A method, device, medium and equipment for evaluating laser radar performance

Abstract

The present invention provides a method, device, medium and equipment for evaluating laser radar performance indicators. The method comprises: in different types of test scenarios, respectively obtaining test data after the radar to be tested scans a static test component; analyzing the test data to obtain test results of static performance indicators of the radar to be tested; the static performance indicators include: ranging accuracy, ranging consistency, measurement intensity, number of isolated noise points, effective point ratio and material recognition rate; obtaining the first point cloud data after the radar to be tested scans a dynamic target; obtaining test results of dynamic performance indicators of the radar to be tested; the dynamic performance indicators include: human leg recognition rate and ground object mapping accuracy; in this way, static testing and dynamic testing of the radar to be tested under a variety of test environments can comprehensively and effectively evaluate the performance of the radar to be tested, thereby improving the building accuracy of the robot.

Description

Technical Field

[0001] The present invention belongs to the field of robotics, and in particular relates to a method, device, medium and equipment for evaluating laser radar performance indicators. Background Art

[0002] A robot is a machine device that performs work automatically. It can accept instructions from users, communicate with users, run pre-programmed programs, and act according to strategies customized by artificial intelligence technology. At present, it has important uses in industry, medicine, agriculture and even the military.

[0003] Usually, the main sensors of robots include lidar, camera, inertial measurement unit (IMU), etc. Without reliable, stable and applicable sensor support, the robot cannot complete the specified task efficiently and with high quality. Therefore, effective evaluation of the reliability, stability, applicability and other performance of the sensor is the primary task in the early stage of robot construction. Among them, the performance evaluation of lidar is particularly important.

[0004] The relevant technology only evaluates some performance indicators of the radar in a single scenario, but the application scenarios of robots are relatively complex, so the existing evaluation methods cannot effectively evaluate the performance of the lidar, which in turn affects the accuracy of the robot. Summary of the invention

[0005] In response to the problems existing in the prior art, the embodiments of the present invention provide a method, device, medium and equipment for evaluating laser radar performance indicators, which are used to solve the technical problem that the prior art cannot comprehensively and effectively evaluate the performance of laser radar.

[0006] According to a first aspect of the present invention, there is provided a method for evaluating laser radar performance, the method comprising:

[0007] In different types of test scenarios, test data after the radar to be tested scans the static test component is obtained respectively; the test scenarios include: normal scene, strong light scene, particle fog scene, non-room temperature scene and humid scene; the static test component includes: performance test board, performance test tube, strength test board and performance evaluation board;

[0008] Analyze the test data and obtain test results of static performance indicators of the radar to be tested; the static performance indicators include: ranging accuracy, ranging consistency, measurement intensity, number of isolated noise points, effective point ratio and material recognition rate;

[0009] Acquire the first point cloud data after the radar to be tested scans the dynamic target;

[0010] The first point cloud data is analyzed to obtain test results of dynamic performance indicators of the radar to be tested; the dynamic performance indicators include: human leg recognition rate and ground object mapping accuracy.

[0011] In the above solution, when the static test component is the performance test board, the step of respectively obtaining test data after the radar to be tested scans the static test component includes:

[0012] In each of the test scenarios, when the distance between the radar to be tested and the performance test board is a first preset distance, a first test distance after the radar to be tested scans the performance test board is respectively obtained;

[0013] When the distance between the radar to be tested and the performance test board is the second preset distance, the second test distance after the radar to be tested scans the performance test board is obtained respectively; wherein,

[0014] The performance test board includes: a performance test board with a first reflectivity and a performance test board with a second reflectivity; the first reflectivity is different from the second reflectivity; the first distance is 5 to 30 cm; the second distance is 1 to 10 m; the target test scene is all scenes of the normal scene, the strong light scene, the particle fog scene, the non-room temperature scene and the humid scene.

[0015] In the above solution, when the static test component is the performance test cylinder, the step of respectively obtaining test data after the radar to be tested scans the static test component includes:

[0016] In each of the test scenarios, when the radar to be tested is located at the center of the performance test cylinder, a third test distance is obtained after the radar to be tested scans the performance test cylinder at different scanning angles; wherein,

[0017] The performance test cylinder includes: a test cylinder formed by a performance test plate of a first reflectivity and a test cylinder formed by a performance test plate of a second reflectivity; the target test scenes are all scenes among the normal scene, the strong light scene, the particle fog scene, the non-room temperature scene and the humid scene.

