Reighting fusion test method and device, storage medium and electronic equipment

Abstract

The embodiment of the invention provides a testing method and device for Leiyu fusion, a storage medium and electronic equipment, and the method comprises the steps: building an external field environment through scene simulation software; acquiring a plurality of groups of mounting pose parameters corresponding to the sensing equipment, and adjusting the mounting pose of the sensing equipment and the mounting pose of the sensing model according to the current mounting pose parameters; detecting the target object through the sensing model to obtain first scene data, transmitting the first scene data to the sensing device, and obtaining first test data obtained by testing the first scene data through the sensing device; according to the first test data, determining a sensing performance parameter of the sensing device under the current installation pose parameter; and determining the installation pose parameter corresponding to the optimal sensing performance parameter in the plurality of groups of installation pose parameters as the optimal installation pose parameter of the sensing equipment, thereby solving the problem of low installation position test efficiency in an external field parameter adjustment method.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of fusion testing technology, and specifically, to a test method, device, storage medium and electronic device for radar-vision fusion. Background Art

[0002] Radar-vision fusion, that is, the fusion of millimeter-wave radar and camera, as the core perception part of the intelligent transportation system, greatly improves the perception ability by fusing radar and video perception data. In order to accurately capture the dynamics of the target, eliminate blind spots and reduce misjudgments, it is usually necessary to perform field fine-tuning and calibration of the collaborative operation of the millimeter-wave radar and camera. Among them, field parameter adjustment includes manual adjustment of the installation position and angle, and determining the optimal installation position of the millimeter-wave radar and camera through repeated trials and optimization. This field parameter adjustment method is not only time-consuming and labor-intensive, but also requires repeated trials to determine the optimal installation position of the millimeter-wave radar and camera, which is inefficient. Summary of the invention

[0003] The embodiments of the present application provide a test method, device, storage medium and electronic device for radar and vision fusion, so as to at least solve the problem of low efficiency of installation position testing existing in the field parameter adjustment method.

[0004] According to one aspect of an embodiment of the present application, a test method for radar-visual fusion is provided, comprising: establishing an outdoor environment through scene simulation software; the outdoor environment is established according to the actual installation environment in which a perception device is located; the outdoor environment includes a target object and a sensor model corresponding to the perception device; obtaining multiple sets of installation posture parameters corresponding to the perception device, and using each set of installation posture parameters in the multiple sets of installation posture parameters as current installation posture parameters to perform the following test operations to obtain perception performance parameters of the perception device under each set of installation posture parameters: adjusting the installation posture of the perception device and the installation posture of the sensor model according to the current installation posture parameters; detecting the target object through the sensor model to obtain first scene data, transmitting the first scene data to the perception device, and obtaining first test data obtained by testing the first scene data by the perception device; determining the perception performance parameters of the perception device under the current installation posture parameters according to the first test data; determining the installation posture parameters corresponding to the optimal perception performance parameters in the multiple sets of installation posture parameters as the optimal installation posture parameters of the perception device.

[0005] According to another aspect of the embodiment of the present application, a test device for radar-visual fusion is provided, including: a simulation environment establishment module, used to establish an outdoor environment through scene simulation software; the outdoor environment is established according to the actual installation environment where the perception device is located; the outdoor environment contains a target object and a sensor model corresponding to the perception device; an installation posture test module, used to obtain multiple groups of installation posture parameters corresponding to the perception device, and use each group of installation posture parameters in the multiple groups of installation posture parameters as the current installation posture parameters to perform the following test operations to obtain the perception performance parameters of the perception device under each group of installation posture parameters: according to the The current installation posture parameters are used to adjust the installation posture of the perception device and the installation posture of the sensor model; the target object is detected by the sensor model to obtain first scene data, the first scene data is transmitted to the perception device, and first test data obtained by testing the first scene data by the perception device is obtained; according to the first test data, the perception performance parameters of the perception device under the current installation posture parameters are determined; an installation posture determination module is used to determine the installation posture parameters corresponding to the optimal perception performance parameters among the multiple groups of installation posture parameters as the optimal installation posture parameters of the perception device.

[0006] According to another aspect of the embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned radar-visual fusion test method when running.

[0007] According to another aspect of an embodiment of the present application, there is also provided an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the radar-vision fusion testing method through the computer program.

[0008] According to another aspect of the embodiments of the present application, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps in any of the above-mentioned radar-visual fusion test method embodiments.

[0009] Through the embodiments of the present application, an outdoor environment is established through scene simulation software, and a sensor model corresponding to the perception device is configured in the outdoor environment. It is possible to quickly test multiple sets of installation posture parameters without actually deploying hardware, significantly reducing the number of experiments and shortening the test cycle, thereby significantly improving the test efficiency; further, according to the current installation posture parameters, the installation posture of the perception device and the installation posture of the sensor model are adjusted; the target object is detected through the sensor model to obtain first scene data, the first scene data is transmitted to the perception device, and the first test data obtained by the perception device testing the first scene data is obtained, wherein the first scene data of the real perception device is introduced into the test process. A test data can make the test result more realistic and accurate, and according to the first test data, determine the perception performance parameters of the perception device under the current installation posture parameters, and determine the installation posture parameters corresponding to the optimal perception performance parameters in multiple groups of installation posture parameters as the optimal installation posture parameters of the perception device. The above-mentioned determination of the optimal installation posture parameters of the perception device by hardware-in-the-loop simulation testing can quickly iterate multiple groups of installation posture parameters of the perception device, and evaluate the perception performance parameters of the perception device under each group of installation posture parameters in real time, and quickly find the optimal installation posture parameters, thereby improving the test efficiency and solving the problem of low efficiency of installation position testing in the field parameter adjustment method. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a hardware structure block diagram of an optional radar-visual fusion testing method of an embodiment of the present application;

[0011] Figure 2 is a flow chart of an optional test method for radar-visual fusion according to an embodiment of the present application;

