Laser radar calibration method, device, computer equipment and storage medium

Abstract

The embodiments of the present disclosure relate to a laser radar calibration method, device, computer equipment and storage medium. The method obtains radar point cloud data within a preset scanning range of the laser radar, and then obtains map point cloud data of a to-be-matched area corresponding to the preset scanning range from map point cloud data whose accuracy of the preset scanning range is greater than a preset accuracy threshold, and then matches the map point cloud data of the to-be-matched area with the radar point cloud data to obtain the calibration parameters of the laser radar. Since the map point cloud data is high-precision map point cloud data, the laser radar is calibrated using high-precision data. Compared with the traditional method of calibrating the laser radar using a specific positioning device, the calibration method described in the embodiments of the present disclosure will not affect the accuracy of the calibration due to the low accuracy of the positioning device. Therefore, the calibration method provided by the embodiments of the present disclosure can improve the accuracy of the calibration.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of map measurement technology, and in particular to a laser radar calibration method, device, computer equipment and storage medium. Background Art

[0002] With the development of measurement technology, roadside LiDAR has a relatively mature detection capability. The base station can identify the target objects in the surrounding environment based on the point cloud data output by the LiDAR, and then obtain the position, height, size and other information of the target objects. In the detection process of the roadside LiDAR, the origin of the LiDAR needs to be calibrated first, so that the absolute position of the target object can be calculated based on the origin of the calibrated LiDAR, and then the target object can be accurately identified.

[0003] At present, the method for calibrating the origin of the laser radar mainly uses a GPS positioning device, an angle measuring device, or other measuring equipment to measure the installation position of the laser radar, and directly uses the parameters obtained after the measurement as the origin of the calibrated laser radar.

[0004] However, due to factors such as improper operation level or low accuracy of the equipment itself, the above calibration method has the problem of inaccurate calibration. Summary of the invention

[0005] The embodiments of the present disclosure provide a laser radar calibration method, apparatus, computer equipment, and storage medium, which can be used to improve the calibration accuracy when calibrating the laser radar.

[0006] In a first aspect, an embodiment of the present disclosure provides a laser radar calibration method, the method comprising:

[0007] Obtain radar point cloud data within the preset scanning range of the laser radar;

[0008] From the map point cloud data of the preset scanning range, the map point cloud data of the to-be-matched area corresponding to the preset scanning range is obtained; the accuracy of the map point cloud data is greater than the preset accuracy threshold;

[0009] The map point cloud data and radar point cloud data of the area to be matched are matched to obtain the calibration parameters of the laser radar; the map point cloud data of the area to be matched and the radar point cloud data within the preset scanning range contain the same object to be matched; the calibration parameters include the longitude, latitude, altitude, rotation angle around longitude, rotation angle around latitude, and rotation angle around altitude of the origin of the laser radar coordinate system.

[0010] In one embodiment, before matching the map point cloud data and the radar point cloud data of the area to be matched to obtain the calibration parameters of the laser radar, the method further includes:

[0011] The dynamic radar point cloud data in the radar point cloud data is eliminated to obtain the static radar point cloud data;

[0012] Match the map point cloud data and radar point cloud data of the area to be matched to obtain the calibration parameters of the lidar, including:

[0013] Match the map point cloud data of the area to be matched with the static radar point cloud data to obtain the calibration parameters of the lidar.

[0014] In one embodiment, the map point cloud data of the area to be matched and the static radar point cloud data are matched to obtain the calibration parameters of the laser radar, including:

[0015] Extracting features from the static radar point cloud data to obtain a first feature set; the first feature set includes at least two first features;

[0016] Extracting features from the map point cloud data of the area to be matched to obtain a second feature set;

[0017] The first feature set is matched with the second feature set to obtain the calibration parameters of the laser radar.

[0018] In one embodiment, the calibration parameters include the rotation angle of the origin of the laser radar coordinate system, and the first feature set is matched with the second feature set to obtain the calibration parameters of the laser radar, including:

[0019] Obtaining a first projection line segment of a line segment between two first features in the first feature set on a preset plane in the radar coordinate system, and obtaining a first projection angle between the first projection line segment and a corresponding coordinate axis;

[0020] Obtain a second projection line segment of a line segment between two second features in the second feature set on a preset plane in the geographic coordinate system, and obtain a second projection angle between the second projection line segment and the corresponding coordinate axis; the types of the two second features in the second feature set are the same as the types of the two first features in the first feature set;

[0021] The first projection angle and the second projection angle are differenced to obtain the rotation angle of the laser radar; the rotation angle of the origin of the laser radar coordinate system includes the rotation angle around the longitude, the rotation angle around the latitude, and the rotation angle around the altitude.