[0018] In the above scheme, when the static test component is the strength test board, the step of respectively obtaining the test data after the radar to be tested scans the static test component includes:

[0019] In each of the test scenarios, when the distance between the radar to be tested and the strength test board is a third preset distance, the strength value after the radar to be tested scans the strength test board is obtained respectively; wherein,

[0020] The strength test board is a combined test board formed by splicing a performance test board of a first reflectivity and a performance test board of a second reflectivity; the target test scene is all scenes including the normal scene, the strong light scene, the particle fog scene, the non-room temperature scene and the humid scene.

[0021] In the above scheme, the test data is analyzed and the test results of the static performance indicators of the radar to be tested are obtained, including:

[0022] When the static test component is the performance test board, a first distance difference between a first preset distance and a first test distance, and a second distance difference between a second preset distance and a second test distance are obtained; a ranging accuracy of the radar to be tested is determined according to the first distance difference and the second distance difference; or,

[0023] When the static test component is the performance test cylinder, the ranging consistency of the radar to be tested is determined according to the corresponding third test distances obtained after the radar to be tested scans the performance test cylinder at different scanning angles; or

[0024] When the static test component is a strength test board, the strength value distribution result is determined according to the strength value after the radar to be tested scans the strength test board, and the measurement strength of the radar to be tested is determined according to the strength value distribution result.

[0025] In the above solution, the step of analyzing the first point cloud data and obtaining the test results of the dynamic performance indicators of the radar to be tested includes:

[0026] When the dynamic performance indicator is the human leg recognition rate, matching the first point cloud data using the trained human leg point cloud model to obtain a matching result;

[0027] The human leg recognition rate is determined according to the matching result.

[0028] In the above solution, the analyzing the first point cloud data to obtain the dynamic performance index of the radar to be tested includes:

[0029] When the dynamic performance indicator is the ground object mapping accuracy, obtaining first point cloud data corresponding to at least three radars to be tested scanning the same mapping environment;

[0030] Using the same mapping algorithm to perform closed-loop mapping on each of the first point cloud data, respectively, to obtain the corresponding ground feature maps;

[0031] The above-mentioned ground object maps are matched simultaneously, and the ground object mapping accuracy of each radar to be tested is determined according to the matching results.

[0032] A second aspect of the present invention provides a device for evaluating laser radar performance, the device comprising:

[0033] The first acquisition unit is used to respectively acquire test data after the radar to be tested scans the static test component in different types of test scenarios; the test scenarios include: normal scene, strong light scene, particle fog scene, non-room temperature scene and humid scene; the static test component includes: performance test board, performance test tube, strength test board and performance evaluation board;

[0034] A first analysis unit is used to analyze the test data and obtain test results of static performance indicators of the radar to be tested; the static performance indicators include: ranging accuracy, ranging consistency, measurement intensity, number of isolated noise points, effective point ratio and material recognition rate;

[0035] A second acquisition unit acquires first point cloud data after the radar to be tested scans the dynamic target;

[0036] The second analysis unit analyzes the first point cloud data and obtains test results of dynamic performance indicators of the radar to be tested; the dynamic performance indicators include: human leg recognition rate and ground object mapping accuracy.

[0037] According to a third aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method described in any one of the first aspects is implemented.

[0038] According to a fourth aspect of the present invention, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in any one of the first aspects is implemented.

[0039] The present invention provides a method, device, medium and equipment for evaluating laser radar performance indicators. The method comprises: obtaining test data after the radar to be tested scans a static test component in different types of test scenes; the test scenes comprise: a normal scene, a strong light scene, a particle fog scene, a non-room temperature scene and a humid scene; the static test component comprises: a performance test board, a performance test tube, a strength test board and a performance evaluation board; analyzing the test data and obtaining test results of the static performance indicators of the radar to be tested; the static performance indicators comprise: ranging accuracy, ranging consistency, measurement intensity, number of isolated noise points, effective point ratio and material recognition rate; obtaining first point cloud data after the radar to be tested scans a dynamic target; analyzing the first point cloud data The cloud data is analyzed, and the test results of the dynamic performance indicators of the radar to be tested are obtained; the dynamic performance indicators include: human leg recognition rate and ground object mapping accuracy; in this way, the present application takes into account the diversity of the robot's working environment, and therefore performs static tests and dynamic tests on the radar to be tested in a variety of test scenarios, and tests static test indicators such as ranging accuracy, ranging consistency, measurement intensity, number of isolated noise points, effective point ratio and material recognition rate of the radar to be tested; at the same time, in the above-mentioned different test environments, the human leg recognition rate and ground object mapping accuracy of the radar to be tested are tested. It can be seen that the present application performs static tests and dynamic tests on the radar to be tested in a variety of test environments, which can comprehensively and effectively evaluate the performance of the radar to be tested, thereby improving the construction accuracy of the robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0041] Figure 1 A schematic flow chart of a method for evaluating laser radar performance provided by an embodiment of the present invention;

