Laser radar test method and device and terminal equipment

Abstract

The invention is suitable for the technical field of radars, and provides a laser radar test method and device and terminal equipment, and the method comprises the steps: obtaining a current test condition corresponding to a laser radar; acquiring multi-frame point cloud data corresponding to the traffic participants collected by the laser radar in the test environment; performing identification processing on each frame of point cloud data to determine a traffic participant identification result corresponding to each frame of point cloud data; and determining performance parameters corresponding to the laser radar according to the traffic participant identification result corresponding to each frame of point cloud data and the current test condition. Therefore, the experimental environment for simulating the real use environment of the roadside laser radar is established, the performance parameters corresponding to the laser radar are effectively evaluated, and the possible problems of the laser radar in actual use can be found in time according to the test result for improvement, so that the reliability and the stability of the laser radar in the use process are ensured.

Description

Technical Field

[0001] This application belongs to the technical field of radar, and particularly relates to a test method, device, terminal device and computer-readable storage medium for lidar. Background Art

[0002] With the development of society, the number of cars is increasing continuously. The speed of infrastructure construction lags behind the growth rate of vehicles, resulting in a severe traffic safety situation. In recent years, due to frequent traffic jams, traffic accidents occur frequently, causing huge losses. Therefore, intelligent transportation plays a crucial role in traffic infrastructure construction.

[0003] In the related art, as one of the indispensable sensors in the construction of intelligent transportation, roadside lidar plays an important role in intelligent transportation. However, at present, the test means for roadside lidar are only limited to the laboratory stage, and there are very few evaluation means for lidar point clouds, and it is impossible to effectively evaluate the point cloud performance of roadside lidar during actual use, thus it is impossible to ensure the reliability and stability of roadside lidar during use. Summary of the Invention

[0004] The embodiments of this application provide a test method, device, terminal device and storage medium for lidar, which can solve the problem that it is impossible to effectively evaluate the point cloud performance of roadside lidar during actual use, thus it is impossible to ensure the reliability and stability of roadside lidar during use.

[0005] In a first aspect, the embodiments of this application provide a test method for lidar, including: obtaining the current test conditions corresponding to the lidar; obtaining multiple frames of point cloud data corresponding to traffic participants collected by the lidar in the test environment; performing identification processing on each frame of point cloud data to determine the traffic participant identification result corresponding to each frame of point cloud data; and determining the performance parameters corresponding to the lidar according to the traffic participant identification result corresponding to each frame of point cloud data and the current test conditions.

[0006] In a possible implementation manner of the first aspect, the above performance parameters include at least one of detection accuracy, effective vertical field of view, maximum detection distance, and effective horizontal field of view.

[0007] Optionally, in another possible implementation manner of the first aspect, the above performance parameter includes detection accuracy, and the above current test conditions include the actual parameters of traffic participants; correspondingly, the above performing identification processing on each frame of point cloud data to determine the traffic participant identification result corresponding to each frame of point cloud data includes:

[0008] Performing identification processing on each frame of point cloud data to determine the traffic participant detection parameters corresponding to each frame of point cloud data;

[0009] Correspondingly, determining the performance parameters corresponding to the lidar according to the traffic participant recognition results corresponding to each frame of point cloud data and the current test conditions includes:

[0010] Determining the detection accuracy corresponding to the lidar according to the traffic participant detection parameters and the actual traffic participant parameters corresponding to each frame of point cloud data.

[0011] Optionally, in another possible implementation manner of the first aspect, determining the detection accuracy corresponding to the lidar according to the traffic participant detection parameters and the actual traffic participant parameters corresponding to each frame of point cloud data includes:

[0012] Determining the difference between the traffic participant detection parameters and the actual traffic participant parameters corresponding to each frame of point cloud data;

[0013] Determining the detection accuracy according to the difference between the traffic participant detection parameters and the actual traffic participant parameters corresponding to each frame of point cloud data.

[0014] Optionally, in another possible implementation manner of the first aspect, the performance parameters include an effective vertical field of view angle, and the current test conditions include a first point cloud condition and the installation height corresponding to the lidar; correspondingly, performing recognition processing on each frame of point cloud data to determine the traffic participant recognition result corresponding to each frame of point cloud data includes:

[0015] Performing recognition processing on each frame of point cloud data to determine the target point cloud points corresponding to each frame of point cloud data, where the target point cloud points refer to the point cloud points corresponding to traffic participants;

[0016] Correspondingly, determining the performance parameters corresponding to the lidar according to the traffic participant recognition results corresponding to each frame of point cloud data and the current test conditions includes:

[0017] Determining the point cloud data with target point cloud points satisfying the first point cloud condition as the first target point cloud data;

[0018] Performing recognition processing on each frame of the first target point cloud data to determine the horizontal distance between the traffic participant corresponding to each frame of the first target point cloud data and the lidar;

[0019] Determining the effective vertical field of view angle corresponding to the lidar according to the installation height and the horizontal distance between the traffic participant corresponding to each frame of the first target point cloud data and the lidar.

[0020] Optionally, in another possible implementation manner of the first aspect, the first point cloud condition includes a first point cloud quantity condition, a first point cloud row number condition, and a first distance condition; correspondingly, determining the point cloud data with target point cloud points satisfying the first point cloud condition as the first target point cloud data includes:

[0021] Identify and process the target point cloud points corresponding to each frame of point cloud data to determine the number of target point cloud points, the number of rows of target point cloud points, and the horizontal distance between the traffic participant and the lidar corresponding to each frame of point cloud data;

[0022] Determine the point cloud data with the number of target point cloud points meeting the first point cloud number condition, the number of rows of target point cloud points meeting the first point cloud row number condition, and the horizontal distance between the traffic participant and the lidar meeting the first distance condition as the first target point cloud data.

[0023] Optionally, in another possible implementation manner of the first aspect, the above performance parameter includes the maximum detection distance, and the above current test condition includes the second point cloud condition; correspondingly, the above identification and processing of each frame of point cloud data to determine the traffic participant identification result corresponding to each frame of point cloud data includes:

[0024] Identify and process each frame of point cloud data to determine the target point cloud points corresponding to each frame of point cloud data, where the target point cloud points refer to the point cloud points corresponding to traffic participants;

[0025] Correspondingly, the above determination of the performance parameter corresponding to the lidar according to the traffic participant identification result corresponding to each frame of point cloud data and the current test condition includes:

[0026] Determine the point cloud data with the target point cloud points meeting the second point cloud condition as the second target point cloud data;

[0027] Identify and process each frame of the second target point cloud data to determine the horizontal distance between the traffic participant and the lidar corresponding to each frame of the second target point cloud data;

[0028] Determine the maximum detection distance corresponding to the lidar according to the horizontal distance between the traffic participant and the lidar corresponding to each frame of the second target point cloud data.

[0029] Optionally, in yet another possible implementation manner of the first aspect, the above second point cloud condition includes the second point cloud number condition, the second point cloud row number condition, the second distance condition, and the second moving direction; correspondingly, the above determination of the point cloud data with the target point cloud points meeting the second point cloud condition as the second target point cloud data includes:

[0030] Identify and process the target point cloud points corresponding to each frame of point cloud data to determine the number of target point cloud points, the number of rows of target point cloud points, the horizontal distance between the traffic participant and the lidar, and the traffic participant moving direction corresponding to each frame of point cloud data;

[0031] The point cloud data where the number of target point cloud points meets the second point cloud number condition, the number of rows of target point cloud points meets the second point cloud row number condition, the horizontal distance between the traffic participant and the lidar meets the second distance condition, and the moving direction of the traffic participant meets the second moving direction is determined as the second target point cloud data.

[0032] Optionally, in another possible implementation manner of the first aspect, the above performance parameter includes an effective horizontal field of view angle. The above lidar is installed on a rotating device, and when the rotating device rotates, it drives the lidar to rotate. Each frame of point cloud data is collected when the rotating device rotates. The above traffic participant is within the effective vertical field of view angle corresponding to the lidar and is stationary. The above current test condition includes a third point cloud condition. Correspondingly, the above identification and processing of each frame of point cloud data to determine the traffic participant identification result corresponding to each frame of point cloud data includes:

[0033] Perform identification and processing on each frame of point cloud data to determine the target point cloud points corresponding to each frame of point cloud data and the cumulative rotation angle of the rotating device, where the target point cloud points refer to the point cloud points corresponding to the traffic participant.

[0034] Correspondingly, the above determination of the performance parameter corresponding to the lidar according to the traffic participant identification result corresponding to each frame of point cloud data and the current test condition includes:

[0035] The point cloud data where the target point cloud points meet the third point cloud condition is determined as the third target point cloud data;

[0036] Determine the effective horizontal field of view angle corresponding to the lidar according to the cumulative rotation angle corresponding to the third target point cloud data.

[0037] Optionally, in another possible implementation manner of the first aspect, the above third point cloud condition includes a third point cloud number condition and a third point cloud row number condition. Correspondingly, the above determination of the point cloud data where the target point cloud points meet the third point cloud condition as the third target point cloud data includes:

[0038] Perform identification and processing on the target point cloud points corresponding to each frame of point cloud data to determine the number of target point cloud points and the number of rows of target point cloud points corresponding to each frame of point cloud data;

[0039] The point cloud data where the number of target point cloud points meets the third point cloud number condition and the number of rows of target point cloud points meets the third point cloud row number condition is determined as the third target point cloud data.

[0040] In a second aspect, an embodiment of the present application provides a test device for a lidar, including: a first acquisition module, configured to acquire current test conditions corresponding to the lidar; a second acquisition module, configured to acquire multiple frames of point cloud data corresponding to traffic participants collected by the lidar in a test environment; a first determination module, configured to perform identification processing on each frame of point cloud data to determine a traffic participant identification result corresponding to each frame of point cloud data; a second determination module, configured to determine performance parameters corresponding to the lidar according to the traffic participant identification result corresponding to each frame of point cloud data and the current test conditions.

[0041] In a possible implementation manner of the second aspect, the above performance parameters include at least one of detection accuracy, effective vertical field of view angle, maximum detection distance, and effective horizontal field of view angle.

[0042] Optionally, in another possible implementation manner of the second aspect, the above performance parameter includes detection accuracy, and the above current test conditions include actual parameters of traffic participants; correspondingly, the above first determination module includes:

[0043] A first determination unit, configured to perform identification processing on each frame of point cloud data to determine traffic participant detection parameters corresponding to each frame of point cloud data;

[0044] Correspondingly, the above second determination module includes:

[0045] A second determination unit, configured to determine the detection accuracy corresponding to the lidar according to the traffic participant detection parameters corresponding to each frame of point cloud data and the actual parameters of traffic participants.

[0046] Optionally, in another possible implementation manner of the second aspect, the above second determination unit is specifically configured to:

[0047] Determine the difference between the traffic participant detection parameters corresponding to each frame of point cloud data and the actual parameters of traffic participants;

[0048] Determine the detection accuracy according to the difference between the traffic participant detection parameters corresponding to each frame of point cloud data and the actual parameters of traffic participants.

[0049] Optionally, in another possible implementation manner of the second aspect, the above performance parameter includes an effective vertical field of view angle, and the above current test conditions include a first point cloud condition and the installation height corresponding to the lidar; correspondingly, the above first determination module includes:

[0050] A third determination unit, configured to perform identification processing on each frame of point cloud data to determine a target point cloud point corresponding to each frame of point cloud data, where the target point cloud point refers to the point cloud point corresponding to a traffic participant;

[0051] Correspondingly, the above second determination module includes:

[0052] A fourth determination unit, configured to determine the point cloud data of the target point cloud points that meet the first point cloud condition as the first target point cloud data;

[0053] A fifth determination unit, configured to perform identification processing on each frame of the first target point cloud data to determine the horizontal distance between the traffic participant corresponding to each frame of the first target point cloud data and the lidar;

[0054] A sixth determination unit, configured to determine the effective vertical field of view angle corresponding to the lidar according to the installation height and the horizontal distance between the traffic participant corresponding to each frame of the first target point cloud data and the lidar.