[0012] Figure 3 is an optional optimization flow chart of the installation position of the sensing device according to an embodiment of the present application;

[0013] Figure 4 is a flow chart of an optional perception performance evaluation of a perception device according to an embodiment of the present application;

[0014] Figure 5 is a test architecture diagram of an optional radar-visual fusion according to an embodiment of the present application;

[0015] Figure 6 is a calibration flow chart of an optional sensing device according to an embodiment of the present application;

[0016] Figure 7 is a structural block diagram of an optional radar-visual fusion testing device according to an embodiment of the present application;

[0017] Figure 8It is a structural block diagram of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0019] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0020] According to one aspect of an embodiment of the present application, a method for testing thunder and visual fusion is provided. Optionally, in this embodiment, the thunder and visual fusion testing method can be applied to Figure 1 In the hardware environment composed of the test device 102 and the sensing device 104 shown in FIG. Figure 1As shown, the perception device 104 is connected to the test device 102, and the test device 102 is deployed with scene simulation software, and the test device 102 establishes an outdoor environment through the scene simulation software; the outdoor environment is established according to the actual installation environment where the perception device 104 is located; the outdoor environment includes a target object and a sensor model corresponding to the perception device 104; the test device 102 obtains multiple sets of installation posture parameters corresponding to the perception device 104, and uses each set of installation posture parameters in the multiple sets of installation posture parameters as the current installation posture parameters to perform the following test operations, and obtains the perception device 104 under each set of installation posture parameters. Perception performance parameters: according to the current installation posture parameters, adjust the installation posture of the perception device 104 and the installation posture of the sensing model; detect the target object through the sensing model to obtain the first scene data, transmit the first scene data to the perception device, and obtain the first test data obtained by the perception device 104 testing the first scene data; according to the first test data, determine the perception performance parameters of the perception device 104 under the current installation posture parameters; the test device 102 determines the installation posture parameters corresponding to the optimal perception performance parameters in multiple sets of installation posture parameters as the optimal installation posture parameters of the perception device 104. Among them, the test device 102 may not be limited to PC, mobile phone, tablet computer and other devices. The perception device 104 may not be limited to radar, camera, camera and other devices.

[0021] The test method for the fusion of thunder and vision in the embodiment of the present application may be executed by the test device 102 . Figure 2 is a flow chart of an optional test method for radar-visual fusion according to an embodiment of the present application, such as Figure 2 As shown, the process of the method may include the following steps:

[0022] Step S202, establishing an external field environment through scene simulation software; the external field environment is established according to the actual installation environment where the sensing device is located; the external field environment includes a target object and a sensing model corresponding to the sensing device.

[0023] The sensing device refers to a device that can receive and process external environmental information to detect, track, identify or classify target objects. For example, the sensing device can be a radar, camera, infrared sensor, etc.

[0024] The field environment refers to a virtual environment established based on the actual installation environment of the sensing device.

[0025] Scenario simulation software is used to simulate the road environment, including environment models, target models, and sensor models. Among them, the environment model is used to simulate the real road environment, including the road itself, traffic signs, road markings, weather conditions (such as sunny days, rainy days, foggy days, etc.), lighting conditions (such as daytime, night, dusk, etc.), and buildings and vegetation around the road. The target model is used to simulate various traffic participants in the road environment, such as vehicles, pedestrians, bicycles, etc. The sensor model refers to a mathematical model that describes the relationship between the input and output of the sensing device. In scenario simulation, the sensor model is used to simulate how the sensing device receives and processes information in the external environment.

[0026] The target object refers to the virtual object set in the field environment established by the scene simulation software and needs to be recognized by the sensor model corresponding to the perception device. For example, the target object can be a moving target such as a vehicle, pedestrian, or animal, or a static target such as a building or a tree.

[0027] Optionally, the test device obtains detailed data of the actual installation environment in which the sensing device is located, and imports the detailed data into the scene simulation software. The scene simulation software configures various parameters of the field environment according to the imported detailed data to obtain a virtual field environment. The test device sets a target object in the field environment, and configures a sensing model corresponding to the sensing device according to the type and characteristics of the sensing device.

[0028] Step S204, obtain multiple groups of installation posture parameters corresponding to the perception device, and use each group of installation posture parameters in the multiple groups as the current installation posture parameters to perform the following test operations to obtain the perception performance parameters of the perception device under each group of installation posture parameters: adjust the installation posture of the perception device and the installation posture of the sensing model according to the current installation posture parameters; detect the target object through the sensing model to obtain first scene data, transmit the first scene data to the perception device, and obtain first test data obtained by the perception device testing the first scene data; determine the perception performance parameters of the perception device under the current installation posture parameters based on the first test data.

[0029] The installation posture parameters refer to the specific position and orientation parameters of the sensing device when it is installed or deployed. For example, the installation posture parameters include the three-dimensional coordinates of the sensing device in space (for example, the coordinate values ​​of the X, Y, and Z axes) and the angle of the sensing device (for example, the pitch angle, yaw angle, and roll angle, or simple horizontal and vertical angles).

[0030] Perception performance parameters are quantitative indicators that measure the ability of perception equipment to detect, identify or track target objects in a specified installation position. For example, perception performance parameters include detection accuracy, detection range, target tracking performance, target recognition rate and road coverage.

[0031] The first scene data refers to the result data obtained by detecting the target object through the sensing model after adjusting the installation posture of the sensing device and the sensing model according to the current installation posture parameters. The first scene data is passed to the sensing device as input data to test the processing capability and performance of the sensing device. During the test, different application scenarios and test environments can be simulated by adjusting the parameters and conditions of the first scene data. For example, the first scene data includes parameters such as the video image of the target object captured by the sensing model, the three-dimensional position coordinates of the target object in the simulation environment, and the movement speed and heading of the target object.

[0032] The first test data refers to a series of result data reflecting the performance of the perception device obtained after the perception device tests the first scene data. The first test data generally includes the actual response of the perception device to the first scene data, and is used to evaluate the performance and reliability of the perception device. For example, the first test data includes information such as the size, speed, distance, and acceleration of the identified target object.