[0042] Figure 2 A schematic diagram of the structure of a device for evaluating laser radar performance provided by an embodiment of the present invention;

[0043] Figure 3 A schematic diagram of the computer device structure provided by an embodiment of the present invention;

[0044] Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0046] This embodiment provides a method for evaluating the performance of a laser radar. Figure 1 As shown, the method comprises the following steps:

[0047] S110, in different types of test scenarios, respectively obtaining test data after the radar to be tested scans the static test component; the test scenarios include: normal scene, strong light scene, particle fog scene, non-room temperature scene and humid scene; the static test component includes: performance test board, performance test tube, strength test board and performance evaluation board;

[0048] In order to comprehensively and effectively evaluate the performance of the radar to be tested and thus improve the accuracy of robot construction, this embodiment obtains test data after the radar to be tested scans the static test component in different types of test scenarios.

[0049] The test scenarios in this embodiment include: normal scene, strong light scene, particle fog scene, non-room temperature scene and humid scene; the static test components include: performance test board, performance test tube and strength test board.

[0050] Because the robot may work in different scenarios, this embodiment determines the test scenario based on the environment in which the robot may work. The normal scenario can be understood as an environment with constant temperature (such as a temperature of about 25°C) and constant humidity (humidity of 45% to 60%); the strong light environment can be an environment with a light intensity of 70,000 to 100,000 lux, the particle fog scene can be understood as a fog scene with a horizontal visibility of less than 1 km, the non-room temperature scene can be understood as a scene with a temperature below 0°C and a temperature above 36°C; the humid scene can be understood as an environment with an ambient humidity greater than 70%.

[0051] When performing performance testing on the radar to be tested, this embodiment needs to test the radar to be tested in the above five test environments respectively to obtain corresponding test data.

[0052] In an optional embodiment, when the static test component is a performance test board, obtaining test data after the radar to be tested scans the static test component includes:

[0053] In each test scenario, when the distance between the radar to be tested and the performance test board is a first preset distance, a first test distance after the radar to be tested scans the performance test board is respectively obtained;

[0054] When the distance between the radar to be tested and the performance test board is the second preset distance, the second test distance after the radar to be tested scans the performance test board is obtained respectively; wherein,

[0055] The performance test board includes: a performance test board with a first reflectivity and a performance test board with a second reflectivity; the first reflectivity is different from the second reflectivity; the first distance is 5 to 30 cm; the second distance is 1 to 10 m; the target test scenes are all scenes in the normal scene, strong light scene, particle fog scene, non-room temperature scene and the humid scene.

[0056] Specifically, the performance test board with the first reflectivity may be a performance test board with a reflectivity of 80-90%, such as a white performance test board; the performance test board with the second reflectivity may be a performance test board with a reflectivity of 10-20%, such as a black performance test board.

[0057] Then in each test scenario, the radar to be tested needs to separately test the performance test board of the first reflectivity and the performance test board of the second reflectivity; and when testing separately, it is also necessary to separately test the first distance and the second distance.

[0058] For example, assuming that in a normal scenario, the radar to be tested needs to scan a performance test board of a first reflectivity. First, the performance test board of the first reflectivity is scanned at a first preset distance. In order to ensure the test accuracy, the first preset distance can be: 10cm, 20cm and 30cm; that is, the performance test board of the first reflectivity needs to be scanned at 10, 20cm and 30cm respectively.

[0059] Then, the performance test board of the second reflectivity is scanned at the first preset distance. Similarly, the performance test board of the first reflectivity needs to be scanned at 10 cm, 20 cm and 30 cm.

[0060] Secondly, the performance test board of the first reflectivity is scanned at a second distance. In order to ensure the test accuracy, the second preset distance can be 1m, 2m, 3m, 4m, 5m, 6m, 7m, 8m, 9m and 10m; that is, the performance test board of the first reflectivity needs to be scanned at 1m, 2m, 3m, 4m, 5m, 6m, 7m, 8m, 9m and 10m respectively.

[0061] Finally, the performance test board of the second reflectivity is scanned at the second preset distance. Similarly, the performance test board of the second reflectivity needs to be scanned at 1m, 2m, 3m, 4m, 5m, 6m, 7m, 8m, 9m and 10m.

[0062] The testing process in other test scenarios is the same as the testing process in normal scenarios, so it will not be repeated here.