[0055] Optionally, in another possible implementation manner of the second aspect, the first point cloud condition includes a first point cloud quantity condition, a first point cloud row number condition, and a first distance condition; correspondingly, the fourth determination unit is specifically configured to:

[0056] Perform identification processing on the target point cloud points corresponding to each frame of point cloud data to determine the number of target point cloud points, the number of rows of target point cloud points, and the horizontal distance between the traffic participant and the lidar corresponding to each frame of point cloud data;

[0057] Determine the point cloud data in which the number of target point cloud points meets the first point cloud quantity condition, the number of rows of target point cloud points meets the first point cloud row number condition, and the horizontal distance between the traffic participant and the lidar meets the first distance condition as the first target point cloud data.

[0058] Optionally, in another possible implementation manner of the second aspect, the performance parameter includes a maximum detection distance, and the current test condition includes a second point cloud condition; correspondingly, the first determination module includes:

[0059] A seventh determination unit, configured to perform identification processing on each frame of point cloud data to determine the target point cloud points corresponding to each frame of point cloud data, where the target point cloud points refer to the point cloud points corresponding to the traffic participant;

[0060] Correspondingly, the second determination module includes:

[0061] An eighth determination unit, configured to determine the point cloud data in which the target point cloud points meet the second point cloud condition as the second target point cloud data;

[0062] A ninth determination unit, configured to perform identification processing on each frame of the second target point cloud data to determine the horizontal distance between the traffic participant corresponding to each frame of the second target point cloud data and the lidar;

[0063] A tenth determination unit, configured to determine a maximum detection distance corresponding to the lidar according to a horizontal distance between a traffic participant corresponding to each frame of second target point cloud data and the lidar.

[0064] Optionally, in another possible implementation manner of the second aspect, the above-mentioned second point cloud condition includes a second point cloud quantity condition, a second point cloud row number condition, a second distance condition, and a second moving direction; correspondingly, the above-mentioned eighth determination unit is specifically configured to:

[0065] Perform recognition processing on the target point cloud points corresponding to each frame of point cloud data to determine the number of target point cloud points, the number of rows of target point cloud points, the horizontal distance between the traffic participant and the lidar, and the moving direction of the traffic participant corresponding to each frame of point cloud data;

[0066] Determine the point cloud data whose number of target point cloud points meets the second point cloud quantity condition, the number of rows of target point cloud points meets the second point cloud row number condition, the horizontal distance between the traffic participant and the lidar meets the second distance condition, and the moving direction of the traffic participant meets the second moving direction as the second target point cloud data.

[0067] Optionally, in another possible implementation manner of the second aspect, the above-mentioned performance parameter includes an effective horizontal field of view angle, the above-mentioned lidar is installed on a rotating device, the rotating device drives the lidar to rotate when rotating, each frame of point cloud data is collected when the rotating device rotates, the traffic participant is within the effective vertical field of view angle corresponding to the lidar and is stationary, and the above-mentioned current test condition includes a third point cloud condition; correspondingly, the above-mentioned first determination module includes:

[0068] An eleventh determination unit, configured to perform recognition processing on each frame of point cloud data to determine the target point cloud points corresponding to each frame of point cloud data and the cumulative rotation angle of the rotating device, where the target point cloud points refer to the point cloud points corresponding to the traffic participant;

[0069] Correspondingly, the above-mentioned second determination module includes:

[0070] A twelfth determination unit, configured to determine the point cloud data whose target point cloud points meet the third point cloud condition as the third target point cloud data;

[0071] A thirteenth determination unit, configured to determine the effective horizontal field of view angle corresponding to the lidar according to the cumulative rotation angle corresponding to the third target point cloud data.

[0072] Optionally, in another possible implementation manner of the second aspect, the above-mentioned third point cloud condition includes a third point cloud quantity condition and a third point cloud row number condition; correspondingly, the above-mentioned twelfth determination unit is specifically configured to:

[0073] Identify and process the target point cloud points corresponding to each frame of point cloud data to determine the number of target point cloud points and the number of rows of target point cloud points corresponding to each frame of point cloud data;

[0074] Determine the point cloud data whose number of target point cloud points meets the third point cloud quantity condition and whose number of rows of target point cloud points meets the third point cloud row condition as the third target point cloud data.

[0075] In a third aspect, an embodiment of the present application provides a terminal device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the test method of the lidar as described above is implemented.

[0076] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the test method of the lidar as described above is implemented.

[0077] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on a terminal device, the terminal device is enabled to execute the test method of the lidar as described above.

[0078] The beneficial effects of the embodiments of the present application compared with the prior art are as follows: By building an experimental environment that simulates the actual use environment of the roadside lidar, and determining the traffic participant recognition results corresponding to each frame of point cloud data based on the point cloud data of traffic participants collected by the lidar, and then evaluating the traffic participant recognition results according to the pre-configured test conditions, so as to effectively evaluate the performance parameters corresponding to the lidar, and timely discover and improve the possible problems of the lidar in actual use according to the test results, thus ensuring the reliability and stability of the lidar during use. Description of the Drawings

[0079] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0080] Figure 1 is a schematic flowchart of a test method for a lidar provided by an embodiment of the present application;

[0081] Figure 2 is a schematic structural diagram of a test system for a lidar provided by an embodiment of the present application;

[0082] Figure 3It is a schematic structural diagram of another test system for a lidar provided by an embodiment of the present application;

[0083] Figure 4 It is a schematic flowchart of a test method for a lidar provided by another embodiment of the present application;

[0084] Figure 5 It is a schematic diagram of the effective vertical field of view corresponding to a lidar provided by an embodiment of the present application;

[0085] Figure 6 It is a schematic diagram of the front view and rear view corresponding to a traffic participant provided by an embodiment of the present application;

[0086] Figure 7 It is a schematic diagram of the point cloud points of the front view and rear view corresponding to a traffic participant provided by an embodiment of the present application;

[0087] Figure 8 It is a schematic flowchart of a test method for a lidar provided by still another embodiment of the present application;

[0088] Figure 9 It is a schematic diagram of the maximum detection distance corresponding to a lidar provided by an embodiment of the present application;

[0089] Figure 10 It is a schematic diagram of the maximum detection distance corresponding to another lidar provided by an embodiment of the present application;

[0090] Figure 11 It is a schematic flowchart of a test method for a lidar provided by yet another embodiment of the present application;

[0091] Figure 12 It is a schematic structural diagram of a test device for a lidar provided by an embodiment of the present application;

[0092] Figure 13 It is a schematic structural diagram of a terminal device provided by an embodiment of the present application. Detailed implementation manners

[0093] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system architectures, technologies, etc. are presented to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0094] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0095] It should also be understood that the term "and / or" used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0096] As used in the specification of the present application and the appended claims, the term "if" may be interpreted as "when", "once", "in response to determining", or "in response to detecting" according to the context. Similarly, the phrases "if determined" or "if [the described condition or event] is detected" may be interpreted as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]" according to the context.

[0097] In addition, in the description of the specification of the present application and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0098] Reference to "one embodiment" or "some embodiments" etc. described in the specification of the present application means that a specific feature, structure or characteristic described in connection with that embodiment is included in one or more embodiments of the present application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0099] The test method, device, terminal device, storage medium and computer program provided by the present application will be described in detail below with reference to the accompanying drawings.

[0100] Figure 1 The flowchart of a test method for a lidar provided by an embodiment of the present application is shown.

[0101] As Figure 1 shown, the test method for the lidar includes the following steps:

[0102] Step 101, obtaining the current test conditions corresponding to the lidar.

[0103] It should be noted that the test method of the lidar in the embodiments of the present application can be executed by the test device of the lidar in the embodiments of the present application. The test device of the lidar in the embodiments of the present application can be configured in any terminal device to execute the test method of the lidar in the embodiments of the present application.

[0104] For example, in order to implement the test method of the lidar in the embodiments of the present application, an experimental environment as shown in Figure 2 can be pre-built to simulate the actual usage environment of the lidar. The experimental environment includes a test system 200 of the lidar, and the test system 200 of the lidar includes a lidar 210, a control device 220, and a traffic participant 230. The lidar 210 is installed on a bracket, and the height of the bracket is not limited; the lidar 200 is connected to the control device 220. After the lidar 200 collects point cloud data, it can be transmitted to the control device 220; the test device of the lidar in the embodiments of the present application can be configured in the control device 220 to execute the test method of the lidar in the embodiments of the present application, and the control device 220 can be any type of terminal device. The traffic participant 230 can move within the lower area of the lidar, and the moving area and moving distance are not limited; as shown in Figure 3 the traffic participant 230 can appear in different orientations of the lidar 210.

[0105] It should be noted that in actual use, the connection method between the lidar and the control device can be a wired connection or a wireless network connection, and the embodiments of the present application do not make any limitations on this; Figure 2 the connection line between the lidar 210 and the control terminal 220 in the figure is only used to indicate the connection relationship between the two and cannot be regarded as a limitation on its specific connection method.

[0106] As a possible implementation, before the formal test, in order to ensure the accuracy and stability of the test, the following preparatory work can also be done: build a test environment corresponding to the lidar according to the actual test requirements and the used test method; power on the lidar and wait for it to run stably.

[0107] Among them, the current test conditions can refer to those determined according to the current actual test requirements; it can refer to the indicators used to measure the performance parameters of the lidar under the current test requirements, or the parameters required to determine the performance parameters of the lidar.

[0108] As an example, when the current test requirement is to test the detection accuracy of a lidar, the current test conditions may include the actual parameters of traffic participants, which are used to measure whether the traffic participant parameters identified based on the point cloud data collected by the lidar are accurate, and then to test the detection accuracy of the lidar. For another example, when the current test requirement is to test the effective vertical field of view angle of a lidar, the current test conditions may include the first point cloud condition and the installation height corresponding to the lidar. Among them, the first point cloud condition can be used to select the point cloud data representing the effective vertical field of view angle corresponding to the lidar, and the installation height corresponding to the lidar can be used to participate in the calculation of the effective vertical field of view angle corresponding to the lidar. For another example, when the current test requirement is to test the maximum detection of a lidar, the current test conditions may include the second point cloud condition. Among them, the second point cloud condition can be used to select the point cloud data representing the maximum detection corresponding to the lidar, and then to calculate the maximum detection distance corresponding to the lidar based on the selected point cloud data.

[0109] It should be noted that the above-listed test conditions are only exemplary and should not be regarded as a limitation to this application. In actual use, the current test conditions can be determined according to the actual test requirements and specific application scenarios, and the embodiments of this application do not make any limitations thereto.

[0110] As a possible implementation manner, the user can set the current test conditions in the control device. Therefore, an interactive interface can be provided in the control device, and when the setting operation of the current test conditions by the user on the interactive interface is obtained, according to the setting operation of the user, the test conditions selected or input by the user are determined as the current test conditions.

[0111] Step 102: Obtain multiple frames of point cloud data corresponding to traffic participants collected by the lidar in the test environment.

[0112] Among them, the traffic participant can be any type of traffic participant that may be encountered in the actual use scenario of the roadside lidar; for example, motor vehicles, non-motor vehicles, pedestrians, etc. Since the parameters such as the shape and size of motor vehicles are usually relatively fixed and unified, the embodiments of this application take the traffic participant as a motor vehicle as an example to illustrate the test method of the lidar in the embodiments of this application.

[0113] Among them, the point cloud data corresponding to a traffic participant refers to the point cloud data collected by a lidar for the area within its field of view. It should be noted that since a traffic participant may leave the field of view of the lidar when the lidar is collecting point cloud data, the point cloud data corresponding to the traffic participant does not necessarily contain the point cloud points corresponding to the traffic participant. The point cloud data corresponding to the traffic participant mentioned in the embodiments of the present application refers to the point cloud data collected by the lidar during the period when the traffic participant is driving in the area below it, regardless of whether the point cloud data contains the point cloud points corresponding to the traffic participant.