[0033] Optionally, Figure 3 FIG. 1 is an optimization flow chart of the installation position of the sensing device in one embodiment, such as Figure 3 As shown, the test device obtains multiple sets of installation posture parameters corresponding to the perception device, and uses each set of installation posture parameters in the multiple sets of installation posture parameters as the current installation posture parameters to perform the following test operations to obtain the perception performance parameters of the perception device under each set of installation posture parameters: the test device adjusts the installation posture of the perception device in the real installation environment and the installation posture of the sensor model in the simulation scene according to the current installation posture parameters; detects the target object in the simulated field environment through the sensor model to obtain the first scene data, and transmits the first scene data to the perception device. After receiving the first scene data, the perception device processes and analyzes it to obtain the first test data, and feeds the first test data back to the test device. The test device determines the perception performance parameters of the perception device under the current installation posture parameters based on the difference between the first test data and the first scene data.

[0034] Step S206: Determine the installation posture parameters corresponding to the optimal perception performance parameters among the multiple groups of installation posture parameters as the optimal installation posture parameters of the perception device.

[0035] Alternatively, if Figure 3 As shown, the test device obtains and compares the perception performance parameters of the perception device under each set of installation posture parameters, determines an optimal set of installation posture parameters, and determines the optimal set of installation posture parameters as the optimal installation posture parameters of the perception device.

[0036] Through the above steps S202 to S206, an outdoor environment is established through scene simulation software, and a sensor model corresponding to the perception device is configured in the outdoor environment. It is possible to quickly test multiple sets of installation posture parameters without actually deploying hardware, significantly reducing the number of experiments and shortening the test cycle, thereby significantly improving the test efficiency; further, according to the current installation posture parameters, the installation posture of the perception device and the installation posture of the sensor model are adjusted; the target object is detected through the sensor model to obtain the first scene data, the first scene data is transmitted to the perception device, and the first test data obtained by the perception device testing the first scene data is obtained, wherein the real sensor is introduced into the test process. The first test data of the known device can make the test result more real and accurate, and according to the first test data, determine the perception performance parameters of the perception device under the current installation posture parameters, and determine the installation posture parameters corresponding to the optimal perception performance parameters in multiple groups of installation posture parameters as the optimal installation posture parameters of the perception device. The above-mentioned determination of the optimal installation posture parameters of the perception device by hardware-in-the-loop simulation testing can quickly iterate multiple groups of installation posture parameters of the perception device, and evaluate the perception performance parameters of the perception device under each group of installation posture parameters in real time, and quickly find the optimal installation posture parameters, thereby improving the test efficiency and solving the problem of low efficiency of installation position testing in the field parameter adjustment method.

[0037] In an exemplary embodiment, the perception device includes a radar and a camera; the first scene data includes target detection data and video data, the target detection data is output to the radar, and the video data is output to the camera.

[0038] Among them, the sensing models corresponding to the perception devices include radar models and camera models.

[0039] Target detection data refers to the data generated by the radar model identifying the target object in the field environment during the simulation test. Target detection data is used to simulate the state of the target in the real world. For example, target detection data includes the three-dimensional or two-dimensional position information of the target object in the simulation environment (field environment), the velocity vector of the target object, the heading of the target, RCS (radar cross-section) and other parameters. The target detection data is output to the radar in order to evaluate the detection capability, accuracy and stability of the radar in a given installation posture.

[0040] Video data refers to the real-time visual information captured by the camera model in the simulation environment, which is used to simulate the image information captured by the camera in the actual environment. For example, video data includes static image sequences or dynamic video streams. Video data is output to the camera to test the performance indicators such as image capture quality, field of view, color reproduction, image clarity, etc. of the camera in a given installation position.

[0041] In some embodiments, obtaining first test data obtained by a perception device testing first scene data includes:

[0042] Acquire first perception data obtained by the radar sensing the target detection data; acquire second perception data obtained by the camera sensing the video data; wherein the first test data includes the first perception data and the second perception data.

[0043] The first perception data refers to the output result after the radar perceives and processes the target detection data. The first perception data reflects the radar's perception result of the target state, for example, including accurate information such as the target's distance, speed, and direction.

[0044] The second perception data refers to the output result after the camera perceives and processes the video data. For example, the second perception data includes information such as the image features, position, size, and motion trajectory of the target.

[0045] The first test data is a comprehensive data set, including the first perception data and the second perception data obtained by the radar and the camera after processing the target detection data and video data respectively. The first perception data and the second perception data together constitute a comprehensive evaluation of the performance of the perception device, which helps to determine the optimal installation posture parameters of the perception device and improve the perception ability and accuracy of the entire system.

[0046] Optionally, the testing device outputs the target detection data output by the radar model in the simulation environment to the radar, outputs the video data output by the camera model in the simulation environment to the camera, receives first perception data obtained by the radar perceiving the target detection data, and receives second perception data obtained by the camera perceiving the video data, and determines the first perception data and the second perception data as first test data obtained by the perception device testing the first scene data.

[0047] Through this embodiment, two different types of perception devices, radar and camera, are integrated, and target detection data and video data are generated through simulation software. The data are output to the radar and camera for perception processing, respectively. The two perception devices, radar and camera, can be tested and verified without relying on actual hardware, which not only saves time and cost, but also allows repeated tests in different scenarios and conditions to evaluate the performance and stability of the two perception devices, radar and camera.

[0048] In an exemplary embodiment, determining the perception performance parameters of the perception device under the current installation posture parameters according to the first test data includes:

[0049] The first perception data and the second perception data are fused to obtain target fusion data; and the perception performance parameters of the perception device under the current installation posture parameters are determined according to the difference between the target fusion data and the first scene data.