[0063] After the test is completed, the first test distance after the radar to be tested scans the performance test board and the second test distance after the radar to be tested scans the performance test board in each test scenario can be obtained.

[0064] In addition, the robot may scan at different angles during actual work, so it is also necessary to test the ranging consistency index of the radar to be tested. In this embodiment, a performance test tube is used to test the radar to be tested.

[0065] In an optional embodiment, when the static test component is a performance test cylinder, obtaining test data after the radar to be tested scans the static test component includes:

[0066] In each test scenario, when the radar to be tested is located at the center of the performance test cylinder, the third test distance after the radar to be tested scans the performance test cylinder at different scanning angles is obtained respectively; wherein,

[0067] The performance test cylinder includes: a test cylinder formed by a performance test plate of a first reflectivity and a test cylinder formed by a performance test plate of a second reflectivity; the target test scenes include all scenes of normal scenes, strong light scenes, particle fog scenes, non-room temperature scenes and humid scenes.

[0068] Taking a test cylinder formed by a performance test plate of a first reflectivity as an example, the radar to be tested can be placed at the center of the test cylinder (which can be understood as the center of a circle), and then the performance test cylinder can be scanned at different scanning angles.

[0069] If the third test distances obtained at each scanning angle are the same, it means that the ranging consistency of the radar to be tested is good.

[0070] Furthermore, it is also necessary to test the scanning intensity of the radar to be tested. In an optional embodiment, when the static test component is a strength test board, test data after the radar to be tested scans the static test component is obtained respectively, including:

[0071] In each test scenario, when the distance between the radar to be tested and the strength test board is a third preset distance, the strength value after the radar to be tested scans the strength test board is obtained respectively; wherein,

[0072] The strength test board is a combined test board formed by splicing a performance test board with a first reflectivity and a performance test board with a second reflectivity; the target test scenes are all scenes including normal scenes, strong light scenes, particle fog scenes, non-room temperature scenes and humid scenes.

[0073] In addition, if the number of isolated noise points, effective point ratio and material recognition rate are also required for evaluation, the static test component is a performance evaluation board formed by splicing N different materials, which can be metal, marble, elevator door material and other materials that robots may encounter in working scenes. Then the test data of the static test component scanned by the radar to be tested is obtained separately, including:

[0074] In each test scenario, when the distance between the radar to be tested and the performance evaluation board is a fourth preset distance, second point cloud data is obtained after the radar to be tested scans the performance evaluation board; the second point cloud data includes static point cloud data, and dynamic point cloud data of the radar to be tested scanning the rotated performance evaluation board when the performance evaluation board is rotated to a preset angle.

[0075] In this way, the test data corresponding to the static performance indicators of the radar to be tested are obtained.

[0076] S111, analyzing the test data and obtaining test results of static performance indicators of the radar to be tested; the static performance indicators include: ranging accuracy, ranging consistency, measurement intensity, number of isolated noise points, effective point ratio and material recognition rate;

[0077] After obtaining the test data corresponding to the static performance indicators, the test data is analyzed and the test results of the static performance indicators of the radar to be tested are obtained; the static performance indicators include: ranging accuracy, ranging consistency, measurement intensity, number of isolated noise points, effective point ratio and material recognition rate.

[0078] In an optional embodiment, analyzing the test data and obtaining the test results of the static performance indicators of the radar to be tested include:

[0079] When the static test component is a performance test board, a first distance difference between a first preset distance and a first test distance, and a second distance difference between a second preset distance and a second test distance are obtained; and the ranging accuracy of the radar to be tested is determined based on the first distance difference and the second distance difference.

[0080] Taking the normal scenario as an example, when the first preset distance is 10 cm, the radar under test obtains the first test distance by scanning the performance test board of the first reflectivity, and when the second preset distance is 1 m, the radar under test obtains the second test distance by scanning the performance test board of the first reflectivity. If the first test distance is 9 cm and the second test distance is 0.95 m, then the difference in the first distance is 1 cm and the difference in the second distance is 5 cm.

[0081] If the first distance difference is less than the preset first distance threshold and the second distance difference is less than the preset second distance threshold, it means that the ranging accuracy of the radar to be tested meets the requirements. The first distance threshold and the second distance threshold can be determined based on the actual scenario of the robot application and are not limited here.

[0082] Alternatively, when the static test component is a performance test cylinder, the distance measurement consistency of the radar to be tested is determined according to a corresponding third test distance obtained after the radar to be tested scans the performance test cylinder at different scanning angles.

[0083] For example, if the difference between any two third test distances is less than the preset third distance threshold, it means that the distance measurement consistency of the radar to be tested meets the requirement.