[0114] In the embodiments of the present application, after the test environment is set up according to actual test requirements and it is determined that the lidar is running stably, the traffic participant can be made to move in the area below the lidar, and both the moving area and the moving distance of the traffic participant are not limited, so that the lidar can fully obtain the point cloud data corresponding to the traffic participant at each position of the lidar. After the system starts running, the traffic participant starts to move, the lidar starts to collect point cloud data, and the collected point cloud data corresponding to the traffic participant is sent to the control device, and the control device can receive the point cloud data corresponding to the traffic participant sent by the lidar in real time.

[0115] Step 103: Perform identification processing on each frame of point cloud data to determine the traffic participant identification result corresponding to each frame of point cloud data.

[0116] In the embodiments of the present application, after the point cloud data corresponding to the traffic participant collected by the lidar is obtained, each frame of point cloud data can be processed to determine the traffic participant identification result corresponding to each frame of point cloud data.

[0117] As a possible implementation manner, since in different test requirements, the indicators for evaluating the performance of the lidar may also be different, the method for processing each frame of point cloud data can be determined according to the current test requirements to determine the traffic participant identification result required for the current test scenario.

[0118] As an example, if the current test requirement is to test the detection accuracy of a lidar, the parameters of traffic participants can be identified based on the point cloud data corresponding to the traffic participants, so as to test the detection accuracy of the lidar according to the difference between the identified difference parameters and the actual parameters; that is, when the current test requirement is to test the detection accuracy of the lidar, the traffic participant recognition result can include traffic participant detection parameters, such as size, type, color, etc. Therefore, when the current test requirement is to test the detection accuracy of the lidar, each frame of point cloud data can be processed to identify traffic participant detection parameters based on each frame of point cloud data. That is, in a possible implementation manner of the embodiment of the present application, when the performance parameter of the lidar includes detection accuracy, step 103 described above may include:

[0119] Perform recognition processing on each frame of point cloud data to determine the traffic participant detection parameters corresponding to each frame of point cloud data.

[0120] It should be noted that the parameters of traffic participants may include at least one of parameters such as size, type, color, etc., but are not limited thereto, and the embodiments of the present application do not make any limitations in this regard. For example, when the parameter of the traffic participant includes size, the actual parameter of the traffic participant may include the actual size, and the traffic participant detection parameter may include the traffic participant detection size, so that the detection accuracy of the lidar can be tested according to the difference between the traffic participant detection size and the actual size; another example is that when the parameter of the traffic participant includes the traffic participant type, the actual parameter of the traffic participant may include the actual type, and the traffic participant detection parameter may include the traffic participant detection type, so that the detection accuracy of the lidar can be tested according to the difference between the traffic participant detection type and the actual type; another example is that when the parameter of the traffic participant includes color, the actual parameter of the traffic participant may include the actual color, and the traffic participant detection parameter may include the traffic participant detection color, so that the detection accuracy of the lidar can be tested according to the difference between the traffic participant detection color and the actual color. The following takes the parameter of the traffic participant as size to specifically illustrate the embodiment of the present application.

[0121] For example, if the traffic participant is a motor vehicle, the actual size of the traffic participant may include the actual length, actual width and actual height, and the traffic participant detection size may include the length, width and height corresponding to the traffic participant identified from the point cloud data, that is, the traffic participant detection length, detection width and detection height.

[0122] Step 104, determine the performance parameter corresponding to the lidar according to the traffic participant recognition result corresponding to each frame of point cloud data and the current test condition.

[0123] In the embodiment of the present application, after determining the traffic participant recognition result corresponding to each frame of point cloud data, the traffic participant recognition result corresponding to each frame of point cloud data can be evaluated according to the current test conditions, and the performance parameters of the lidar can be determined according to the evaluation result.

[0124] As a possible implementation, if the current test requirement is to test the detection accuracy of the lidar, the detection accuracy of the lidar can be tested according to the difference between the traffic participant detection parameters corresponding to each frame of point cloud data and the actual parameters of the traffic participant. That is, in a possible implementation of the embodiment of the present application, the above performance parameters may include detection accuracy. Correspondingly, the above step 104 may include:

[0125] Determine the detection accuracy corresponding to the lidar according to the traffic participant detection parameters corresponding to each frame of point cloud data and the actual parameters of the traffic participant.

[0126] In a possible implementation of the embodiment of the present application, the difference between the traffic participant detection parameters corresponding to the point cloud data and the actual parameters of the traffic participant can be determined; and the detection accuracy can be determined according to the difference between the traffic participant detection parameters corresponding to each frame of point cloud data and the actual parameters of the traffic participant.

[0127] As a possible implementation, when testing the detection accuracy of the lidar through the size detection accuracy of the traffic participant, the difference between the detected size of the traffic participant corresponding to each frame of point cloud data and the actual size of the traffic participant can be calculated, and the difference can be respectively determined as the traffic participant parameter difference corresponding to each frame of point cloud data.

[0128] Correspondingly, when testing the detection accuracy of the lidar through the type detection accuracy of the traffic participant, it can be determined whether the detected type of the traffic participant corresponding to each frame of point cloud data is the same as the actual type of the traffic participant; if the detected type of the traffic participant corresponding to the point cloud data is the same as the actual type of the traffic participant, the first preset value (such as 0) can be determined as the traffic participant parameter difference corresponding to this frame of point cloud data; if the detected type of the traffic participant corresponding to the point cloud data is different from the actual type of the traffic participant, the second preset value (such as 1) can be determined as the traffic participant parameter difference corresponding to this frame of point cloud data.

[0129] Correspondingly, when testing the detection accuracy of the lidar corresponding to the color detection accuracy of traffic participants, it can be determined whether the detected color of the traffic participant corresponding to each frame of point cloud data is the same as the actual color of the traffic participant; if the detected color of the traffic participant corresponding to the point cloud data is the same as the actual color of the traffic participant, the first preset value (such as 0) can be determined as the traffic participant parameter difference corresponding to this frame of point cloud data; if the detected color of the traffic participant corresponding to the point cloud data is not the same as the actual color of the traffic participant, the second preset value (such as 1) can be determined as the traffic participant parameter difference corresponding to this frame of point cloud data.

[0130] As a possible implementation, when measuring whether the traffic participant detection parameters are the same as the actual parameters by confidence, the confidence between the traffic participant detection parameters and the actual parameters corresponding to each frame of point cloud data can also be directly determined as the traffic participant parameter difference corresponding to each frame of point cloud data.

[0131] As a possible implementation, after determining the traffic participant parameter difference corresponding to each frame of point cloud data, the mean value of the traffic participant parameter difference corresponding to each frame of point cloud data can be determined as the detection accuracy corresponding to the lidar; alternatively, different weights can be assigned to each frame of point cloud data, and then the weighted sum of the traffic participant parameter differences corresponding to each frame of point cloud data can be determined as the detection accuracy corresponding to the lidar; alternatively, when there is a negative correlation between the traffic participant parameter difference corresponding to the point cloud data and the actual detection accuracy of the lidar, in order to make the specific value of the finally obtained detection accuracy positively correlated with the performance of the lidar, after determining the mean value of the traffic participant parameter difference corresponding to each frame of point cloud data, the reciprocal of this mean value can also be determined as the detection accuracy corresponding to the lidar.

[0132] For example, assuming that the traffic participant is a motor vehicle and the traffic participant parameter is size, the traffic participant detection size can include the detected length, detected width and detected height, and the traffic participant actual size can include the actual length, actual width and actual height of the traffic participant. Then, the detection accuracy of the lidar can be determined by the following formula:

[0133]

[0134] where E d is the detection accuracy corresponding to the lidar, l′ ij is the detected length of the j-th traffic participant in the i-th point cloud data, l j is the actual length of the j-th traffic participant, w′ ij is the detected width of the j-th traffic participant in the i-th point cloud data, w j is the actual width of the j-th traffic participant, h′ ijThe detection height of the j-th traffic participant in the i-th point cloud data, h j is the actual height of the j-th traffic participant, N is the number of point cloud data corresponding to the traffic participant, i is the serial number of the point cloud data, M is the number of traffic participants in the point cloud data, j is the serial number of the traffic participant in the point cloud data, M is a positive integer, and N is an integer greater than 1.

[0135] As another possible implementation, when testing the detection accuracy of the lidar corresponding to the size detection accuracy of the traffic participant, the mean value of the detected sizes of the traffic participants corresponding to each frame of point cloud data can also be calculated, and the difference between the mean value and the actual size of the traffic participant is determined as the traffic participant parameter difference corresponding to each frame of point cloud data.

[0136] Correspondingly, when testing the detection accuracy of the lidar corresponding to the type detection accuracy of the traffic participant, the number of point cloud data with the detected type of the traffic participant being different from the actual type of the traffic participant can also be determined, and the ratio of this number to the total number of point cloud data is determined as the traffic participant parameter difference corresponding to each frame of point cloud data.

[0137] Correspondingly, when testing the detection accuracy of the lidar corresponding to the color detection accuracy of the traffic participant, the number of point cloud data with the detected color of the traffic participant being different from the actual color of the traffic participant can also be determined, and the ratio of this number to the total number of point cloud data is determined as the traffic participant parameter difference corresponding to each frame of point cloud data.

[0138] It should be noted that when measuring whether the traffic participant detection parameters are the same as the actual parameters through the confidence level, it can be determined that the traffic participant detection parameters corresponding to the point cloud data are the same as the actual parameters when the confidence level between the traffic participant detection parameters and the actual parameters corresponding to the point cloud data is greater than or equal to the confidence level threshold; when the confidence level between the traffic participant detection parameters and the actual parameters corresponding to the point cloud data is less than the confidence level threshold, it is determined that the traffic participant detection parameters corresponding to the point cloud data are different from the actual parameters.

[0139] As a possible implementation, after determining the traffic participant parameter difference corresponding to each frame of point cloud data through the above method, the traffic participant parameter difference can be directly determined as the detection accuracy corresponding to the lidar; or, when the traffic participant parameter difference corresponding to the point cloud data has a negative correlation with the actual detection accuracy of the lidar, in order to make the specific value of the finally obtained detection accuracy have a positive correlation with the performance of the lidar, after determining the traffic participant parameter difference, the reciprocal of the traffic participant parameter difference can also be determined as the detection accuracy corresponding to the lidar.

[0140] For example, assume that the traffic participant is a motor vehicle and the traffic participant parameter is size. Then, the detected size of the traffic participant can include the detected length, width, and height, and the actual size of the traffic participant can include the actual length, width, and height of the traffic participant. The detection accuracy of the lidar can be determined by the following formula:

[0141]

[0142] where E d is the detection accuracy corresponding to the lidar, l′ j is the average detected length of the j-th traffic participant in all point cloud data, l j is the actual length of the j-th traffic participant, w′ j is the average detected width of the j-th traffic participant in all point cloud data, w j is the actual width of the i-th traffic participant, h′ j is the average detected height of the j-th traffic participant in all point cloud data, h j is the actual height of the j-th traffic participant, M is the number of traffic participants, j is the serial number of the traffic participant, and M is a positive integer.

[0143] It should be noted that the above example is only exemplary and should not be regarded as a limitation to this application. In actual use, appropriate parameters can be selected according to actual needs and specific application scenarios to evaluate the detection accuracy corresponding to the lidar, and appropriate methods can be selected to determine the difference in traffic participant parameters and measure the correlation between the difference in traffic participant parameters and the detection accuracy of the lidar. The embodiments of this application do not make any limitations in this regard.

[0144] It should be noted that in each of the above-listed methods for determining the detection accuracy, after determining the detection accuracy according to any of the above methods, the detection accuracy can also be normalized to normalize the detection accuracy to the same numerical interval, such as [0, 1], [0, 10], [0, 100], etc., and the normalized result can be determined as the detection accuracy corresponding to the lidar to improve the standardization and accuracy of the detection accuracy.