[0050] Among them, target fusion data refers to a more comprehensive and accurate description of the target state obtained by fusing the first perception data from the radar and the second perception data from the camera. Both the target fusion data and the first scene data are descriptions of the target state, and there is a certain degree of correlation between them. By comparing the difference between these two types of data, the perception performance parameters of the perception device under the current installation posture parameters can be evaluated.

[0051] It should be noted that: the first scene data is directly generated by the simulation software and is used to simulate the target state in the real world, including the position, speed, heading and other parameters of the target, while the target fusion data is obtained by the actual perception device (radar and camera) perceiving and fusing the scene data. Secondly, the first scene data is idealized and noise-free, and it represents the real state of the target in the simulation environment, while the target fusion data may be affected by multiple factors such as the performance of the perception device, environmental noise, and data fusion algorithm, so there may be certain errors and uncertainties. Finally, the first scene data is mainly used to provide a test benchmark and reference for the perception device to evaluate the performance of the perception device, while the target fusion data is used to provide actual target state information.

[0052] Optionally, Figure 4 FIG. 1 is a flow chart of the perception performance evaluation of a perception device in an embodiment. Figure 4 As shown, the test equipment outputs the target detection data output by the radar model in the simulation environment to the radar, and outputs the video data output by the camera model in the simulation environment to the camera. The radar senses the target detection data to obtain the first sense data, and the camera senses the video data to obtain the second sense data. The first sense data and the second sense data are sensed by the fusion controller to obtain the target fusion data, and the target fusion data is fed back to the test equipment. The test equipment receives the target fusion data, and determines the perception performance parameters of the perception equipment under the current installation posture parameters based on the difference between the target fusion data and the first scene data.

[0053] For example, the test equipment transmits the video data output by the camera model in the simulation environment to the camera through a high-definition display, and sends the target position coordinates, speed, heading, and RCS output by the radar model in the simulation environment to the traffic radar through a millimeter wave instrument. The fusion controller receives the first perception data of the traffic radar and the second perception data of the camera and fuses them, and outputs the target fusion data (such as the size of the target (length, width, height, radar cross-sectional area RCS), speed, distance, acceleration and other parameters) to the test equipment. The test equipment compares the first simulation output information output by the simulation software with the target fusion data output by the fusion controller. The comparison parameters include target speed, distance, and track. The smaller the difference between the target fusion data output by the fusion controller and the first simulation output information output by the simulation software, the better the performance of the perception device under test, thereby detecting the function of the fusion perception system.

[0054] Through this embodiment, by fusing the data of perception devices such as radar and camera, a more comprehensive and accurate description of the target state can be obtained. By fusing these data, they can complement each other to improve the accuracy of perception. By comparing the difference between the target fusion data and the first scene data, the perception performance of the perception device under the current installation posture parameters can be automatically evaluated, which can improve the test efficiency.

[0055] In an exemplary embodiment, the target fusion data and the first scene data are both used to indicate the speed of the target object, the distance between the target object and the perception device, and the track of the target object.

[0056] In some embodiments, determining the perception performance parameters of the perception device under the current installation position and posture parameters according to the difference between the target fusion data and the first scene data includes:

[0057] 1. Determine a first performance parameter of the perception device under the current installation posture parameter according to a difference between a speed of the target object indicated by the target fusion data and a speed of the target object indicated by the first scene data.

[0058] The first performance parameter refers to a quantitative indicator of the accuracy or error degree of the target object speed measurement of the perception device under the current installation posture parameters. By comparing the difference between the target object speed indicated by the target fusion data and the target object speed indicated by the first scene data, the error size of the perception device in speed measurement can be determined, thereby evaluating the performance of the perception device.

[0059] Optionally, the test device obtains the target fusion data and the first scene data output by the simulation software, extracts the target object speed information of the same target object in the target fusion data and the first scene data at the same time point or time period, calculates the difference between the speed indicated by the target fusion data and the speed indicated by the first scene data by subtracting or finding the percentage error, quantifies the difference, and obtains the first performance parameter of the perception device under the current installation posture parameters.

[0060] 2. Determine a second performance parameter of the perception device under the current installation posture parameters based on a difference between a distance between the target object indicated by the target fusion data and the perception device and a distance between the target object indicated by the first scene data and the perception device.

[0061] The second performance parameter refers to a quantitative indicator of the accuracy or error degree of the distance measurement between the target object and the perception device under the current installation posture parameters. By comparing the difference between the distance between the target object and the perception device indicated by the target fusion data and the distance between the target object and the perception device indicated by the first scene data, the error size of the perception device in distance measurement can be determined, thereby evaluating the performance of the perception device.

[0062] Optionally, the test device obtains the target fusion data and the first scene data output by the simulation software, extracts the distance between the same target object in the target fusion data and the first scene data and the perception device at the same time point or time period, calculates the difference between the distance between the target object indicated by the target fusion data and the perception device and the distance between the target object indicated by the first scene data and the perception device by subtracting or calculating the percentage error, quantifies the difference, and obtains the second performance parameter of the perception device under the current installation posture parameters.

[0063] 3. Determine a third performance parameter of the perception device under the current installation posture parameter based on a difference between the track of the target object indicated by the target fusion data and the track of the target object indicated by the first scene data.

[0064] The third performance parameter refers to a quantitative indicator of the accuracy or error degree of the target object track measurement of the perception device under the current installation posture parameters. By comparing the difference between the target object track indicated by the target fusion data and the target object track indicated by the first scene data, the error size of the perception device in track measurement can be determined, thereby evaluating the performance of the perception device.

[0065] Optionally, the test equipment obtains the target fusion data and the first scene data output by the simulation software, extracts the target object track information of the same target object in the target fusion data and the first scene data at the same time point or time period, calculates the difference between the track indicated by the target fusion data and the track indicated by the first scene data by subtracting or finding the percentage error, quantifies the difference, and obtains the third performance parameter of the perception device under the current installation posture parameters.

[0066] 4. Determine the perception performance parameters of the perception device under the current installation posture parameters based on the first performance parameter, the second performance parameter and the third performance parameter.

