner point A (corner_a) obtained by manually measuring the distance to corner point A (corner_a) when the target vehicle is at point 1 during the parking test. , mean(m) is the average value (0.062) of the difference in the x-axis direction between the first coordinate information of corner point A (corner_a) obtained based on the perception algorithm and the second coordinate information of corner point A (corner_a) obtained based on the manually measured distance to corner point A (corner_a) when the target vehicle is located at point 1 during the parking test. std2 is the value (0.1975) of the difference in the x-axis direction between the first coordinate information of corner point A (corner_a) obtained based on the perception algorithm and the second coordinate information of corner point A (corner_a) obtained based on the manually measured distance to corner point A (corner_a) when the target vehicle is located at point 1 during the parking test, sorted from small to large and within the preset range.

[0114] Of course, we will also get the distance test results of the target vehicle at different target positions (such as point 1, point 2, point 3, point 4, point 5) relative to the corner points of the target vehicle (such as corner point A (corner_a), corner point B (corner_b), corner point C (corner_c), corner point D (corner_d)) in the y-axis direction.

[0115] In the implementation of the present application, whether the parking environment of the target vehicle complies with the specifications is also determined based on the Building Information Model (BMI model).

[0116] For example, the BIM model can be used to automatically check whether the design of parking spaces, ramps, and driveways in the garage meets the specifications, thereby improving the speed and efficiency of inspection.

[0117] The vehicle parking test method provided by the implementation of this application tests the parking display image during the vehicle parking process, tests the parking plan during the vehicle parking process, and tests the distance perception during the vehicle parking process, making the vehicle parking test more comprehensive.

[0118] This application is implemented as follows: Figure 9 As shown, a method for managing abnormal parking of a vehicle is also provided, comprising:

[0119] S10, determining the parking perception test result.

[0120] The parking perception test result includes a first parking perception test result and a second parking perception test result.

[0121] Of course, the parking perception test result may also include a third parking perception test result.

[0122] The first parking perception test result, the second parking perception test result, and the third parking perception test result are obtained based on the aforementioned vehicle parking test method.

[0123] S20: Adjust the parking strategy of the target vehicle according to the parking perception test result.

[0124] For example, based on the parking test results, the target vehicle's perception algorithm, image generation technology, assisted parking technology, etc. are adjusted to overcome abnormal problems in the perception test results, so that the vehicle can achieve smart parking more accurately and better.

[0125] The vehicle parking test method and vehicle parking abnormality management method provided by the implementation of this application can be applied to computer equipment, where the computer equipment can specifically be a computer, a cloud computer, a remote server and other devices.

[0126] Taking a computer as an example, a parking scene perception result visualization problem discovery tool and a parking scene real-time perception problem record archiving tool are deployed in the computer. By obtaining the perception information of the vehicle, the parking scene perception result visualization problem discovery tool generates a visualization interface based on the perception information, allowing the user to identify the abnormal object based on the visualization interface and click the location of the abnormal object in the visualization interface to start the parking scene real-time perception problem record archiving tool, which displays the following information: Figure 3The abnormal information recording interface shown allows the user to enter abnormal information of the abnormal object. When the user's "save data" operation is received, an abnormal object file is generated, and the parking scene real-time perception problem recording and archiving tool also generates an abnormal detection video based on the abnormal object file, thereby obtaining the first parking perception test result of the target vehicle based on the abnormal detection video. Furthermore, the computer fuses the panoramic image sub-interface and the electronic map sub-interface to obtain and display the auxiliary parking image, connects the target vehicle, controls the target vehicle to park in the target parking space based on the auxiliary parking image, and obtains the parking result information of the target vehicle in the target parking space in real time. Based on the parking result information, the second parking perception test result of the target vehicle is obtained. Furthermore, the user remotely adjusts the parking strategy of the target vehicle based on the first parking perception test result and the second parking perception test result obtained by the computer.

[0127] See Figure 10 , Figure 10 The figure shows a schematic diagram of the structure of the computer device provided in the embodiment of the present application. Figure 10 As shown, the computer device may include: a transceiver 121 , a processor 122 , and a memory 123 .

[0128] Processor 122 executes computer-executable instructions stored in memory, causing processor 122 to implement the technical solutions of the vehicle parking test method or vehicle parking anomaly management method described in the above-mentioned embodiments. Processor 122 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0129] The memory 123 is connected to the processor 122 via a system bus and communicates with the processor 122. The memory 123 is used to store computer program instructions.

[0130] By way of example and not limitation, memory 123 may include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more thereof. Where appropriate, memory 123 may include removable or non-removable (or fixed) media. Where appropriate, memory 123 may be internal or external to the integrated gateway device. In certain embodiments, memory 123 is a non-volatile solid-state memory. In certain embodiments, memory 123 includes read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), an electrically alterable read-only memory (EAROM), or flash memory, or a combination of two or more thereof. The transceiver 121 may be used to obtain tasks to be executed and configuration information of the tasks to be executed.

[0131] The system bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, among others. System buses can be divided into address buses, data buses, and control buses. For ease of illustration, the diagram uses only a single thick line, but this does not imply a single bus or type of bus. Transceivers enable communication between the database access device and other computers (such as clients, read-write libraries, and read-only libraries). Memory may include random access memory (RAM) and non-volatile memory.

[0132] An embodiment of the present application also provides a chip for running instructions, which is used to execute the technical solutions of the vehicle parking test method, vehicle parking management method, or vehicle parking abnormality management method in the above embodiments.

[0133] An embodiment of the present application also provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed on a processor of a computer device, the processor of the computer device executes the technical solution of the vehicle parking test method or vehicle parking management method of the above-mentioned embodiment.