[0145] As another possible implementation, when testing the detection accuracy of a lidar by multiple parameters such as the size detection accuracy, type detection accuracy, and color detection accuracy of traffic participants, after separately determining the detection accuracy of the lidar under each parameter according to the above method, the final detection accuracy of the lidar can be determined based on the detection accuracy of the lidar under each parameter. For example, the sum of the detection accuracies of the lidar under each parameter can be determined as the final detection accuracy of the lidar; or, the average value of the detection accuracies of the lidar under each parameter can be determined as the final detection accuracy of the lidar; or, according to the importance of each detection accuracy, different weights can be assigned to each detection accuracy, and the weighted sum of the detection accuracies of the lidar under each parameter can be determined as the final detection accuracy of the lidar, and so on.

[0146] The lidar testing method provided by the embodiments of the present application builds an experimental environment that simulates the actual use environment of a roadside lidar, determines the traffic participant recognition result corresponding to each frame of point cloud data according to the point cloud data of traffic participants collected by the lidar, and then evaluates the traffic participant recognition result according to the pre-configured test conditions, so as to effectively evaluate the performance parameters corresponding to the lidar, and timely discover possible problems in the actual use of the lidar according to the test results for improvement, thereby ensuring the reliability and stability of the lidar during use.

[0147] In a possible implementation form of the present application, since the effective vertical field of view angle of the lidar can measure the field of view range of the lidar, the effective vertical field of view angle of the lidar can also be tested to facilitate targeted improvement of the field of view range of the lidar, and further improve the reliability and stability of the lidar in practical applications.

[0148] The following combines Figure 4 , and further describes the lidar testing method provided by the embodiments of the present application.

[0149] Figure 4 The flowchart of another lidar testing method provided by the embodiments of the present application is shown.

[0150] As Figure 4 shown, the lidar testing method includes the following steps:

[0151] Step 401, obtain the current test conditions corresponding to the lidar, where the current test conditions include the first point cloud condition and the installation height corresponding to the lidar.

[0152] Among them, the first point cloud condition may include the first point cloud quantity condition, the first point cloud row number condition, and the first distance condition.

[0153] Among them, the installation height corresponding to the lidar may refer to the vertical height of the lidar from the ground.

[0154] In a possible implementation manner of the embodiment of the present application, the first point cloud condition can be used to screen out the point cloud data that can be used to determine the effective vertical field of view angle corresponding to the lidar from the acquired frames of point cloud data; for example, the first point cloud condition can be set according to the point cloud characteristics when the traffic participant is at the edge of the field of view of the lidar. Among them, the first point cloud quantity condition can be used to limit the number of point cloud points corresponding to the traffic participant in the point cloud data; the first point cloud row condition can be used to limit the number of rows of point cloud points corresponding to the traffic participant in the point cloud data; the first distance condition can be used to limit the horizontal distance between the traffic participant and the lidar.

[0155] As an example, as Figure 5 shown, it is a schematic diagram of the effective vertical field of view angle corresponding to a lidar provided by an embodiment of the present application. Among them, the installation height corresponding to the lidar 210 is H1, point A and point B are respectively the edges of the field of view corresponding to the lidar 210. Assuming that each laser beam emitted by the lidar 210 contains n detection lines, then 240 can be the (n - 1)-th detection line in a certain laser beam emitted by the lidar 210, and 250 is the 2nd detection line in another laser beam emitted by the lidar 210. Then the effective vertical field of view angle corresponding to the lidar 210 can be represented as angle 260 in the figure; from Figure 5 it can be seen that if the point cloud data corresponding to the traffic participants 230 at point A and point B can be collected and screened out, then the horizontal distance L1 between point A and the lidar 210, and the horizontal distance L2 between point B and the lidar 210 can be determined according to the point cloud data corresponding to these two traffic participants 230. Furthermore, according to the installation height H1, the horizontal distance L1, and the horizontal distance L2, the effective vertical field of view angle 260 corresponding to the lidar 210 can be calculated.

[0156] From Figure 5 it can be seen that when the traffic participant 230 is at point A or point B, the lidar 210 can collect the point cloud data of the front view or the rear view corresponding to the traffic participant 230. Assuming that the front view and the rear view corresponding to the traffic participant 230 are as Figure 6 shown, the schematic diagram of the point cloud points of the front view and the rear view corresponding to the traffic participant 230 at point A or point B is as Figure 7As shown, it can be seen that the number of corresponding point cloud points of the traffic participant 230 at point A or point B is 5, and the number of rows of the point cloud points is 2 rows; it can be understood that if the traffic participant 230 is at a position between point A and point B, the number of corresponding point cloud points of the traffic participant 230 in the point cloud data will be greater than or equal to 5, and / or the number of rows of the corresponding point cloud points of the traffic participant 230 in the point cloud data will be greater than or equal to 2 rows. Therefore, in order to filter out the point cloud data corresponding to the traffic participant 230 at the edge of the field of view of the lidar 210, the first point cloud quantity condition can be determined to be greater than a first preset quantity (such as 4), and the first point cloud row number condition can be determined to be greater than or equal to a first preset row number (such as 2 rows), because if the number of detection lines of the lidar hitting the traffic participant is too small, it is usually impossible to effectively identify the traffic participant, and thus it cannot be considered to be within the effective vertical field of view angle corresponding to the lidar; through the above first point cloud quantity condition and the first point cloud row number condition, the point cloud data corresponding to all traffic participants 230 with a horizontal distance greater than or equal to L1 and less than or equal to L2 from the lidar 210 can be filtered out (if the traffic participant 230 moves along the straight line where point A and point B are located, the point cloud data corresponding to all traffic participants 230 between point A and point B can be filtered out); it is easy to understand that among all the point cloud data filtered out according to the above first point cloud quantity condition and the first point cloud row number condition, only the point cloud data corresponding to the traffic participant 230 with the closest and farthest distances can be used to calculate the effective vertical field of view angle corresponding to the lidar 210. Therefore, the first distance condition can be set to be the closest or farthest horizontal distance from the lidar, so that through the above conditions, the point cloud data corresponding to the traffic participant 230 corresponding to point A and point B in Figure 5 can be filtered out to be used to determine the effective vertical field of view angle corresponding to the lidar 210.

[0157] It should be noted that Figure 7 the number and rows of the point cloud points in the front view and rear view corresponding to the traffic participant shown in

[0158] are only exemplary and should not be regarded as a limitation to this application.

[0159] Step 402, obtain multiple frames of point cloud data corresponding to the traffic participant collected by the lidar in the test environment.

[0160] As a possible implementation, in order to improve the accuracy of determining the effective vertical field of view angle, when collecting point cloud data, the traffic participant can also be made to move along one of the coordinate axes of the coordinate system corresponding to the lidar, so that according to the first point cloud condition, two frames of point cloud data corresponding to the traffic participants at the edge of the field of view range of the lidar can be directly filtered out.

[0161] For example, assume that the coordinate system corresponding to the lidar is as Figure 5 shown, where the X-axis is parallel to the ground plane, the Y-axis is perpendicular to the X-axis, and the Z-axis is perpendicular to the plane formed by the X-axis and the Y-axis. Then, when testing the effective vertical field of view angle corresponding to the lidar 210, the moving direction of the traffic participant can be made parallel to the X-axis.

[0162] For other specific implementation processes and principles of step 402 above, reference can be made to the detailed description of the above embodiments, which will not be elaborated here.

[0163] Step 403: Perform recognition processing on each frame of point cloud data to determine the target point cloud points corresponding to each frame of point cloud data, where the target point cloud points refer to the point cloud points corresponding to the traffic participants.

[0164] In the embodiment of the present application, after obtaining each frame of point cloud data collected by the lidar, the target point cloud points corresponding to the traffic participants included in each frame of point cloud data can be recognized to determine the target point cloud points included in each frame of point cloud data, and then according to the number of target point cloud points included in each frame of point cloud data, the point cloud data that can be used to calculate the effective vertical field of view angle corresponding to the lidar can be filtered out as described above.

[0165] Step 404: Determine the point cloud data whose target point cloud points meet the first point cloud condition as the first target point cloud data.

[0166] In the embodiment of the present application, after determining the target point cloud points corresponding to each frame of point cloud data, the point cloud data whose included target point cloud points meet the first point cloud condition can be filtered out according to the first point cloud condition as the first target point cloud data that can be used to calculate the effective vertical field of view angle corresponding to the lidar.

[0167] As a possible implementation, when the first point cloud condition includes the first point cloud quantity condition, the first point cloud row number condition, and the first distance condition, the first target point cloud data can be determined in the following manner:

[0168] Perform recognition processing on the target point cloud points corresponding to each frame of point cloud data to determine the number of target point cloud points, the number of rows of target point cloud points, and the horizontal distance between the traffic participant and the lidar corresponding to each frame of point cloud data;

[0169] The point cloud data where the number of target point cloud points meets the first point cloud number condition, the number of rows of target point cloud points meets the first point cloud row number condition, and the horizontal distance between the traffic participant and the lidar meets the first distance condition is determined as the first target point cloud data.

[0170] As an example, as Figure 5 shown, through the analysis of the foregoing steps, assuming that the first point cloud number condition is greater than the first preset number, and the first point cloud row number condition is greater than or equal to the first preset row number, then first, according to this condition, the point cloud data corresponding to the traffic participants whose horizontal distance from the lidar 210 is between L1 and L2 can be filtered out, that is, the reference point cloud data; assuming that the first distance condition is that the horizontal distance between the lidar and the reference point cloud data is the smallest or the largest, then according to the horizontal distance between the traffic participants corresponding to each reference point cloud data and the lidar, two frames of point cloud data corresponding to the traffic participants at the edge of the lidar field of view can be filtered out as the first target point cloud data; for example, in Figure 5 it, the first target point cloud data can be the point cloud data collected when the traffic participant 230 is at point A, and the point cloud data collected when the traffic participant 230 is at point B.

[0171] Step 405: Perform recognition processing on each frame of the first target point cloud data to determine the horizontal distance between the traffic participant corresponding to each frame of the first target point cloud data and the lidar.

[0172] In the embodiment of the present application, after determining the first target point cloud data for calculating the effective vertical field of view angle corresponding to the lidar, each frame of the first target point cloud data can be subjected to recognition processing to determine the horizontal distance between the traffic participant corresponding to each frame of the first target point cloud data and the lidar.

[0173] For example, as Figure 5 shown, the first target point cloud data can be the point cloud data collected when the traffic participant 230 is at point A, and the point cloud data collected when the traffic participant 230 is at point B. Then, by performing recognition processing on these two frames of the first target point cloud data, the minimum horizontal distance L1 and the maximum horizontal distance L2 can be determined.

[0174] Step 406: Determine the effective vertical field of view angle corresponding to the lidar according to the installation height and the horizontal distance between the traffic participant corresponding to each frame of the first target point cloud data and the lidar.

[0175] In the embodiment of the present application, after the horizontal distance between the traffic participant corresponding to each frame of the first target point cloud data and the lidar, as Figure 5 shown, the effective vertical field of view angle corresponding to the lidar can be determined through the following formula:

[0176]

[0177] Wherein, α is the effective vertical field of view angle corresponding to the lidar, H1 is the installation height corresponding to the lidar, L1 is the minimum horizontal distance between the traffic participants recognizable by the lidar and the lidar, and L2 is the maximum horizontal distance between the traffic participants recognizable by the lidar and the lidar.

[0178] It should be noted that when testing the effective vertical field of view angle corresponding to the lidar, multiple tests can also be carried out in the above manner to determine multiple effective vertical field of view angles, and then the effective vertical field of view angle corresponding to the lidar can be determined according to the multiple measured effective vertical field of view angles. For example, the average value of the multiple measured effective vertical field of view angles can be determined as the effective vertical field of view angle corresponding to the lidar.