[0084] Alternatively, when the static test component is a strength test board, the strength value distribution result is determined according to the strength value after the radar to be tested scans the strength test board, and the measurement intensity of the radar to be tested is determined according to the strength value distribution result.

[0085] For example, since the black test board has a stronger ability to absorb light, the corresponding intensity value will be small; the white test board has a weaker ability to absorb light, so the corresponding intensity value will be large. If the intensity test board is formed by splicing a black test board and a white test board adjacent to each other, the intensity distribution result should have a clear distinguishing boundary. If the actual intensity value distribution result also has a clear distinguishing boundary, it means that the scanning intensity of the radar to be tested meets the requirements.

[0086] Alternatively, when the static test component is a performance evaluation board, the second point cloud data is first roughly filtered. For example, when the fourth preset distance is 1 m, the second point cloud data within 1.5 m can be filtered out to participate in subsequent calculations.

[0087] For each second point cloud data after filtering, the coordinates (x coordinate and y coordinate) of each second point cloud (laser point) in the laser coordinate system are calculated.

[0088] The second point cloud data is traversed to determine isolated noise points in the second point cloud data, and the isolated noise points are removed, and the remaining second point cloud data can be called the third point cloud data. For example: for the target second point cloud, based on the corresponding coordinates, if the distance between the target second point cloud and two adjacent second point clouds is greater than a preset distance threshold, it means that the target second point cloud is an isolated noise point.

[0089] Then, a linear fit is performed on the third point cloud data to obtain a fitting straight line for the first point cloud; the third point clouds in the third point cloud data are traversed, and the distances between each third point cloud and the fitting straight line for the first point cloud are calculated in turn; if the distance between the current point cloud and the fitting straight line for the first point cloud is greater than a preset distance threshold, the current third point cloud is determined to be a long-distance noise point, otherwise, it is a close-distance noise point.

[0090] The long-distance noise points and short-distance noise points in the third point cloud data are removed, and the remaining third point cloud is a valid point cloud.

[0091] Then, based on the endpoint coordinates of the two ends of the performance evaluation board scanned by the laser and the coordinates of the laser origin, the angle formed by the two end points of the evaluation board and the laser emission position can be calculated. The theoretical number of laser points in the above angle area can be determined through the laser angle resolution; finally, the number of effective point clouds is divided by the theoretical number of laser points to obtain the effective point ratio.

[0092] This embodiment can also test the material recognition rate of the radar to be tested. Specifically, a straight line is fitted to the valid point cloud to obtain a second point cloud fitting line, and the mean square error of the distance from each valid point cloud to the second point cloud fitting line is calculated.

[0093] Then divide the performance evaluation board into N equal segments to obtain N-1 equal points; calculate the coordinates of the equal points based on the coordinate values ​​of the two end points of the performance evaluation board. Every two adjacent equal points and the laser emission point form an angle area, and determine the theoretical point cloud number of each angle area; then determine the ratio between the actual point cloud number and the theoretical point cloud number of each angle area. If the ratio is less than the preset threshold, it is considered that the radar under test has not identified the angle area. Finally, the number of unidentified angle areas will be obtained.

[0094] Finally, the number of unrecognized angle areas is divided by the total number of angle areas to obtain the material recognition rate of the radar to be tested.

[0095] S112, obtaining first point cloud data after the radar to be tested scans the dynamic target;

[0096] In practical applications, robots also need to identify dynamic targets, so this embodiment also needs to obtain the first point cloud data after the radar to be tested scans the dynamic target. Dynamic targets can be: human legs and dynamic objects in the mapping environment; dynamic objects can include people, cars, animals, etc.

[0097] S113, analyzing the first point cloud data, and obtaining test results of dynamic performance indicators of the radar to be tested; the dynamic performance indicators include: human leg recognition rate and ground object mapping accuracy.

[0098] After the first point cloud data is acquired, the first point cloud data is analyzed, and a test result of a dynamic performance index of the radar to be tested is obtained.

[0099] In an optional embodiment, analyzing the first point cloud data and obtaining a test result of a dynamic performance index of the radar to be tested includes:

[0100] When the dynamic performance indicator is the human leg recognition rate, the first point cloud data is matched using the trained human leg point cloud model to obtain a matching result;

[0101] The human leg recognition rate is determined based on the matching results.

[0102] Here, the human leg recognition model is pre-trained based on the point cloud data of the human legs scanned by the radar for multiple people. If the matching result is greater than the preset recognition threshold, it is determined that the human leg recognition rate of the radar to be tested meets the requirements. Among them, the recognition threshold can be set based on the actual scene, such as 90%.