[0134] In some possible implementations, various aspects of the method provided in the present application can also be implemented in the form of a program product, which includes program code. When the program product runs on a processor of a computer device, the program code is used to enable the processor of the computer device to execute the steps of the method according to the various exemplary implementations of the present application described above in this specification. For example, the computer device can execute the vehicle parking test method or vehicle parking management method recorded in the embodiments of the present application.

[0135] The program product may employ any combination of one or more readable media. The readable medium may be a readable data medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CDROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0136] The implementation of the present application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium. When the at least one processor executes the computer program, it can implement the technical solutions of the vehicle parking test method or the vehicle parking management method in the above-mentioned embodiment.

[0137] It should be noted that, in addition to the implementation of the present application described in the above-mentioned specific embodiments, those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Although the description of the present application is introduced in conjunction with the preferred embodiment, this does not mean that the features of this invention are limited to this implementation. On the contrary, the purpose of introducing the invention in conjunction with the implementation is to cover other options or modifications that may be extended from the present application. In order to provide an in-depth understanding of the present application, the above description contains many specific details, and the present application can also be implemented without using these details. In addition, in order to avoid confusion or blurring the focus of the present application, some specific details will be omitted in the description. It should be noted that, in the absence of conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0138] It should be noted that in this specification, similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0139] It should be noted that the terms "first", "second", etc. are only used for distinction and description, and cannot be understood as indicating or implying relative importance.

[0140] It should be noted that in the accompanying drawings, some structural or method features may be shown in a specific arrangement and / or order. However, it should be understood that such a specific arrangement and / or order may not be required. Rather, in some embodiments, these features may be arranged in a manner and / or order different from that shown in the illustrative drawings. In addition, the inclusion of structural or method features in a particular figure does not imply that such features are required in all embodiments, and in some embodiments, these features may not be included or may be combined with other features.

[0141] Although the present application has been illustrated and described with reference to certain preferred implementations of the present application, those skilled in the art should understand that the above description is provided as a further detailed explanation of the present application in conjunction with specific implementations, and that the specific implementation of the present application should not be limited to these descriptions. Those skilled in the art may make various changes in form and details, including simple deductions or substitutions, without departing from the spirit and scope of the present application.

Claims

1. A vehicle parking test method, characterized in that: The method comprises: Acquire the perception information of the target vehicle during parking; generating a visualization interface based on the perception information and displaying the visualization interface, wherein the visualization interface includes a panoramic image sub-interface and an electronic map sub-interface, wherein the panoramic image sub-interface displays a panoramic image of the target vehicle, and the electronic map sub-interface displays mapping information of the panoramic image of the target vehicle; In a case where an abnormal object and abnormal information corresponding to the abnormal object are determined according to the visual interface, generating an abnormal object file according to the abnormal information corresponding to the abnormal object; An abnormality detection video is generated according to the abnormal object file, so as to obtain a first parking perception test result of the target vehicle according to the abnormality detection video.

2. The vehicle parking test method according to claim 1, characterized in that: The perception information includes vehicle surrounding environment information and vehicle position information, and generating a visualization interface based on the perception information includes: Obtaining a panoramic image based on the vehicle surrounding environment information to generate the panoramic image sub-interface; The electronic map sub-interface within a preset area is generated according to the vehicle position information and the panoramic image.

3. The vehicle parking test method according to claim 2, characterized in that: Determining an abnormal object and abnormal information corresponding to the abnormal object according to the visual interface includes: An abnormality marking operation performed by a user according to the visual interface is received, and an abnormal object and abnormal information corresponding to the abnormal object are determined according to the abnormality marking operation.

4. The vehicle parking test method according to claim 3, characterized in that: Receiving an abnormality marking operation performed by the user according to the visual interface, including: Displaying a dot-triggering interface according to a dot-triggering operation performed by the user through the visual interface; Receive the abnormal marking operation performed by the user on the marking interface.

5. The vehicle parking test method according to claim 4, characterized in that: Obtaining a first parking perception test result of the target vehicle according to the abnormality detection video includes: sending the abnormality detection video to a corresponding user, so that the user performs abnormality detection analysis based on the abnormality detection video to obtain a first parking perception test result of the target vehicle; or Anomaly detection analysis is directly performed based on the anomaly detection video to obtain a first parking perception test result of the target vehicle.

6. The vehicle parking test method according to claim 5, characterized in that: The abnormal information of the abnormal object includes test information, target obstacle, abnormal type, problem description, video length, test package and test log path.

7. The vehicle parking test method according to claim 6, characterized in that: The exception object file is a comma-separated value file.

8. The vehicle parking test method according to claim 7, characterized in that: The method further comprises: fusing the panoramic image sub-interface and the electronic map sub-interface to obtain and display an auxiliary parking image, so as to control the target vehicle to park in a target parking space according to the auxiliary parking image; Determining parking result information of the target vehicle parking in the target parking space; A second parking perception test result of the target vehicle is obtained according to the parking result information.

9. A method for managing abnormal parking of vehicles, characterized in that: The method comprises: Determining a parking perception test result, the parking perception test result including a first parking perception test result and a second parking perception test result, the first parking perception test result and the second parking perception test result being obtained based on the vehicle parking test method according to claim 8; Adjusting the parking strategy of the target vehicle according to the parking perception test result.

10. A computer device, characterized in that: The computer device comprises: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to enable the computer device to implement the vehicle parking test method described in any one of claims 1 to 8, or to enable the computer device to implement the vehicle parking abnormality management method described in claim 9.

Images