[0179] The lidar testing method provided by the embodiment of the present application builds an experimental environment that simulates the real usage environment of the roadside lidar, and determines the point cloud points corresponding to the traffic participants included in each frame of point cloud data according to the point cloud data of the traffic participants collected by the lidar. Furthermore, according to the pre-configured first point cloud condition, the point cloud data corresponding to the traffic participants at the edge of the field of view range of the lidar is screened out, so as to calculate the effective vertical field of view angle corresponding to the lidar according to the screened point cloud data, thereby realizing an effective evaluation of the effective vertical field of view angle corresponding to the lidar, and timely discovering possible problems with the field of view range of the lidar during actual use according to the test results for targeted improvement, thereby further improving the reliability and stability of the lidar in actual applications.

[0180] In a possible implementation form of the present application, since the maximum detection distance of the lidar can also measure the field of view range of the lidar, the maximum detection distance of the lidar can also be tested to facilitate targeted improvement of the field of view range of the lidar and further improve the reliability and stability of the lidar in actual applications.

[0181] The following combines Figure 8 , and further describes the lidar testing method provided by the embodiment of the present application.

[0182] Figure 8 The flowchart of still another lidar testing method provided by the embodiment of the present application is shown.

[0183] As Figure 8 shown, the lidar testing method includes the following steps:

[0184] Step 801, obtain the current test conditions corresponding to the lidar, where the current test conditions include the second point cloud condition.

[0185] Among them, the second point cloud condition may include a second point cloud quantity condition, a second point cloud row number condition, a second distance condition, and a second moving direction.

[0186] In a possible implementation manner of the embodiment of the present application, the second point cloud condition can be used to screen out the point cloud data that can be used to determine the maximum detection distance corresponding to the lidar from the acquired frame point cloud data; for example, the second point cloud condition can be set according to the point cloud characteristics when the traffic participant is at the edge of the field of view range of the lidar and the horizontal distance from the lidar is the largest. Among them, the second point cloud quantity condition can be used to limit the number of point cloud points corresponding to the traffic participant in the point cloud data; the second point cloud row number condition can be used to limit the number of rows of point cloud points corresponding to the traffic participant in the point cloud data; the second distance condition can be used to limit the horizontal distance between the traffic participant and the lidar; the second moving direction can be used to limit the moving direction of the traffic participant relative to the lidar.

[0187] As an example, as Figure 9 shown, it is a schematic diagram of the maximum detection distance corresponding to a lidar provided by an embodiment of the present application. Points B1 and B2 are respectively the edges of the field of view range corresponding to the lidar 210 and the points farthest from the lidar 210. The distance between B1 and B2, that is, L3 + L4, is the maximum detection distance corresponding to the lidar 210. From Figure 9 it can be seen that if the point cloud data corresponding to the traffic participants 230 at points B1 and B2 can be collected and screened out, then the horizontal distance L3 between point B1 and the lidar 210 and the horizontal distance L4 between point B2 and the lidar 210 can be determined according to the point cloud data corresponding to these two traffic participants 230. Furthermore, by adding the horizontal distance L3 and the horizontal distance L4, the maximum detection distance corresponding to the lidar 210 can be obtained.

[0188] From Figure 7 it can be seen that when the traffic participant 230 is at point B1 or B2, the lidar 210 can collect the point cloud data of the front view or the rear view corresponding to the traffic participant 230. Assume that the front view and the rear view corresponding to the traffic participant 230 are as Figure 6 shown, and the schematic diagram of the point cloud points of the front view and the rear view corresponding to the traffic participant 230 at point B1 or B2 is as Figure 7As shown in the figure, through the analysis of the foregoing embodiments, it can be determined that the second point cloud quantity condition is greater than a second preset quantity (such as 4), and the second point cloud row number condition can be determined to be greater than or equal to a second preset row number (such as 2 rows). This is because if the number of detection lines of the lidar hitting the traffic participant is too small, it is usually impossible to effectively identify the traffic participant, and thus it cannot be considered that the traffic participant is within the maximum detection distance corresponding to the lidar; it is easy to understand that among all the point cloud data filtered according to the above second point cloud quantity condition and second point cloud row number condition, the point cloud data corresponding to the traffic participant 230 with the farthest distance is the point cloud data that can be used to calculate the maximum detection distance corresponding to the lidar 210. Therefore, the second distance condition can be set to be the farthest horizontal distance from the lidar; from Figure 9 As can be seen, to calculate the maximum detection distance corresponding to the lidar 210, points B1 and B2 need to be on a straight line, so that the moving direction of the traffic participant can be restricted by the second moving direction, so as to simultaneously filter out at least two frames of point cloud data corresponding to the traffic participants that are on the same straight line and have the farthest horizontal distance from the lidar. For example, the coordinate system corresponding to the lidar 210 is as Figure 9 shown, the X-axis is parallel to the ground plane, the positive direction of the X-axis is horizontally to the right, the Y-axis is perpendicular to the X-axis, and the Z-axis is perpendicular to the plane formed by the X-axis and the Y-axis. Then the second moving direction can be set to have an angle of 0° and 180° with the positive direction of the X-axis, so that through the above conditions, the two frames of point cloud data corresponding to the traffic participant 230 corresponding to points B1 and B2 in Figure 9 can be filtered out; or, the second moving direction can be set to have an angle of 90° and 270° with the positive direction of the X-axis, that is, an angle of 0° and 180° with the positive direction of the Z-axis, so that through the above conditions, the two frames of point cloud data corresponding to the traffic participant 230 corresponding to points C1 and C2 in Figure 10 can be filtered out; or, the second moving direction can also be set to have angles of 0°, 90°, 180°, and 270° with the positive direction of the X-axis, so that through the above conditions, the four frames of point cloud data corresponding to the traffic participant 230 corresponding to points B1, B2, C1, and C2 in Figure 10 can be filtered out.

[0189] For the other specific implementation processes and principles of step 801 above, reference can be made to the detailed description of the foregoing embodiments, and details will not be elaborated here.

[0190] Step 802, obtain multiple frames of point cloud data corresponding to traffic participants collected by the lidar in the test environment.

[0191] As a possible implementation, in order to improve the accuracy of determining the effective vertical field of view angle, when collecting point cloud data, the traffic participants can also be moved along one or two coordinate axes of the coordinate system corresponding to the lidar, so that according to the second point cloud condition, two or four frames of point cloud data corresponding to the traffic participants at the edge of the field of view range of the lidar can be directly filtered out.

[0192] For example, assume that the coordinate system corresponding to the lidar is as Figure 9 shown, where the X-axis is parallel to the ground plane, the Y-axis is perpendicular to the X-axis, and the Z-axis is perpendicular to the plane formed by the X-axis and the Y-axis. Then, when testing the maximum detection distance corresponding to the lidar 210, the traffic participants can be moved parallel to the X-axis to collect point cloud data, and the traffic participants can be moved parallel to the Z-axis to continue collecting point cloud data.

[0193] For other specific implementation processes and principles of step 802 above, reference can be made to the detailed description of the above embodiments, which will not be elaborated here.

[0194] Step 803: Perform recognition processing on each frame of point cloud data to determine the target point cloud points corresponding to each frame of point cloud data, where the target point cloud points refer to the point cloud points corresponding to the traffic participants.

[0195] In the embodiments of the present application, after obtaining each frame of point cloud data collected by the lidar, the target point cloud points corresponding to the traffic participants included in each frame of point cloud data can be recognized to determine the target point cloud points included in each frame of point cloud data, and then, according to the number of target point cloud points included in each frame of point cloud data, the point cloud data that can be used to calculate the maximum detection distance corresponding to the lidar can be filtered out as described above.

[0196] Step 804: Determine the point cloud data whose target point cloud points meet the second point cloud condition as the second target point cloud data.

[0197] In the embodiments of the present application, after determining the target point cloud points corresponding to each frame of point cloud data, the point cloud data whose included target point cloud points meet the second point cloud condition can be filtered out according to the second point cloud condition as the second target point cloud data that can be used to calculate the maximum detection distance corresponding to the lidar.

[0198] As a possible implementation, when the second point cloud condition includes the second point cloud quantity condition, the second point cloud row number condition, the second distance condition, and the second movement direction, the second target point cloud data can be determined in the following manner:

[0199] Identify and process the target point cloud points corresponding to each frame of point cloud data to determine the number of target point cloud points, the number of target point cloud point rows, the horizontal distance between the traffic participant and the laser radar, and the moving direction of the traffic participant corresponding to each frame of point cloud data;

[0200] The point cloud data whose target point cloud point quantity meets the second point cloud quantity condition, whose target point cloud point row number meets the second point cloud row number condition, whose horizontal distance between the traffic participant and the laser radar meets the second distance condition, and whose traffic participant moving direction meets the second moving direction is determined as the second target point cloud data.

[0201] As an example, Figure 9 and Figure 10 As shown, through the analysis of the above steps, assuming that the second point cloud quantity condition is greater than the second preset quantity, and the second point cloud row number condition is greater than or equal to the second preset row number, the condition can first filter out the horizontal distance between the laser radar 210 and Figure 5 The point cloud data corresponding to the traffic participants between L1 and L2 in the figure are the reference point cloud data; assuming that the angle between the second moving direction and the positive direction of the X-axis is 0°, 90°, 180° and 270°, and the second distance condition is that the horizontal distance between the laser radar and each moving direction is the maximum, then the 4 frames of point cloud data corresponding to the traffic participants at the edge of the laser radar field of view can be selected as the second target point cloud data according to the horizontal distance and moving direction between the traffic participants corresponding to each reference point cloud data and the laser radar; for example, Figure 10 In the figure, the second target point cloud data may be the point cloud data collected when the traffic participant 230 is at point B1, the point cloud data collected when the traffic participant 230 is at point B2, the point cloud data collected when the traffic participant 230 is at point C1, and the point cloud data collected when the traffic participant 230 is at point C2.

[0202] For another example, if the angle between the second moving direction and the positive direction of the X-axis is 0° and 180°, and other conditions remain unchanged, the second target point cloud data may be the point cloud data collected when the traffic participant 230 is at point B1, and the point cloud data collected when the traffic participant 230 is at point B2. If the angle between the second moving direction and the positive direction of the X-axis is 90° and 270°, and other conditions remain unchanged, the second target point cloud data may be the point cloud data collected when the traffic participant 230 is at point C1, and the point cloud data collected when the traffic participant 230 is at point C2.

[0203] Step 805 , performing recognition processing on each frame of the second target point cloud data to determine the horizontal distance between the traffic participant corresponding to each frame of the second target point cloud data and the laser radar.

[0204] In an embodiment of the present application, after determining the second target point cloud data corresponding to the maximum detection distance of the lidar, each frame of the second target point cloud data can be identified to determine the horizontal distance between the traffic participant corresponding to each frame of the second target point cloud data and the lidar.

[0205] For example, as Figure 10 shown, if the second target point cloud data is the point cloud data collected when the traffic participant 230 is at point B1, the point cloud data collected when the traffic participant 230 is at point B2, the point cloud data collected when the traffic participant 230 is at point C1, and the point cloud data collected when the traffic participant 230 is at point C2, then by identifying and processing these 4 frames of second target point cloud data, the horizontal distances L3 and L4 parallel to the X-axis, and the horizontal distances L5 and L6 parallel to the Z-axis (i.e., perpendicular to the X-axis) can be determined.

[0206] Step 806, determine the maximum detection distance of the lidar according to the horizontal distance between the traffic participant corresponding to each frame of the second target point cloud data and the lidar.

[0207] As a possible implementation, if only two frames of second target point cloud data of traffic participants on a straight line are selected, the sum of the horizontal distances between the traffic participants corresponding to these two frames of second target point cloud data and the lidar can be determined as the maximum detection distance of the lidar.

[0208] For example, assume that the second target point cloud data is the point cloud data collected when the traffic participant 230 is at point B1 and the point cloud data collected when the traffic participant 230 is at point B2, that is, the horizontal distances between the traffic participants corresponding to the two frames of second target point cloud data and the lidar are L3 and L4 respectively, then the maximum detection distance of the lidar can be determined as L3 + L4.