[0067] Optionally, the test equipment adopts weighted average method, principal component analysis method, fuzzy comprehensive evaluation method and other methods to synthesize the data of the first performance parameter, the second performance parameter and the third performance parameter, and calculate the perception performance parameters of the perception device under the current installation posture parameters.

[0068] Through this embodiment, the determined first performance parameter, second performance parameter and third performance parameter cover key aspects such as speed measurement, distance measurement, target object recognition rate, etc., and the perception performance parameters of the perception device under the current installation posture parameters are determined based on the first performance parameter, the second performance parameter and the third performance parameter. The performance of the perception device can be comprehensively and in-depth evaluated, thereby ensuring the comprehensiveness and accuracy of the evaluation results.

[0069] In an exemplary embodiment, the perception performance parameters include target tracking performance, target recognition rate and road coverage; the target fusion data and the first scene data both include identification information of the detected target object and road area data.

[0070] Among them, target tracking performance refers to the ability of the perception device to accurately track and locate specific target objects in a continuous time series.

[0071] The target recognition rate refers to the proportion of target objects that are correctly identified and classified by the sensing device.

[0072] Road coverage refers to the ratio between the road area detected by the perception device and the road area actually existing in the simulation environment.

[0073] The identification information is used to uniquely identify and recognize the target object. For example, the identification information may be unique coding information.

[0074] Road area data refers to data used to describe roads and their related elements. For example, road area data includes information such as the number, shape, boundary, type (such as lanes, parking spaces, sidewalks) of road surface areas.

[0075] In some embodiments, determining the perception performance parameters of the perception device under the current installation posture parameters according to the difference between the target fusion data and the first scene data includes:

[0076] 1. Determine the target tracking performance and target recognition rate of the perception device under the current installation posture parameters based on the difference between the identification information of the target object in the target fusion data and the identification information of the target object in the first scene data.

[0077] Optionally, the test device obtains the target fusion data and the first scene data output by the simulation software, and compares the identification information of the target object in the target fusion data with the identification information of the target object in the first scene data one by one to find the corresponding relationship between the two. For each successfully matched target object, the test device calculates the difference in key attributes such as position and speed in the target fusion data and the scene data as the tracking error, and according to the size and distribution of the tracking error, the target tracking performance of the perception device under the current installation posture parameters, such as the average tracking error, the maximum tracking error, etc., is counted. The test device counts the number of target objects that appear in the target fusion data and are also successfully identified in the first scene data, and counts the number of target objects that appear in the target fusion data but are not identified or incorrectly identified in the first scene data. According to the successful identification count and the failed identification count, the target recognition rate of the perception device under the current installation posture parameters is calculated, that is, the ratio of the number of successful identifications to the total number of targets.

[0078] 2. Determine the road coverage of the perception device under the current installation posture parameters based on the difference between the road area data in the target fusion data and the road area data in the first scene data.

[0079] Optionally, the test device obtains the target fusion data and the first scene data output by the simulation software, converts the road area data in the target fusion data and the first scene data to the same coordinate system, and uses spatial analysis technology (such as regional overlay analysis) to compare the road area data in the target fusion data with the road area data in the first scene data, and identifies the road areas shared by the target fusion data and the first scene data, as well as the road areas that are unique to each. For each shared road area, the test device calculates the area or length of the shared road area, compares the road area area (or length) detected by the perception device with the road area area (or length) that actually exists in the simulation environment, and calculates the coverage ratio, that is, the percentage of the road area area (or length) detected by the perception device to the actual road area area (or length) in the simulation environment.

[0080] Through this embodiment, the perception performance parameters of the perception device in a specified installation position are determined from dimensions such as target tracking performance, target recognition rate and road coverage. This enables the perception capability evaluation of the radar-vision fusion perception device in a laboratory environment, thereby improving the research and development efficiency of the radar-vision fusion system in smart transportation.

[0081] In an exemplary embodiment, before performing the following test operation using each set of installation posture parameters in the multiple sets of installation posture parameters as the current installation posture parameters, the above-mentioned radar-visual fusion test method further includes:

[0082] Equipment placement indication information is received, wherein the equipment placement indication information is used to indicate that the radar has been placed in the millimeter wave test dark box, and the camera has been placed in the optical test dark box.

[0083] Among them, the millimeter wave test box provides millimeter wave radar target information, installation location and test environment to prevent external interference.

[0084] The camera test box provides the camera with video stream information data, installation location and test environment to prevent external interference.

[0085] Optionally, the radar is placed in a millimeter wave test dark box manually or mechanically, the camera is placed in an optical test dark box, and the equipment position indication information is fed back to the test equipment. After the test equipment receives the equipment position indication information, it starts to execute the step of performing the test operation using each set of installation posture parameters in multiple sets of installation posture parameters as the current installation posture parameters.

[0086] Figure 5 FIG. 1 is a test architecture diagram of the radar-visual fusion in an embodiment. Figure 5 As shown, the radar is placed in a millimeter wave test dark box, and the camera is placed in an optical test dark box. Scene simulation software and test software are deployed on the test equipment. Among them, the test equipment runs the scene simulation software to edit the scene; runs the test software, and sends the first simulation output parameter to the perception device, records the performance test data of the perception device under test, and performs data comparison and analysis. The scene simulation software is used to simulate the road environment. The test software provides a human-computer interaction interface software, through which the first scene data is sent to the radar and the camera, and the target fusion data returned by the fusion controller is received, and the first scene data output by the test equipment and the received target fusion data are monitored in real time, and data are recorded and analyzed.

[0087] like Figure 5As shown, the scene simulation software outputs the target detection data output by the radar model in the simulation environment to the radar, and outputs the video data output by the camera model in the simulation environment to the camera. The radar senses the target detection data to obtain the first sense data, and the camera senses the video data to obtain the second sense data. The fusion controller performs sense data fusion on the first sense data and the second sense data to obtain target fusion data, and feeds the target fusion data back to the test software. The test software compares the first scene data output by the scene simulation software with the target fusion data output by the fusion controller. The comparison parameters include target speed, distance, and track, and determines the perception performance parameters of the perception device under the current installation posture parameters based on the difference between the target fusion data and the first scene data.