[0022] In one embodiment, if the preset plane in the radar coordinate system is the XZ plane, the coordinate axis corresponding to the XZ plane is the Z axis, the preset plane in the geographic coordinate system is the altitude plane, the coordinate axis corresponding to the altitude plane is the altitude axis, and the rotation angle of the origin of the laser radar coordinate system is the rotation angle around the latitude;

[0023] If the preset plane in the radar coordinate system is the YZ plane, the coordinate axis corresponding to the YZ plane is the Y axis. If the preset plane in the geographic coordinate system is the latitude plane, the coordinate axis corresponding to the latitude plane is the latitude axis. The rotation angle of the origin of the laser radar coordinate system is the rotation angle around the longitude.

[0024] If the preset plane in the radar coordinate system is the XY plane, the coordinate axis corresponding to the XY plane is the X axis. If the preset plane in the geographic coordinate system is the longitude plane, the coordinate axis corresponding to the longitude plane is the longitude axis. The rotation angle of the origin of the lidar coordinate system is the rotation angle around the altitude.

[0025] In one embodiment, the calibration parameters also include the position coordinates of the origin of the laser radar coordinate system. The calibration parameters of the laser radar are obtained according to the first feature set and the second feature set, including:

[0026] Matching each first feature in the first feature set with each second feature in the second feature set to obtain a target first feature and a target second feature that belong to the same type;

[0027] The position coordinates of the origin of the laser radar coordinate system are determined according to the position coordinates of the first feature of the target and the position coordinates of the second feature of the target; the position coordinates include longitude, latitude, and altitude.

[0028] In one embodiment, determining the position coordinates of the origin of the laser radar coordinate system according to the position coordinates of the first feature of the target and the position coordinates of the second feature of the target includes:

[0029] Substituting the rotation angle into a preset cosine function to obtain a value of the cosine function, and correcting the position coordinates of the first feature of the target according to the value of the cosine function to obtain the corrected position coordinates of the first feature of the target;

[0030] The position coordinates of the origin of the laser radar coordinate system are determined according to the corrected position coordinates of the first feature of the target and the position coordinates of the second feature of the target.

[0031] In one embodiment, determining the position coordinates of the origin of the laser radar coordinate system according to the position coordinates of the first feature of the target and the position coordinates of the second feature of the target includes:

[0032] Determine the longitude of the origin of the laser radar coordinate system according to the corrected X coordinate in the position coordinates of the first feature of the target and the longitude coordinate in the position coordinates of the second feature of the target;

[0033] Determine the latitude of the origin of the laser radar coordinate system according to the Y coordinate in the position coordinates of the first feature of the target and the latitude coordinate in the position coordinates of the second feature of the target after correction;

[0034] The altitude of the origin of the laser radar coordinate system is determined according to the Z coordinate in the corrected position coordinates of the first feature of the target and the altitude coordinate in the position coordinates of the second feature of the target.

[0035] In one embodiment, obtaining map point cloud data of a to-be-matched area corresponding to the preset scanning range from the map point cloud data according to the preset scanning range includes:

[0036] Determine the initial origin according to the installation position of the laser radar;

[0037] With the initial origin as the center, map point cloud data within a preset scanning range is selected from the map point cloud data as the map point cloud data of the area to be matched.

[0038] In a second aspect, an embodiment of the present disclosure provides a laser radar calibration device, the device comprising:

[0039] The first acquisition module is used to acquire radar point cloud data of the laser radar within a preset scanning range;

[0040] A second acquisition module is used to acquire, from the map point cloud data of the preset scanning range, the map point cloud data of the to-be-matched area corresponding to the preset scanning range; the accuracy of the map point cloud data is greater than a preset accuracy threshold;

[0041] A matching module is used to match the map point cloud data of the area to be matched with the radar point cloud data to obtain the calibration parameters of the laser radar; the map point cloud data of the area to be matched and the radar point cloud data within a preset scanning range contain the same object to be matched; the calibration parameters include the longitude, latitude, altitude, rotation angle around longitude, rotation angle around latitude, and rotation angle around altitude of the origin of the laser radar coordinate system.

[0042] In a third aspect, an embodiment of the present disclosure provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the computer program.