[0209] Another example, assume that the second target point cloud data is the point cloud data collected when the traffic participant 230 is at point C1 and the point cloud data collected when the traffic participant 230 is at point C2, that is, the horizontal distances between the traffic participants corresponding to the two frames of second target point cloud data and the lidar are L5 and L6 respectively, then the maximum detection distance of the lidar can be determined as L5 + L6.

[0210] As a possible implementation, if only two frames of second target point cloud data of traffic participants on two straight lines are selected, the sum of the horizontal distances between the traffic participants on these two straight lines and the lidar can be calculated respectively, and the larger value between the two can be determined as the maximum detection distance of the lidar.

[0211] For example, if the second target point cloud data is the point cloud data collected when the traffic participant 230 is at point B1, the point cloud data collected when the traffic participant 230 is at point B2, the point cloud data collected when the traffic participant 230 is at point C1, and the point cloud data collected when the traffic participant 230 is at point C2, then the sum of the horizontal distance L3 and the horizontal distance L4, and the sum of the horizontal distance L5 and the horizontal distance L6 can be determined; if L3 + L4 > L5 + L6, then L3 + L4 can be determined as the maximum detection distance corresponding to the lidar; if L3 + L4 < L5 + L6, then L5 + L6 can be determined as the maximum detection distance corresponding to the lidar.

[0212] It should be noted that when testing the maximum detection distance corresponding to the lidar, the above method can also be used for multiple tests to determine multiple maximum detection distances, and then determine the maximum detection distance corresponding to the lidar based on the multiple measured maximum detection distances. For example, the mean value of the multiple measured maximum detection distances can be determined as the maximum detection distance corresponding to the lidar.

[0213] The lidar test method provided by the embodiments of the present application builds an experimental environment that simulates the actual use environment of the roadside lidar, determines the point cloud points corresponding to the traffic participants included in each frame of point cloud data according to the point cloud data of the traffic participants collected by the lidar, and then filters out the point cloud data corresponding to the traffic participants at the edge of the field of view range of the lidar according to the pre-configured second point cloud condition, so as to calculate the maximum detection distance corresponding to the lidar based on the filtered point cloud data, thereby effectively evaluating the maximum detection distance corresponding to the lidar, and timely discovering possible field of view range problems of the lidar in actual use according to the test results for targeted improvement, thereby further improving the reliability and stability of the lidar in actual application.

[0214] In a possible implementation form of the present application, due to the performance limitations of the lidar itself or limited by the installation conditions of the lidar, the lidar may not be able to obtain a 360° horizontal field of view angle. Therefore, the effective horizontal field of view angle of the lidar can also be tested to facilitate targeted improvement of the field of view range of the lidar or guidance for the actual installation of the lidar, and further improve the reliability and stability of the lidar in actual application.

[0215] The following combines Figure 11 , and further illustrates the lidar test method provided by the embodiments of the present application.

[0216] Figure 11 Fig. shows a schematic flowchart of another lidar test method provided by the embodiments of the present application.

[0217] AsFigure 11 As shown in the figure, the test method of the lidar includes the following steps:

[0218] Step 1101: Obtain the current test conditions corresponding to the lidar, where the current test conditions include the third point cloud condition.

[0219] Among them, the lidar can be installed on a rotating device, and the rotating device can drive the lidar to rotate when it rotates.

[0220] As a possible implementation, in order to test the effective horizontal field of view angle corresponding to the lidar, traffic participants can be made to move within the 360° area around the lidar and maintain a certain distance from the lidar, so that the traffic participants are within the effective vertical field of view angle corresponding to the lidar. Then, according to the positions of the traffic participants that can be detected by the lidar, the effective horizontal field of view angle corresponding to the lidar can be determined. However, testing in this way requires a large test site. Therefore, in order to save the test site and reduce the environmental conditions required for testing, making the test easier to implement, the lidar can be installed on a rotating device, such as a rotatable vertical pole, so as to drive the lidar to rotate through the rotating device, achieving the purpose of changing the relative position between the lidar and the traffic participants. By testing in this way, the traffic participants can be in a fixed position, thus saving the test site and reducing the environmental requirements for implementing the test.

[0221] Among them, the third point cloud condition can include the third point cloud quantity condition and the third point cloud row condition.

[0222] In a possible implementation of the embodiment of the present application, the third point cloud condition can be used to screen out the point cloud data that can be used to determine the effective horizontal field of view angle corresponding to the lidar from the acquired frames of point cloud data; for example, the third point cloud condition can be set according to the point cloud characteristics when the traffic participants are at the edge of the field of view of the lidar. Among them, the third point cloud quantity condition can be used to limit the number of point cloud points corresponding to the traffic participants in the point cloud data; the third point cloud row condition can be used to limit the number of rows of point cloud points corresponding to the traffic participants in the point cloud data.

[0223] It should be noted that the first point cloud quantity condition, the second point cloud quantity condition, and the third point cloud quantity condition mentioned in the embodiment of the present application can be the same or different; and the first point cloud row condition, the second point cloud row condition, and the third point cloud row condition can be the same or different, and the embodiment of the present application does not make any limitations in this regard.

[0224] As an example, assuming that when the traffic participants are at the edge of the field of view of the lidar, the schematic diagram of the point cloud points is as Figure 7As shown, when the traffic participant is at the critical condition of the edge of the field of view of the lidar, the number of point cloud points corresponding to this is 5, and the number of rows of point cloud points is 2 rows. It can be understood that if the traffic participant is at other positions within the field of view of the lidar, the number of point cloud points corresponding to the traffic participant in the point cloud data will be greater than or equal to 5, and / or the number of rows of point cloud points corresponding to the traffic participant in the point cloud data will be greater than or equal to 2 rows. Therefore, in order to screen out the point cloud data corresponding to the traffic participants at the edge of the field of view of the lidar, the third point cloud number condition can be determined to be within a preset number range (such as 5 - 10), and the third point cloud row number condition can be determined to be greater than or equal to a preset row number range (such as 2 - 5). This is because if the number of detection lines of the lidar hitting the traffic participant is too small, it is usually impossible to effectively identify the traffic participant, and thus it cannot be considered to be within the effective horizontal field of view angle corresponding to the lidar. And if the third point cloud number condition and the third point cloud row number condition are directly determined to be the above critical values (such as 5 and 2 rows), due to the complex situation in the actual use process of the lidar, it is very difficult to ensure that the point cloud data meeting this critical value can be detected, resulting in a test failure; while determining the third point cloud number condition and the third point cloud row number condition to be too large values will also cause the point cloud data corresponding to the traffic participant at the edge of the field of view of the lidar not to be measured, resulting in a large deviation in the test results. Therefore, the third point cloud number condition and the third point cloud row number condition can be determined to be a numerical range close to the above critical value to ensure the accuracy of the effective horizontal field of view angle test; through the above third point cloud number condition and the third point cloud row number condition, the point cloud data corresponding to the traffic participants at or very close to the edge of the field of view of the lidar can be screened out for determining the effective horizontal field of view angle corresponding to the lidar.

[0225] It should be noted that the above-listed third point cloud number condition and the third point cloud row number condition are only exemplary and should not be regarded as a limitation to this application. In actual use, the third point cloud number condition and the third point cloud row number condition can be set according to actual needs, specific application scenarios, and based on the principles described above. The embodiments of this application do not make any limitations in this regard.

[0226] For the other specific implementation processes and principles of the above step 1101, reference can be made to the detailed description of the above embodiments, and details will not be repeated here.

[0227] Step 1102, obtain multiple frames of point cloud data corresponding to traffic participants collected by the lidar in the test environment.

[0228] Among them, each frame of point cloud data is collected when the rotating device rotates, and the traffic participant is within the effective vertical field of view angle corresponding to the lidar and is stationary.

[0229] As a possible implementation, from the description of the foregoing steps, it can be seen that when determining the effective horizontal field of view angle corresponding to the lidar, a traffic participant can be placed at any position within the effective vertical field of view angle corresponding to the lidar and kept stationary, and the rotation device can be driven to rotate the lidar to change the relative position between the lidar and the traffic participant. Therefore, during the process of the lidar collecting point cloud data, the rotation device can be controlled to rotate at a certain angular step, and at each rotation angle corresponding to the rotation device, the lidar can collect at least one frame of point cloud data (that is, the rotation rate of the rotation device can be less than the collection frame rate corresponding to the lidar), so that multiple frames of point cloud data can be obtained during the process of the rotation device rotating one week. Then, based on the point cloud data collected during the process of the rotation device rotating one week, the effective horizontal field of view angle corresponding to the lidar can be determined.

[0230] For example, the angular step when the rotation device rotates can be 1°, and the rotation rate is 1 rotation per second, that is, it takes 360 seconds for the rotation device to rotate one week.

[0231] It should be noted that the above example is only exemplary and should not be regarded as a limitation to this application. In actual use, the angular step and rotation rate when the rotation device rotates can be set according to actual needs and specific application scenarios, and the embodiments of this application do not make any limitations in this regard.

[0232] For the other specific implementation processes and principles of the above step 1102, reference can be made to the detailed description of the above embodiments, and details will not be described here again.

[0233] Step 1103: Perform recognition processing on each frame of point cloud data to determine the target point cloud points corresponding to each frame of point cloud data and the cumulative rotation angle of the rotation device, where the target point cloud points refer to the point cloud points corresponding to the traffic participant.

[0234] Among them, the cumulative rotation angle of the rotation device corresponding to the point cloud data can refer to the total angle that the rotation device has cumulatively rotated when the lidar collects this point cloud data.

[0235] For example, assume that the rotation step when the rotation device rotates is 1°. When the lidar collects a frame of point cloud data, the rotation device has rotated 3 times, then it can be determined that the cumulative rotation angle corresponding to this frame of point cloud data is 3°.

[0236] In an embodiment of the present application, after obtaining each frame of point cloud data collected by the lidar, the target point cloud points corresponding to traffic participants in each frame of point cloud data can be identified to determine the target point cloud points and the corresponding cumulative rotation angles included in each frame of point cloud data. Furthermore, according to the number and rows of the target point cloud points included in each frame of point cloud data, the point cloud data that can be used to calculate the effective horizontal field of view angle corresponding to the lidar can be screened out as described above.

[0237] Step 1104: Determine the point cloud data with target point cloud points satisfying the third point cloud condition as the third target point cloud data.

[0238] In an embodiment of the present application, after determining the target point cloud points corresponding to each frame of point cloud data, the point cloud data with the target point cloud points satisfying the third point cloud condition can be screened out according to the third point cloud condition as the third target point cloud data that can be used to calculate the effective horizontal field of view angle corresponding to the lidar.

[0239] As a possible implementation, when the third point cloud condition includes a third point cloud quantity condition and a third point cloud row condition, the third target point cloud data can be determined in the following manner:

[0240] Perform identification processing on the target point cloud points corresponding to each frame of point cloud data to determine the number of target point cloud points and the number of rows of target point cloud points corresponding to each frame of point cloud data;

[0241] Determine the point cloud data with the number of target point cloud points satisfying the third point cloud quantity condition and the number of rows of target point cloud points satisfying the third point cloud row condition as the third target point cloud data.

[0242] As an example, through the analysis of the foregoing steps, assuming that the third point cloud quantity condition is within a preset quantity range and the third point cloud row condition is within a preset row range, the point cloud data with the number of corresponding target point cloud points within the preset quantity range and the number of rows of target point cloud points within the preset row range can be screened out as the third target point cloud data.

[0243] It should be noted that since the traffic participants are stationary, the relative positions between the lidar and the traffic participants are the same at the same rotation angle of the rotating device. That is, when the rotating device rotates to a certain fixed angle, if the lidar collects multiple frames of point cloud data, then these frames of point cloud data are the same. Therefore, for these frames of point cloud data, one frame of point cloud data can be randomly selected for processing to determine whether the point cloud data is the third target point cloud data.