[0088] In this embodiment, placing the radar in a millimeter wave test dark box and placing the camera in an optical test dark box can effectively prevent external interference, thereby improving the accuracy and reliability of the test.

[0089] In an exemplary embodiment, after determining the installation posture parameters corresponding to the optimal perception performance parameters in the multiple sets of installation posture parameters as the optimal installation posture parameters of the perception device, the method further includes:

[0090] 1. Set up a calibration target in the field environment at the specified direction of the sensor model.

[0091] The specified direction refers to a calibration direction set in a simulation environment to achieve the calibration of the sensing device. The specified direction can be determined based on the coordinate system of the simulation environment, for example, using the X-axis, Y-axis, and Z-axis in a three-dimensional coordinate system to define the direction. For example, the specified direction can be the direction at 0° of the sensing model. The purpose of the specified direction is to determine the positional relationship of the calibration target relative to the sensing model, ensuring that the sensing model can accurately sense and measure in this direction.

[0092] A calibration target refers to one or more specific objects or signals set up in a simulation environment to calibrate the sensor model. The purpose of a calibration target is to provide a known, stable reference point or reference signal to verify and correct the perception and measurement results of the sensor model. The calibration target can be a virtual vehicle, pedestrian, traffic sign, etc., or a specific signal source, such as a radio signal, laser signal, etc. These calibration targets have known properties such as position, shape, speed, etc., so they can be used as a benchmark for sensor model calibration.

[0093] Optionally, Figure 6 is a flow chart of the calibration of a sensing device in one embodiment, such as Figure 6As shown, the test equipment sets a calibration target located in a specified direction of the sensor model in an outdoor environment through a target model in the scene simulation software.

[0094] 2. According to the optimal installation posture parameters, adjust the installation posture of the perception device and the installation posture of the sensor model in the scene simulation software.

[0095] Alternatively, if Figure 6 As shown, the test equipment adjusts the installation posture of the perception device in the real installation environment and the installation posture of the sensor model in the simulation scenario according to the optimal installation posture parameters, so that the installation posture of the perception device and the installation posture of the sensor model are consistent with the optimal installation posture parameters.

[0096] 3. Detect the calibration target through the sensing model to obtain second scene data, transmit the second scene data to the perception device, and obtain second test data obtained by the perception device testing the second scene data.

[0097] The second scene data refers to the result data obtained by detecting the calibration target through the sensing model after adjusting the installation posture of the perception device and the sensing model according to the optimal installation posture parameters. The second scene data is passed to the perception device as input data to test the processing capability and performance of the perception device. During the test, different application scenarios and test environments can be simulated by adjusting the parameters and conditions of the second scene data. For example, the second scene data includes parameters such as the video image of the calibration target captured by the sensing model, the three-dimensional position coordinates of the calibration target in the simulation environment, and the movement speed and heading of the calibration target.

[0098] The second test data refers to a series of result data reflecting the performance of the perception device obtained after the perception device tests the second scene data. The second test data generally includes the actual response of the perception device to the second scene data, and is used to evaluate the performance and reliability of the perception device. For example, the second test data includes information such as the size, speed, distance, and acceleration of the calibration target obtained by identification.

[0099] Optionally, the test device detects the calibration target in the simulated field environment through the sensing model to obtain second scene data, and transmits the second scene data to the perception device. After receiving the second scene data, the perception device processes and analyzes it to obtain second test data, and feeds the second test data back to the test device.

[0100] 4. Generate calibration parameters of the sensing device at the optimal installation position based on the second test data, and calibrate the sensing device based on the calibration parameters to obtain a calibrated sensing device.

[0101] The calibration parameters refer to the specific parameter values ​​used in a series of calibration operations performed on the device after installation to ensure that the sensing device can accurately and reliably sense and measure objects or signals in the surrounding environment. For example, the calibration parameters include installation location parameters, sensing parameters, and other parameters.

[0102] Optionally, the test device establishes a calibration model, which is used to describe the relationship between the measurement results of the perception device and the real environment. The test device inputs the second test data and the second scene data into the calibration model, and the calibration model generates calibration parameters of the perception device at the optimal installation position according to the difference between the second test data and the second scene data. The test device applies the generated calibration parameters to the perception device and adjusts its configuration so that the perception device can use these parameters for correction during measurement, thereby obtaining a calibrated perception device.

[0103] Through this embodiment, a calibration target located in a specified direction of the sensor model is set in an external field environment, which can simulate the perception scene in the real world, thereby generating more accurate calibration parameters; further, according to the acquired second scene data and the second test data, the calibration parameters of the perception device in the optimal installation position are generated, and the perception device is calibrated based on the calibration parameters to obtain a calibrated perception device, which can realize automatic calibration of the perception device, and perform calibration and testing in a simulation environment, which can avoid complex and time-consuming testing work in the actual environment, not only saving time and cost, but also improving test efficiency.

[0104] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0105] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware server, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM (Read-Only Memory) / RAM (Random Access Memory), a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of each embodiment of the present application.