[0103] In addition, since the robot needs to map the terrain, this embodiment also needs to test the terrain mapping accuracy of the radar to be tested.

[0104] In an optional embodiment, analyzing the first point cloud data to obtain a dynamic performance index of the radar to be tested includes:

[0105] When the dynamic performance indicator is the accuracy of ground object mapping, first point cloud data corresponding to at least three radars to be tested scanning the same mapping environment is obtained;

[0106] Using the same mapping algorithm, closed-loop mapping is performed on each first point cloud data to obtain the corresponding ground feature map;

[0107] The maps of various features are matched simultaneously, and the accuracy of the feature mapping of each radar to be tested is determined based on the matching results.

[0108] It should be noted that if the dynamic performance indicator is the mapping accuracy of the ground object, the first point cloud data not only includes the point cloud data of the dynamic targets in the mapping environment, but also includes the point cloud data of the static targets after scanning in the mapping environment. The static targets may include: trees, traffic lights, buildings, road lines, etc.

[0109] Since the present embodiment uses the same mapping algorithm to map the first point cloud data of different radars to be tested respectively, if the mapping effects of all radars to be tested are better, the matching rate of the corresponding object maps will be higher; therefore, the object mapping accuracy of the corresponding radar to be tested can be tested according to the matching rate between the object maps.

[0110] This embodiment takes into account the diversity of the robot's working environment, and therefore performs static tests and dynamic tests on the radar to be tested in a variety of test scenarios, and tests static test indicators such as ranging accuracy, ranging consistency, measurement intensity, number of isolated noise points, effective point ratio and material recognition rate of the radar to be tested; at the same time, in the above-mentioned different test environments, the human leg recognition rate and the ground object mapping accuracy of the radar to be tested are tested. It can be seen that this embodiment performs static tests and dynamic tests on the radar to be tested in a variety of test environments, which can comprehensively and effectively evaluate the performance of the radar to be tested, provide a reference basis for building a robot, and thereby improve the building accuracy of the robot.

[0111] Based on the same inventive concept as the above-mentioned embodiment, the embodiment of the present invention also provides a device for evaluating the performance index of a laser radar, such as Figure 2 As shown, the device comprises:

[0112] The first acquisition unit 21 is used to respectively acquire test data after the radar to be tested scans the static test component in different types of test scenarios; the test scenarios include: normal scene, strong light scene, particle fog scene, non-room temperature scene and humid scene; the static test component includes: performance test board, performance test tube, strength test board and performance evaluation board;

[0113] The first analysis unit 22 is used to analyze the test data and obtain the test results of the static performance indicators of the radar to be tested; the static performance indicators include: ranging accuracy, ranging consistency, measurement intensity, number of isolated noise points, effective point ratio and material recognition rate;

[0114] A second acquisition unit 23 acquires first point cloud data after the radar to be tested scans the dynamic target;

[0115] The second analysis unit 24 analyzes the first point cloud data and obtains test results of dynamic performance indicators of the radar to be tested; the dynamic performance indicators include: human leg recognition rate and ground object mapping accuracy.

[0116] It should be noted that the device may be a computer, server or other equipment with computing or storage functions. The device may be an independent server, which is not limited here.

[0117] Since the device introduced in the embodiment of the present invention is a device used to implement the method of the embodiment of the present invention, based on the method introduced in the embodiment of the present invention, the person skilled in the art can understand the specific structure and deformation of the device, so it is not repeated here. All devices used in the method of the embodiment of the present invention belong to the scope of protection of the present invention.

[0118] Based on the same inventive concept as the above-mentioned embodiment, this embodiment provides a computer device 300, such as Figure 3 As shown, it includes a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, the following steps are implemented:

[0119] In different types of test scenarios, test data after the radar to be tested scans the static test component is obtained respectively; the test scenarios include: normal scene, strong light scene, particle fog scene, non-room temperature scene and humid scene; the static test component includes: performance test board, performance test tube, strength test board and performance evaluation board;

[0120] Analyze the test data and obtain test results of static performance indicators of the radar to be tested; the static performance indicators include: ranging accuracy, ranging consistency, measurement intensity, number of isolated noise points, effective point ratio and material recognition rate;

[0121] Acquire the first point cloud data after the radar to be tested scans the dynamic target;

[0122] The first point cloud data is analyzed to obtain test results of dynamic performance indicators of the radar to be tested; the dynamic performance indicators include: human leg recognition rate and ground object mapping accuracy.

[0123] In a specific implementation process, when the processor 420 executes the computer program 411, any implementation method in the foregoing embodiments can be implemented.