[0244] For example, assume that the angular step of the rotating device during rotation is 1°, that is, the rotating device needs to rotate 360 times to complete one full rotation. If the lidar collects 100 frames of point cloud data at each rotation angle of the rotating device, then one frame of point cloud data can be randomly selected from the 100 frames of point cloud data corresponding to each rotation angle, so that 360 different frames of point cloud data can be selected, and the third target point cloud data that meets the third point cloud condition can be screened out from these 360 frames of point cloud data.

[0245] Step 1105: Determine the effective horizontal field of view angle corresponding to the lidar according to the cumulative rotation angle corresponding to the third target point cloud data.

[0246] As a possible implementation, if the two frames of third target point cloud data are screened out and the cumulative rotation angles corresponding to these two frames of target point cloud data are different, it can be determined that these two frames of point cloud data are collected at the critical positions of the effective horizontal field of view angle corresponding to the lidar. Therefore, the absolute value of the difference between the cumulative rotation angles corresponding to these two frames of third target point cloud data can be determined as the effective horizontal field of view angle corresponding to the lidar.

[0247] As a possible implementation, since when the third point cloud quantity condition and the third point cloud row quantity condition are within a numerical range, it is possible to screen out multiple frames of third target point cloud data at the same critical position of the effective horizontal field of view angle corresponding to the lidar; therefore, an angle threshold can be set, and when the number of third target point cloud data is greater than 2 frames, determine whether the absolute value of the difference between the cumulative rotation angles corresponding to any two frames of third target point cloud data is less than or equal to the angle threshold; if the absolute value of the difference between the cumulative rotation angles corresponding to any two frames of third target point cloud data is less than or equal to the angle threshold, it can be determined that these two frames of third target point cloud data are point cloud data collected at the same critical position of the effective horizontal field of view angle corresponding to the lidar; if the absolute value of the difference between the cumulative rotation angles corresponding to any two frames of third target point cloud data is greater than the angle threshold, it can be determined that these two frames of third target point cloud data are point cloud data collected at different critical positions of the effective horizontal field of view angle corresponding to the lidar; thus, each third target point cloud data can be divided into two groups, and each group of third target point cloud data corresponds to a critical position of the effective horizontal field of view angle of the lidar.

[0248] After that, one frame of third target point cloud data can be selected from each group of third target point cloud data to represent the two critical positions of the effective horizontal field of view angle respectively, and the absolute value of the difference between the cumulative rotation angles corresponding to these two frames of third target point cloud data can be determined as the effective horizontal field of view angle corresponding to the lidar.

[0249] As an example, when the number of frames of the third target point cloud data is greater than 2 and the third target point cloud data is divided into two groups in the above manner, one frame of the third target point cloud data can be randomly selected from the two groups of the third target point cloud data to represent the critical position of the effective horizontal field of view.

[0250] As an example, it is also possible to screen the point cloud data that can represent the critical position of the effective horizontal field of view from the two groups of the third target point cloud data respectively according to the number of target point cloud points and the number of rows of target point cloud points included in each frame of the third target point cloud data. It can be understood that if the number or the number of rows of the target point cloud points included in a frame of point cloud data is smaller, it can indicate that the frame of point cloud data is closer to the critical position of the effective horizontal field of view; therefore, for a group of the third target point cloud data, the third target point cloud data with the smallest number of target point cloud points or the smallest number of rows of target point cloud points included in this group of the third target point cloud data can be selected to represent a critical position of the effective horizontal field of view.

[0251] For example, assume that a group of the third target point cloud data includes 2 frames of the third target point cloud data. The number of target point cloud points corresponding to the third target point cloud data A is 5, and the number of rows of target point cloud points is 2 rows. The number of target point cloud points corresponding to the third target point cloud data B is 10, and the number of rows of target point cloud points is 3 rows. Then, the third target point cloud data A can be selected to represent a critical position of the effective horizontal field of view.

[0252] It should be noted that when testing the effective horizontal field of view corresponding to the lidar, the rotation device can also be controlled to rotate multiple weeks to perform multiple tests in the above manner, so as to determine multiple effective horizontal fields of view, and then determine the effective horizontal field of view corresponding to the lidar according to the effective horizontal fields of view measured multiple times. For example, the average value of the effective horizontal fields of view measured multiple times can be determined as the effective horizontal field of view corresponding to the lidar.

[0253] The method for testing the lidar provided by the embodiment of the present application builds an experimental environment that simulates the real use environment of the roadside lidar, and determines the point cloud points corresponding to the traffic participants included in each frame of point cloud data according to the point cloud data of the traffic participants collected by the lidar. Then, according to the pre-configured third point cloud condition, the point cloud data corresponding to the traffic participants at the edge of the field of view range of the lidar is screened out, so as to calculate the effective horizontal field of view corresponding to the lidar according to the screened point cloud data, thereby realizing an effective evaluation of the effective horizontal field of view corresponding to the lidar, and timely discovering possible problems with the field of view range of the lidar in actual use according to the test results for targeted improvement, thereby further improving the reliability and stability of the lidar in actual applications.

[0254] It should be understood that the sequence numbers of the steps in the above embodiments do not imply the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0255] Corresponding to the method for testing a lidar described in the above embodiments, Figure 12 FIG. shows a schematic structural diagram of a testing apparatus for a lidar provided by an embodiment of the present application. For the sake of convenience of description, only the part related to the embodiment of the present application is shown.

[0256] Referring to Figure 12 , the apparatus 1200 includes:

[0257] A first acquisition module 1201, configured to acquire the current test conditions corresponding to the lidar;

[0258] A second acquisition module 1202, configured to acquire multiple frames of point cloud data corresponding to traffic participants collected by the lidar in a test environment;

[0259] A first determination module 1203, configured to perform identification processing on each frame of point cloud data to determine the traffic participant identification result corresponding to each frame of point cloud data;

[0260] A second determination module 1204, configured to determine the performance parameters corresponding to the lidar according to the traffic participant identification result corresponding to each frame of point cloud data and the current test conditions.

[0261] The testing apparatus for a lidar provided by an embodiment of the present application builds an experimental environment that simulates the actual use environment of a roadside lidar, determines the traffic participant identification result corresponding to each frame of point cloud data according to the point cloud data of traffic participants collected by the lidar, and then evaluates the traffic participant identification result according to the pre-configured test conditions, so as to effectively evaluate the performance parameters corresponding to the lidar, and timely discover possible problems in the actual use of the lidar according to the test results for improvement, thereby ensuring the reliability and stability of the lidar during use.

[0262] In a possible implementation form of the present application, the above performance parameters include at least one of detection accuracy, effective vertical field of view, and maximum detection distance.

[0263] Further, in another possible implementation form of the present application, the above performance parameter includes detection accuracy, and the above current test conditions include the actual parameters of traffic participants; correspondingly, the above first determination module 1203 includes:

[0264] A first determination unit, configured to perform identification processing on each frame of point cloud data to determine the traffic participant detection parameters corresponding to each frame of point cloud data;

[0265] Correspondingly, the above-mentioned second determination module 1204 includes:

[0266] A second determination unit, configured to determine the detection accuracy corresponding to the lidar according to the traffic participant detection parameters and the actual parameters of the traffic participants corresponding to each frame of point cloud data.

[0267] Further, in another possible implementation form of the present application, the above-mentioned second determination unit is specifically configured to:

[0268] Determine the difference between the traffic participant detection parameters and the actual parameters of the traffic participants corresponding to each frame of point cloud data;

[0269] Determine the detection accuracy according to the difference between the traffic participant detection parameters and the actual parameters of the traffic participants corresponding to each frame of point cloud data.

[0270] Further, in another possible implementation form of the present application, the above-mentioned performance parameter includes an effective vertical field of view angle, and the above-mentioned current test condition includes a first point cloud condition and the installation height corresponding to the lidar; correspondingly, the above-mentioned first determination module 1203 includes:

[0271] A third determination unit, configured to perform identification processing on each frame of point cloud data to determine the target point cloud points corresponding to each frame of point cloud data, where the target point cloud points refer to the point cloud points corresponding to traffic participants;

[0272] Correspondingly, the above-mentioned second determination module 1204 includes:

[0273] A fourth determination unit, configured to determine the point cloud data for which the target point cloud points satisfy the first point cloud condition as the first target point cloud data;

[0274] A fifth determination unit, configured to perform identification processing on each frame of the first target point cloud data to determine the horizontal distance between the traffic participant corresponding to each frame of the first target point cloud data and the lidar;

[0275] A sixth determination unit, configured to determine the effective vertical field of view angle corresponding to the lidar according to the installation height and the horizontal distance between the traffic participant corresponding to each frame of the first target point cloud data and the lidar.

[0276] Further, in another possible implementation form of the present application, the above-mentioned first point cloud condition includes a first point cloud quantity condition, a first point cloud row number condition, and a first distance condition; correspondingly, the above-mentioned fourth determination unit is specifically configured to:

[0277] Perform identification processing on the target point cloud points corresponding to each frame of point cloud data to determine the number of target point cloud points, the number of rows of target point cloud points, and the horizontal distance between the traffic participant and the lidar corresponding to each frame of point cloud data;

[0278] The point cloud data where the number of target point cloud points meets the first point cloud number condition, the number of rows of target point cloud points meets the first point cloud row number condition, and the horizontal distance between the traffic participant and the lidar meets the first distance condition is determined as the first target point cloud data.

[0279] Further, in another possible implementation form of the present application, the above performance parameter includes the maximum detection distance, and the above current test condition includes the second point cloud condition; correspondingly, the above first determination module 1203 includes:

[0280] The seventh determination unit is used to perform identification processing on each frame of point cloud data to determine the target point cloud points corresponding to each frame of point cloud data, where the target point cloud points refer to the point cloud points corresponding to the traffic participant;

[0281] Correspondingly, the above second determination module 1204 includes:

[0282] The eighth determination unit is used to determine the point cloud data where the target point cloud points meet the second point cloud condition as the second target point cloud data;

[0283] The ninth determination unit is used to perform identification processing on each frame of the second target point cloud data to determine the horizontal distance between the traffic participant corresponding to each frame of the second target point cloud data and the lidar;

[0284] The tenth determination unit is used to determine the maximum detection distance corresponding to the lidar according to the horizontal distance between the traffic participant corresponding to each frame of the second target point cloud data and the lidar.

[0285] Further, in yet another possible implementation form of the present application, the above second point cloud condition includes a second point cloud number condition, a second point cloud row number condition, a second distance condition, and a second moving direction; correspondingly, the above eighth determination unit is specifically used for:

[0286] Perform identification processing on the target point cloud points corresponding to each frame of point cloud data to determine the number of target point cloud points, the number of rows of target point cloud points, the horizontal distance between the traffic participant and the lidar, and the moving direction of the traffic participant corresponding to each frame of point cloud data;

[0287] The point cloud data where the number of target point cloud points meets the second point cloud number condition, the number of rows of target point cloud points meets the second point cloud row number condition, the horizontal distance between the traffic participant and the lidar meets the second distance condition, and the moving direction of the traffic participant meets the second moving direction is determined as the second target point cloud data.

[0288] Further, in another possible implementation form of the present application, the above performance parameter includes an effective horizontal field of view angle. The above lidar is installed on a rotating device, and when the rotating device rotates, it drives the lidar to rotate. Each frame of point cloud data is collected when the rotating device rotates. The above traffic participant is within the effective vertical field of view angle corresponding to the lidar and is stationary. The above current test condition includes a third point cloud condition. Correspondingly, the above first determination module 1203 includes:

[0289] An eleventh determination unit, configured to perform identification processing on each frame of point cloud data to determine the target point cloud points corresponding to each frame of point cloud data and the cumulative rotation angle of the rotating device, where the target point cloud points refer to the point cloud points corresponding to traffic participants;

[0290] Correspondingly, the above second determination module 1204 includes:

[0291] A twelfth determination unit, configured to determine the point cloud data whose target point cloud points meet the third point cloud condition as the third target point cloud data;

[0292] A thirteenth determination unit, configured to determine the effective horizontal field of view angle corresponding to the lidar according to the cumulative rotation angle corresponding to the third target point cloud data.