[0106] According to another aspect of the embodiments of the present application, a test device for radar-visual fusion is also provided, which is used to implement the test method for radar-visual fusion provided in the above embodiments, and will not be repeated hereafter. As used below, the term "module" may be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0107] Figure 7 is a structural block diagram of an optional radar-visual fusion testing device according to an embodiment of the present application, such as Figure 7 As shown, the device may include:

[0108] The simulation environment establishment module 701 is used to establish an external environment through scene simulation software; the external environment is established according to the actual installation environment where the sensing device is located; the external environment includes a target object and a sensing model corresponding to the sensing device;

[0109] The installation posture test module 702 is used to obtain multiple groups of installation posture parameters corresponding to the perception device, and use each group of installation posture parameters in the multiple groups of installation posture parameters as the current installation posture parameters to perform the following test operations to obtain the perception performance parameters of the perception device under each group of installation posture parameters: according to the current installation posture parameters, adjust the installation posture of the perception device and the installation posture of the sensing model; detect the target object through the sensing model to obtain first scene data, transmit the first scene data to the perception device, and obtain first test data obtained by the perception device testing the first scene data; determine the perception performance parameters of the perception device under the current installation posture parameters according to the first test data;

[0110] The installation posture determination module 703 is used to determine the installation posture parameters corresponding to the optimal perception performance parameters among the multiple groups of installation posture parameters as the optimal installation posture parameters of the perception device.

[0111] In an exemplary embodiment, the perception device includes a radar and a camera; the first scene data includes target detection data and video data, the target detection data is output to the radar, and the video data is output to the camera; a posture test module 702 is installed, and is also used to obtain first perception data obtained by the radar perceiving the target detection data; and obtain second perception data obtained by the camera perceiving the video data; wherein the first test data includes the first perception data and the second perception data.

[0112] In an exemplary embodiment, the installation posture test module 702 is also used to perform perception data fusion on the first perception data and the second perception data to obtain target fusion data; based on the difference between the target fusion data and the first scene data, the perception performance parameters of the perception device under the current installation posture parameters are determined.

[0113] In an exemplary embodiment, both the target fusion data and the first scene data are used to indicate the speed of the target object, the distance between the target object and the perception device, and the track of the target object; the installation posture test module 702 is further used to determine the first performance parameter of the perception device under the current installation posture parameters according to the difference between the speed of the target object indicated by the target fusion data and the speed of the target object indicated by the first scene data; determine the second performance parameter of the perception device under the current installation posture parameters according to the difference between the distance between the target object indicated by the target fusion data and the perception device and the distance between the target object indicated by the first scene data and the perception device; determine the third performance parameter of the perception device under the current installation posture parameters according to the difference between the track of the target object indicated by the target fusion data and the track of the target object indicated by the first scene data; determine the perception performance parameters of the perception device under the current installation posture parameters according to the first performance parameters, the second performance parameters, and the third performance parameters.

[0114] In an exemplary embodiment, the perception performance parameters include target tracking performance, target recognition rate and road coverage; the target fusion data and the first scene data both include identification information and road area data of the detected target object; the installation posture test module 702 is also used to determine the target tracking performance and target recognition rate of the perception device under the current installation posture parameters based on the difference between the identification information of the target object in the target fusion data and the identification information of the target object in the first scene data; and determine the road coverage of the perception device under the current installation posture parameters based on the difference between the road area data in the target fusion data and the road area data in the first scene data.

[0115] In an exemplary embodiment, the posture test module 702 is installed and is also used to receive device position indication information, wherein the device position indication information is used to indicate that the radar has been placed in the millimeter wave test dark box and the camera has been placed in the optical test dark box.

[0116] In an exemplary embodiment, the installation posture determination module 703 is also used to set a calibration target located in a specified direction of the sensor model in an external field environment; adjust the installation posture of the perception device and the installation posture of the sensor model in the scene simulation software according to the optimal installation posture parameters; detect the calibration target through the sensor model to obtain second scene data, transmit the second scene data to the perception device, and obtain second test data obtained by the perception device testing the second scene data; generate calibration parameters of the perception device at the optimal installation position according to the second test data, and calibrate the perception device based on the calibration parameters to obtain a calibrated perception device.

[0117] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules as part of the device can be run in Figure 1 In the hardware environment shown, it can be implemented by software or by hardware, wherein the hardware environment includes a network environment.

[0118] According to another aspect of the embodiments of the present application, a storage medium is further provided. Optionally, in this embodiment, the storage medium can be used to execute the program code of any of the above-mentioned radar-visual fusion testing methods in the embodiments of the present application.

[0119] Optionally, in this embodiment, the storage medium may be located on at least one network device among a plurality of network devices in the network shown in the above embodiment.

[0120] Optionally, in this embodiment, the storage medium is configured to store a program code for executing any of the above-mentioned radar-visual fusion testing methods.

[0121] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, which will not be described in detail in this embodiment.

[0122] Optionally, in this embodiment, the storage medium may include but is not limited to: a U disk, a ROM, a RAM, a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0123] According to another aspect of the embodiment of the present application, an electronic device for implementing the above-mentioned radar-vision fusion testing method is also provided. The electronic device may be a smart device, a server, a terminal, or a combination thereof.

[0124] Figure 8 is a structural block diagram of an optional electronic device according to an embodiment of the present application, such as Figure 8 As shown, it includes a processor 802, a communication interface 804, a memory 806 and a communication bus 808, wherein the processor 802, the communication interface 804 and the memory 806 communicate with each other through the communication bus 808, wherein,

[0125] Memory 806, used for storing computer programs;

[0126] The processor 802 is used to implement the program code of any of the above-mentioned radar-visual fusion testing methods when executing the computer program stored in the memory 806.

[0127] Optionally, the communication bus may be a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 The communication interface is used for communication between the above electronic device and other devices.

[0128] The memory may include RAM, or may include non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0129] As an example, the memory 806 may include, but is not limited to, each module in the above-mentioned test device for thunder and vision fusion. In addition, it may also include, but is not limited to, other module units in the above-mentioned test device for thunder and vision fusion, which will not be repeated in this example.

[0130] The above-mentioned processor can be a general-purpose processor, which can include but not be limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; it can also be DSP (Digital Signal Processing), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0131] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0132] It can be understood by those skilled in the art that Figure 8 The structure shown is for illustration only. The device for implementing the above-mentioned radar-visual fusion test method may be a terminal device, which may be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, and other terminal devices. Figure 8 The structure of the electronic device is not limited. Figure 8 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 8 Different configurations shown.