[0124] Since the computer device introduced in this embodiment is a device used to implement a method for evaluating laser radar performance in an embodiment of this application, based on the method introduced in the aforementioned embodiment of this application, a person skilled in the art can understand the specific implementation of the computer device of this embodiment and its various variations, so how the server implements the method in the embodiment of this application is not described in detail here. As long as the device used by a person skilled in the art to implement the method in the embodiment of this application is within the scope of protection of this application.

[0125] Based on the same inventive concept, this embodiment also provides a computer-readable storage medium 400, such as Figure 4As shown, a computer program 411 is stored thereon, and when the computer program 411 is executed by a processor, the following steps are implemented:

[0126] In different types of test scenarios, test data after the radar to be tested scans the static test component is obtained respectively; the test scenarios include: normal scene, strong light scene, particle fog scene, non-room temperature scene and humid scene; the static test component includes: performance test board, performance test tube, strength test board and performance evaluation board;

[0127] Analyze the test data and obtain test results of static performance indicators of the radar to be tested; the static performance indicators include: ranging accuracy, ranging consistency, measurement intensity, number of isolated noise points, effective point ratio and material recognition rate;

[0128] Acquire the first point cloud data after the radar to be tested scans the dynamic target;

[0129] The first point cloud data is analyzed to obtain test results of dynamic performance indicators of the radar to be tested; the dynamic performance indicators include: human leg recognition rate and ground object mapping accuracy.

[0130] In the specific implementation process, when the computer program 411 is executed by a processor, any implementation method in the aforementioned embodiments can be implemented.

[0131] The method, device, medium and equipment for evaluating laser radar performance indicators provided by the present invention can bring at least the following beneficial effects:

[0132] The present invention provides a method, device, medium and equipment for evaluating laser radar performance indicators. The method comprises: obtaining test data after the radar to be tested scans a static test component in different types of test scenes; the test scenes comprise: a normal scene, a strong light scene, a particle fog scene, a non-room temperature scene and a humid scene; the static test component comprises: a performance test board, a performance test tube, a strength test board and a performance evaluation board; analyzing the test data and obtaining test results of the static performance indicators of the radar to be tested; the static performance indicators comprise: ranging accuracy, ranging consistency, measurement intensity, number of isolated noise points, effective point ratio and material recognition rate; obtaining first point cloud data after the radar to be tested scans a dynamic target; analyzing the first point cloud data The cloud data is analyzed, and the test results of the dynamic performance indicators of the radar to be tested are obtained; the dynamic performance indicators include: human leg recognition rate and ground object mapping accuracy; in this way, the present application takes into account the diversity of the robot's working environment, and therefore performs static tests and dynamic tests on the radar to be tested in a variety of test scenarios, and tests static test indicators such as ranging accuracy, ranging consistency, measurement intensity, number of isolated noise points, effective point ratio and material recognition rate of the radar to be tested; at the same time, in the above-mentioned different test environments, the human leg recognition rate and ground object mapping accuracy of the radar to be tested are tested. It can be seen that the present application performs static tests and dynamic tests on the radar to be tested in a variety of test environments, which can comprehensively and effectively evaluate the performance of the radar to be tested, thereby improving the construction accuracy of the robot.

[0133] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0134] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0135] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0136] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0137] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0138] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for evaluating laser radar performance, characterized in that: The method comprises: In different types of test scenarios, test data after the radar to be tested scans the static test component is obtained respectively; the test scenarios include: normal scene, strong light scene, particle fog scene, non-room temperature scene and humid scene; the static test component includes: performance test board, performance test tube, strength test board and performance evaluation board; Analyze the test data and obtain test results of static performance indicators of the radar to be tested; the static performance indicators include: ranging accuracy, ranging consistency, measurement intensity, number of isolated noise points, effective point ratio and material recognition rate; Acquire the first point cloud data after the radar to be tested scans the dynamic target; The first point cloud data is analyzed to obtain the test results of the dynamic performance indicators of the radar to be tested; the dynamic performance indicators include: human leg recognition rate and ground object mapping accuracy; wherein, The analyzing the first point cloud data to obtain the dynamic performance index of the radar to be tested includes: When the dynamic performance indicator is the ground object mapping accuracy, obtaining first point cloud data corresponding to at least three radars to be tested scanning the same mapping environment; Using the same mapping algorithm to perform closed-loop mapping on each of the first point cloud data, respectively, to obtain the corresponding ground feature maps; Matching the above-mentioned ground object maps simultaneously, and determining the ground object mapping accuracy of each radar to be tested according to the matching results; The analyzing the first point cloud data and obtaining the test result of the dynamic performance index of the radar to be tested includes: When the dynamic performance indicator is the human leg recognition rate, matching the first point cloud data using the trained human leg point cloud model to obtain a matching result; The human leg recognition rate is determined according to the matching result.