[0043] In a fourth aspect, an embodiment of the present disclosure provides a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method described in the first aspect above.

[0044] The laser radar calibration method, device, computer equipment and storage medium provided in the embodiments of the present disclosure obtains radar point cloud data within a preset scanning range of the laser radar, and then obtains map point cloud data of the to-be-matched area corresponding to the preset scanning range from the map point cloud data whose accuracy of the preset scanning range is greater than the preset accuracy threshold, and then matches the map point cloud data of the to-be-matched area with the radar point cloud data to obtain the calibration parameters of the laser radar, wherein the calibration parameters include the longitude, latitude, altitude, rotation angle around longitude, rotation angle around latitude, and rotation angle around altitude of the origin of the laser radar coordinate system. Since the map point cloud data is high-precision map point cloud data, the laser radar is calibrated using the high-precision map point cloud data and radar point cloud data, thereby realizing the calibration of the laser radar using high-precision data. Compared with the traditional method of calibrating the laser radar using a specific positioning device, the calibration method described in the embodiments of the present disclosure will not affect the accuracy of the calibration due to the low accuracy of the positioning device, and will not affect the efficiency of the calibration due to the instability of the accuracy of the positioning device. Therefore, the calibration method provided by the embodiment of the present disclosure can improve the accuracy of calibration and also improve the efficiency of calibration. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is an application environment diagram of a multi-base station collaborative sensing method in an embodiment;

[0046] Figure 2 Schematic diagram of a process of a multi-base station collaborative sensing method in one embodiment;

[0047] Figure 3 is a schematic diagram of a flow chart of a laser radar calibration method in one embodiment;

[0048] Figure 4 for Figure 3 Schematic diagram of the process of step S1003 in the embodiment;

[0049] Figure 5 for Figure 4 Schematic diagram of the process of step S1006 in the embodiment;

[0050] Figure 6 for Figure 4 Schematic diagram of the process of step S1006 in the embodiment;

[0051] Figure 7 for Figure 6 Schematic diagram of the process of step S1011 in the embodiment;

[0052] Figure 8 for Figure 3 Schematic diagram of the process of step S1002 in the embodiment;

[0053] Fig. 9A schematic diagram of a flow chart of a multi-base station registration method in one embodiment;

[0054] Fig.10 A schematic diagram of a flow chart of a multi-base station registration method in one embodiment;

[0055] Fig.11 A schematic diagram of a flow chart of a multi-base station registration method in one embodiment;

[0056] Fig.12 for Fig.11 Schematic diagram of the process of step S1209 in the embodiment;

[0057] Fig.13 for Fig.12 Schematic diagram of the process of step S1213 in the embodiment;

[0058] Fig.14 A schematic diagram of a process for determining a target region of interest in one embodiment;

[0059] Fig.15 for Fig.14 Schematic diagram of the process of step S1303 in the embodiment;

[0060] Fig.16 is a schematic diagram of a target region of interest in one embodiment;

[0061] Fig.17 for Fig.16 Schematic diagram of the process of step S1306 in the embodiment;

[0062] Fig.18 is a schematic diagram of a target region of interest in one embodiment;

[0063] Fig.19 A schematic diagram of a process for determining a target region of interest in one embodiment;

[0064] Fig. 20 is a flow chart of a data processing method in one embodiment;

[0065] Fig.21 for Fig. 20 Schematic diagram of the process of step S1402 in the embodiment;

[0066] Fig. 22 for Fig.21 Schematic diagram of the process of step S1404 in the embodiment;

[0067] Fig.23 for Fig. 22 Schematic diagram of the process of step S1406 in the embodiment;

[0068] Fig.24 for Fig. 22Schematic diagram of the process of step S1407 in the embodiment;

[0069] Fig.25 is a flow chart of a data processing method in one embodiment;

[0070] Fig.26 for Fig.25 Schematic diagram of the process of step S1417 in the embodiment;

[0071] Fig. 27 for Fig.26 Schematic diagram of the process of step S1419 in the embodiment;

[0072] Fig.28 for Fig.26 Schematic diagram of the process of step S1419 in the embodiment;

[0073] Fig.29 for Fig.26 Schematic diagram of the process of step S1419 in the embodiment;

[0074] Fig.30 for Fig.26 Schematic diagram of the process of step S1419 in the embodiment;

[0075] Fig.31 is a flow chart of a data processing method in one embodiment;

[0076] Fig.32 Schematic diagram of a target detection method in one embodiment;

[0077] Fig.33 is a flow chart of a target detection method in another embodiment;