[0133] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0134] An embodiment of the present application further provides another computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0135] The embodiments of the present application also provide a computer program, which includes computer instructions, which are stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the steps in any one of the above method embodiments.

[0136] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, which can include: a flash drive, ROM, RAM, a magnetic disk or an optical disk, etc.

[0137] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0138] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.

[0139] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0140] In the several embodiments provided in the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0141] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution provided in this embodiment.

[0142] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist physically separately, or at least two units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0143] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for testing radar-visual fusion, characterized in that: include: Establish the field environment through scenario simulation software; The external field environment is established according to the actual installation environment where the sensing device is located; the external field environment includes a target object and a sensing model corresponding to the sensing device; Acquire multiple groups of installation posture parameters corresponding to the perception device, and use each group of installation posture parameters in the multiple groups of installation posture parameters as the current installation posture parameters to perform the following test operations to obtain the perception performance parameters of the perception device under each group of installation posture parameters: adjust the installation posture of the perception device and the installation posture of the sensing model according to the current installation posture parameters; detect the target object through the sensing model to obtain first scene data, transmit the first scene data to the perception device, and obtain first test data obtained by the perception device testing the first scene data; determine the perception performance parameters of the perception device under the current installation posture parameters according to the first test data; The installation posture parameters corresponding to the optimal perception performance parameters in the multiple groups of installation posture parameters are determined as the optimal installation posture parameters of the perception device.

2. The method according to claim 1, characterized in that: The perception device includes a radar and a camera; the first scene data includes target detection data and video data, the target detection data is output to the radar, and the video data is output to the camera; The obtaining first test data obtained by the sensing device testing the first scene data includes: Acquire first perception data obtained by the radar sensing the target detection data; Acquire second perception data obtained by the camera sensing the video data; The first test data includes the first perception data and the second perception data.

3. The method according to claim 2, characterized in that Determining the perception performance parameters of the perception device under the current installation posture parameters according to the first test data includes: Performing perception data fusion on the first perception data and the second perception data to obtain target fusion data; According to the difference between the target fusion data and the first scene data, the perception performance parameters of the perception device under the current installation posture parameters are determined.

4. The method according to claim 3, characterized in that The target fusion data and the first scene data are both used to indicate the speed of the target object, the distance between the target object and the sensing device, and the track of the target object; The determining, according to the difference between the target fusion data and the first scene data, the perception performance parameters of the perception device under the current installation position and posture parameters includes: Determining a first performance parameter of the perception device under the current installation posture parameter according to a difference between a speed of the target object indicated by the target fusion data and a speed of the target object indicated by the first scene data; Determine a second performance parameter of the perception device under the current installation posture parameter according to a difference between a distance between the target object indicated by the target fusion data and the perception device and a distance between the target object indicated by the first scene data and the perception device; Determining a third performance parameter of the perception device under the current installation posture parameter according to a difference between the track of the target object indicated by the target fusion data and the track of the target object indicated by the first scene data; Determine the perception performance parameters of the perception device under the current installation posture parameters according to the first performance parameter, the second performance parameter and the third performance parameter.

5. The method according to claim 3, characterized in that: The perception performance parameters include target tracking performance, target recognition rate and road coverage; the target fusion data and the first scene data both include identification information of the detected target object and road area data; The step of determining the perception performance parameters of the perception device under the current installation posture parameters according to the difference between the target fusion data and the first scene data includes: Determining the target tracking performance and target recognition rate of the perception device under the current installation posture parameters according to the difference between the identification information of the target object in the target fusion data and the identification information of the target object in the first scene data; According to the difference between the road area data in the target fusion data and the road area data in the first scene data, the road coverage of the perception device under the current installation posture parameters is determined.

6. The method according to claim 2, characterized in that Before performing the following test operation using each set of installation posture parameters in the multiple sets of installation posture parameters as current installation posture parameters, the method further includes: Equipment placement indication information is received, wherein the equipment placement indication information is used to indicate that the radar has been placed in a millimeter wave test dark box, and the camera has been placed in an optical test dark box.

7. The method according to any one of claims 1 to 6, characterized in that After determining the installation posture parameters corresponding to the optimal perception performance parameters among the multiple groups of installation posture parameters as the optimal installation posture parameters of the perception device, the method further includes: Setting a calibration target in the field environment at a specified direction of the sensing model; According to the optimal installation posture parameters, adjusting the installation posture of the perception device and the installation posture of the sensor model in the scene simulation software; Detecting the calibration target through the sensing model to obtain second scene data, transmitting the second scene data to the perception device, and obtaining second test data obtained by the perception device testing the second scene data; According to the second test data, calibration parameters of the sensing device in the optimal installation position are generated, and the sensing device is calibrated based on the calibration parameters to obtain the calibrated sensing device.

8. A test device for radar and visual fusion, characterized in that: include: A simulation environment establishment module is used to establish an outdoor environment through scene simulation software; The external field environment is established according to the actual installation environment where the sensing device is located; the external field environment includes a target object and a sensing model corresponding to the sensing device; An installation posture test module is used to obtain multiple groups of installation posture parameters corresponding to the perception device, and use each group of installation posture parameters in the multiple groups of installation posture parameters as the current installation posture parameters to perform the following test operations to obtain the perception performance parameters of the perception device under each group of installation posture parameters: adjust the installation posture of the perception device and the installation posture of the sensing model according to the current installation posture parameters; detect the target object through the sensing model to obtain first scene data, transmit the first scene data to the perception device, and obtain first test data obtained by the perception device testing the first scene data; determine the perception performance parameters of the perception device under the current installation posture parameters according to the first test data; The installation posture determination module is used to determine the installation posture parameters corresponding to the optimal perception performance parameters among the multiple groups of installation posture parameters as the optimal installation posture parameters of the perception device.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program implements the steps of any one of the methods of claims 1 to 7 when executed by a processor.

10. An electronic 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 steps of the method according to any one of claims 1 to 7 are implemented.

Images