[0293] Further, in another possible implementation form of the present application, the above third point cloud condition includes a third point cloud quantity condition and a third point cloud row number condition. Correspondingly, the above twelfth determination unit is specifically configured to:

[0294] Perform identification processing on the target point cloud points corresponding to each frame of point cloud data to determine the number of target point cloud points and the number of rows of target point cloud points corresponding to each frame of point cloud data;

[0295] Determine the point cloud data whose target point cloud point quantity meets the third point cloud quantity condition and whose target point cloud point row number meets the third point cloud row number condition as the third target point cloud data.

[0296] It should be noted that the information interaction, execution process, etc. between the above devices / units, due to being based on the same concept as the method embodiment of the present application, for their specific functions and the technical effects brought, please refer to the method embodiment part for details, and will not be elaborated here.

[0297] Those skilled in the art can clearly understand that, for the convenience and conciseness of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment and will not be elaborated herein.

[0298] To implement the above embodiment, the present application also proposes a terminal device.

[0299] Figure 13 It is a schematic structural diagram of a terminal device according to an embodiment of the present application.

[0300] As Figure 13 shown, the above terminal device 1300 includes:

[0301] A memory 1310 and at least one processor 1320, a bus 1330 connecting different components (including the memory 1310 and the processor 1320), and the memory 1310 stores a computer program. When the processor 1320 executes the program, it implements the test method of the lidar according to the embodiment of the present application.

[0302] The bus 1330 represents one or more of several types of bus structures, including a memory bus or a memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any bus structure in a variety of bus structures. For example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0303] The terminal device 1300 typically includes a variety of electronic device-readable media. These media can be any available media that can be accessed by the terminal device 1300, including volatile and non-volatile media, removable and non-removable media.

[0304] The memory 1310 may also include a computer system readable medium in the form of volatile memory, such as random access memory (RAM) 1340 and / or cache memory 1350. The terminal device 1300 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 1360 may be used for reading and writing on non-removable, non-volatile magnetic media ( Figure 13 not shown, typically referred to as a "hard disk drive"). Although Figure 13 not shown in the figure, a disk drive for reading and writing on a removable non-volatile disk (such as a "floppy disk") and an optical disk drive for reading and writing on a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM or other optical media) may be provided. In these cases, each drive may be connected to the bus 1330 through one or more data media interfaces. The memory 1310 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present application.

[0305] A program / utilities 1380 having a set (at least one) of program modules 1370 may be stored, for example, in the memory 1310. Such program modules 1370 include—but are not limited to—an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment. The program modules 1370 generally perform the functions and / or methods in the embodiments described in the present application.

[0306] The terminal device 1300 may also communicate with one or more external devices 1390 (such as a keyboard, a pointing device, a display 1391, etc.), and may also communicate with one or more devices that enable a user to interact with the terminal device 1300, and / or communicate with any device that enables the terminal device 1300 to communicate with one or more other computing devices (such as a network card, a modem, etc.). Such communication may be carried out through the input / output (I / O) interface 1392. Moreover, the terminal device 1300 may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 1393. As shown in the figure, the network adapter 1393 communicates with other modules of the terminal device 1300 through the bus 1330. It should be understood that although not shown in the figure, other hardware and / or software modules may be used in conjunction with the terminal device 1300, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0307] The processor 1320 executes various functional applications and data processing by running programs stored in the memory 1310.

[0308] It should be noted that for the implementation process and technical principle of the terminal device in this embodiment, refer to the foregoing explanation of the test method of the lidar in the embodiments of the present application, which will not be elaborated here.

[0309] The embodiments of the present application also provide a computer-readable storage medium storing a computer program, which when executed by a processor can implement the steps in the above-mentioned method embodiments.

[0310] The embodiments of the present application provide a computer program product, which when running on a terminal device enables the terminal device to implement the steps in the above-mentioned method embodiments.

[0311] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-mentioned method embodiments of the present application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, which can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device capable of carrying the computer program code to the device / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0312] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0313] Those of ordinary skill in the art will realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0314] In the embodiments provided in this application, it should be understood that the disclosed devices / terminal devices and methods can be implemented in other ways. For example, the device / terminal device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the devices or units can be in an electrical, mechanical or other form.

[0315] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0316] The above-described embodiments are only used to illustrate the technical solutions of this application, rather than to limit it; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of each embodiment of this application, and should all be included in the protection scope of this application.

Claims

1. A testing method for a lidar, characterized in that, Including: Obtaining the current test conditions corresponding to the lidar; Obtaining multiple frames of point cloud data corresponding to traffic participants collected by the lidar in a test environment; Performing recognition processing on each frame of the point cloud data to determine the traffic participant recognition result corresponding to each frame of the point cloud data; Determining the performance parameters corresponding to the lidar according to the traffic participant recognition result corresponding to each frame of the point cloud data and the current test conditions.

2. The method according to claim 1, characterized in that The performance parameters include at least one of detection accuracy, effective vertical field of view angle, maximum detection distance, and effective horizontal field of view angle.

3. The method according to claim 2, wherein The performance parameters include the detection accuracy, the current test conditions include the actual parameters of the traffic participants, and the performing recognition processing on each frame of the point cloud data to determine the traffic participant recognition result corresponding to each frame of the point cloud data includes: Performing recognition processing on each frame of the point cloud data to determine the traffic participant detection parameters corresponding to each frame of the point cloud data; The determining the performance parameters corresponding to the lidar according to the traffic participant recognition result corresponding to each frame of the point cloud data and the current test conditions includes: Determining the detection accuracy corresponding to the lidar according to the traffic participant detection parameters corresponding to each frame of the point cloud data and the actual parameters of the traffic participants.

4. The method according to claim 3, wherein The determining the detection accuracy corresponding to the lidar according to the traffic participant detection parameters corresponding to each frame of the point cloud data and the actual parameters of the traffic participants includes: Determining the difference between the traffic participant detection parameters corresponding to each frame of the point cloud data and the actual parameters of the traffic participants; Determining the detection accuracy according to the difference between the traffic participant detection parameters corresponding to each frame of the point cloud data and the actual parameters of the traffic participants.

5. The method according to claim 2, characterized in that The performance parameters include the effective vertical field of view angle, the current test conditions include the first point cloud condition and the installation height corresponding to the lidar, and the performing recognition processing on each frame of the point cloud data to determine the traffic participant recognition result corresponding to each frame of the point cloud data includes: Performing recognition processing on each frame of the point cloud data to determine the target point cloud points corresponding to each frame of the point cloud data, where the target point cloud points refer to the point cloud points corresponding to the traffic participants; The determining the performance parameters corresponding to the lidar according to the traffic participant recognition result corresponding to each frame of the point cloud data and the current test conditions includes: Determining the point cloud data whose target point cloud points meet the first point cloud condition as the first target point cloud data; Performing recognition processing on each frame of the first target point cloud data to determine the horizontal distance between the traffic participant corresponding to each frame of the first target point cloud data and the lidar; Determining the effective vertical field of view angle corresponding to the lidar according to the installation height and the horizontal distance between the traffic participant corresponding to each frame of the first target point cloud data and the lidar.

6. The method according to claim 5, wherein The first point cloud condition includes the first point cloud quantity condition, the first point cloud row number condition, and the first distance condition, and the determining the point cloud data whose target point cloud points meet the first point cloud condition as the first target point cloud data includes: Identify and process the target point cloud points corresponding to each frame of the point cloud data to determine the number of target point cloud points, the number of rows of target point cloud points, and the horizontal distance between the traffic participant and the lidar corresponding to each frame of the point cloud data; Determine the point cloud data whose number of target point cloud points meets the first point cloud number condition, the number of rows of target point cloud points meets the first point cloud row number condition, and the horizontal distance between the traffic participant and the lidar meets the first distance condition as the first target point cloud data.

7. The method according to claim 2, wherein The performance parameter includes the maximum detection distance, the current test condition includes the second point cloud condition, and the identifying and processing each frame of the point cloud data to determine the traffic participant identification result corresponding to each frame of the point cloud data includes: Identify and process each frame of the point cloud data to determine the target point cloud points corresponding to each frame of the point cloud data, where the target point cloud points refer to the point cloud points corresponding to the traffic participant; Determining the performance parameter corresponding to the lidar according to the traffic participant identification result corresponding to each frame of the point cloud data and the current test condition includes: Determine the point cloud data whose target point cloud points meet the second point cloud condition as the second target point cloud data; Identify and process each frame of the second target point cloud data to determine the horizontal distance between the traffic participant and the lidar corresponding to each frame of the second target point cloud data; Determine the maximum detection distance corresponding to the lidar according to the horizontal distance between the traffic participant and the lidar corresponding to each frame of the second target point cloud data.

8. The method according to claim 7, wherein The second point cloud condition includes a second point cloud number condition, a second point cloud row number condition, a second distance condition, and a second moving direction. Determining the point cloud data whose target point cloud points meet the second point cloud condition as the second target point cloud data includes: Identify and process the target point cloud points corresponding to each frame of the point cloud data to determine the number of target point cloud points, the number of rows of target point cloud points, the horizontal distance between the traffic participant and the lidar, and the traffic participant moving direction corresponding to each frame of the point cloud data; Determine the point cloud data whose number of target point cloud points meets the second point cloud number condition, the number of rows of target point cloud points meets the second point cloud row number condition, the horizontal distance between the traffic participant and the lidar meets the second distance condition, and the traffic participant moving direction meets the second moving direction as the second target point cloud data.

9. The method according to any one of claims 2-8, characterized in that, The performance parameter includes the effective horizontal field of view angle. The lidar is installed on a rotating device. When the rotating device rotates, it drives the lidar to rotate. Each frame of the point cloud data is collected when the rotating device rotates. The traffic participant is within the effective vertical field of view angle corresponding to the lidar and is stationary. The current test condition includes the third point cloud condition. The identifying and processing each frame of the point cloud data to determine the traffic participant identification result corresponding to each frame of the point cloud data includes: Identify and process each frame of the point cloud data to determine the target point cloud points corresponding to each frame of the point cloud data and the cumulative rotation angle of the rotating device, where the target point cloud points refer to the point cloud points corresponding to the traffic participants; Determine the performance parameters corresponding to the lidar according to the traffic participant recognition results corresponding to each frame of the point cloud data and the current test conditions, including: Determine the point cloud data in which the target point cloud points meet the third point cloud condition as the third target point cloud data; Determine the effective horizontal field of view angle corresponding to the lidar according to the cumulative rotation angle corresponding to the third target point cloud data.

10. The method according to claim 9, characterized in that, The third point cloud condition includes a third point cloud quantity condition and a third point cloud row number condition. Determining the point cloud data in which the target point cloud points meet the third point cloud condition as the third target point cloud data includes: Identify and process the target point cloud points corresponding to each frame of the point cloud data to determine the number of target point cloud points and the number of rows of target point cloud points corresponding to each frame of the point cloud data; Determine the point cloud data in which the number of target point cloud points meets the third point cloud quantity condition and the number of rows of target point cloud points meets the third point cloud row number condition as the third target point cloud data.

11. A test device for a lidar, characterized in that, Including: A first acquisition module for acquiring the current test conditions corresponding to the lidar; A second acquisition module for acquiring multiple frames of point cloud data corresponding to traffic participants collected by the lidar in a test environment; A first determination module for identifying and processing each frame of the point cloud data to determine the traffic participant recognition result corresponding to each frame of the point cloud data; A second determination module for determining the performance parameters corresponding to the lidar according to the traffic participant recognition results corresponding to each frame of the point cloud data and the current test conditions.

12. A terminal 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 computer program, the method described in any one of claims 1-10 is implemented.

13. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the method described in any one of claims 1-10 is implemented.

Images