2. The method according to claim 1, characterized in that When the static test component is the performance test board, the step of respectively obtaining test data after the radar to be tested scans the static test component includes: In each of the test scenarios, when the distance between the radar to be tested and the performance test board is a first preset distance, a first test distance after the radar to be tested scans the performance test board is respectively obtained; When the distance between the radar to be tested and the performance test board is the second preset distance, the second test distance after the radar to be tested scans the performance test board is obtained respectively; wherein, The performance test board includes: a performance test board with a first reflectivity and a performance test board with a second reflectivity; the first reflectivity is different from the second reflectivity; the first preset distance is 5~30cm; the second preset distance is 1~10m; the target test scene is all scenes of the normal scene, the strong light scene, the particle fog scene, the non-room temperature scene and the humid scene.

3. The method according to claim 1, characterized in that When the static test component is the performance test cylinder, the step of respectively obtaining test data after the radar to be tested scans the static test component comprises: In each of the test scenarios, when the radar to be tested is located at the center of the performance test cylinder, a third test distance is obtained after the radar to be tested scans the performance test cylinder at different scanning angles; wherein, The performance test cylinder includes: a test cylinder formed by a performance test plate of a first reflectivity and a test cylinder formed by a performance test plate of a second reflectivity; the target test scenes are all scenes among the normal scene, the strong light scene, the particle fog scene, the non-room temperature scene and the humid scene.

4. The method according to claim 1, characterized in that When the static test component is the strength test board, the step of respectively obtaining test data after the radar to be tested scans the static test component includes: In each of the test scenarios, when the distance between the radar to be tested and the strength test board is a third preset distance, the strength value after the radar to be tested scans the strength test board is obtained respectively; wherein, The strength test board is a combined test board formed by splicing a performance test board of a first reflectivity and a performance test board of a second reflectivity; the target test scene is all scenes including the normal scene, the strong light scene, the particle fog scene, the non-room temperature scene and the humid scene.

5. The method according to claim 1, characterized in that The analyzing the test data and obtaining the test results of the static performance indicators of the radar to be tested includes: When the static test component is the performance test board, a first distance difference between a first preset distance and a first test distance, and a second distance difference between a second preset distance and a second test distance are obtained; a ranging accuracy of the radar to be tested is determined according to the first distance difference and the second distance difference; or, When the static test component is the performance test cylinder, the ranging consistency of the radar to be tested is determined according to the corresponding third test distances obtained after the radar to be tested scans the performance test cylinder at different scanning angles; or When the static test component is a strength test board, the strength value distribution result is determined according to the strength value after the radar to be tested scans the strength test board, and the measurement strength of the radar to be tested is determined according to the strength value distribution result.

6. A device for evaluating laser radar performance, characterized in that: The device comprises: The first acquisition unit is used to respectively acquire test data after the radar to be tested scans the static test component in different types of test scenarios; the test scenarios include: normal scene, strong light scene, particle fog scene, non-room temperature scene and humid scene; the static test component includes: performance test board, performance test tube, strength test board and performance evaluation board; A first analysis unit is used to analyze the test data and obtain test results of static performance indicators of the radar to be tested; the static performance indicators include: ranging accuracy, ranging consistency, measurement intensity, number of isolated noise points, effective point ratio and material recognition rate; A second acquisition unit acquires first point cloud data after the radar to be tested scans the dynamic target; The second analysis unit analyzes the first point cloud data and obtains the test results of the dynamic performance indicators of the radar to be tested; the dynamic performance indicators include: human leg recognition rate and ground object mapping accuracy; wherein, The analyzing the first point cloud data to obtain the dynamic performance index of the radar to be tested includes: When the dynamic performance indicator is the ground object mapping accuracy, obtaining first point cloud data corresponding to at least three radars to be tested scanning the same mapping environment; Using the same mapping algorithm to perform closed-loop mapping on each of the first point cloud data, respectively, to obtain the corresponding ground feature maps; Matching the above-mentioned ground object maps simultaneously, and determining the ground object mapping accuracy of each radar to be tested according to the matching results; The analyzing the first point cloud data and obtaining the test result of the dynamic performance index of the radar to be tested includes: When the dynamic performance indicator is the human leg recognition rate, matching the first point cloud data using the trained human leg point cloud model to obtain a matching result; The human leg recognition rate is determined according to the matching result.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 5 is implemented.

Images