[0078] Fig.34 is a flow chart of a target detection method in another embodiment;

[0079] Fig.35 is a flow chart of a target detection method in another embodiment;

[0080] Fig.36 A schematic diagram of a process of a roadside radar positioning monitoring method in an embodiment;

[0081] Fig.37 A schematic diagram of a process for obtaining second space information in one embodiment;

[0082] Fig.38 is a schematic diagram of an initial point cloud image in one embodiment;

[0083] Fig.39 A schematic diagram of a process of obtaining first spatial information in an embodiment;

[0084] Fig.40 A schematic diagram of a process for determining whether a roadside radar has positioning abnormality in one embodiment;

[0085] Fig.41 A schematic diagram of a flow chart for determining whether a roadside radar has positioning abnormality in another embodiment;

[0086] Fig.42 is a structural block diagram of a laser radar calibration device in one embodiment;

[0087] Fig.43 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0088] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0089] The technical solutions involved in the embodiments of the present disclosure are introduced below in combination with the scenarios to which the embodiments of the present disclosure are applied.

[0090] The multi-base station collaborative sensing method provided by the embodiment of the present disclosure can be applied to Figure 1 In the application environment shown. Among them, the server is connected to multiple base stations, each base station can be equipped with a laser radar, the base stations can communicate with each other, and the base stations communicate with the server through the network. Each laser radar is used to scan its surrounding environment area and then output radar point cloud data, and send it to the corresponding server and / or base station; the server and / or base station can process the received radar point cloud data to achieve target detection, target tracking and other processes. Among them, the laser radar can be a roadside laser radar or other types of laser radars. The base station can process the received data. The base station can include various forms of roadside units (RoadSide Unit, RSU), edge servers and other edge computing devices. The server can be an independent server or a server cluster composed of multiple servers.

[0091] In one embodiment, Figure 2 As shown, a multi-base station cooperative sensing method is provided, and the method is applied to Figure 1 The server in the example is used to illustrate the following steps:

[0092] S10, receiving radar point cloud data and their corresponding map point cloud data sent by multiple base stations; the accuracy of the map point cloud data is greater than a preset accuracy threshold.

[0093] S11, matching the radar point cloud data on each base station with the corresponding map point cloud data to obtain the position coordinates of each base station.

[0094] S12. According to the position coordinates of each base station and the relative position coordinates between the base stations, the radar point cloud data of each base station is converted into a preset coordinate system to obtain the target radar point cloud data.

[0095] S13. Determine the target area of ​​interest according to the target radar point cloud data, the first map and the second map; the first map is map point cloud data in a point cloud format, and the second map is map point cloud data in a vector format.

[0096] S14. Extracting radar point cloud data within the target region of interest from the target radar point cloud data.

[0097] S15. Identify the target object in the target area of ​​interest according to the radar point cloud data in the target area of ​​interest, and obtain feature information of the target object.

[0098] The multi-base station collaborative sensing method of this embodiment can realize a wider range of information perception through the collaboration of multiple base stations. It should be noted that the multi-base station collaborative sensing method can be applied to a server, or to an edge computing device, or an integrated system configured with a server and an edge device. As long as the computing power of the server, edge computing device or integrated system is sufficient to support the calculations involved in each step of the above-mentioned multi-base station collaborative sensing method. The present application does not limit whether the multi-base station collaborative sensing method is applied to a server, an edge computing device or the above-mentioned integrated system. When the multi-base station collaborative sensing method is applied to an integrated system configured with a server and an edge device, how to assign corresponding tasks to the server and the edge device can be flexibly selected according to actual needs and device configuration, and the present application does not limit this.

[0099] Before using laser radar for environmental perception, or before performing multi-base station collaborative perception, it is generally necessary to calibrate (align) the laser radar of the base station and each base station in the multi-base station system. The following embodiment describes the calibration (alignment) process in detail, as follows: (It should be noted that the server can calibrate the laser radar, and the base station can also calibrate the laser radar, and the calibration method can be the same. The position coordinates of the origin of the laser radar coordinate system are provided in this embodiment. The calibration process is based on map point cloud data, which is to realize the process of converting the acquired point cloud data to the coordinate system of the map point cloud data by the laser radar or the base station equipped with the laser radar through the principle of permeation)

[0100] In one embodiment, a laser radar calibration method is provided, such as Figure 3 As shown, the method includes:

[0101] S1001. Obtain radar point cloud data of the laser radar within a preset scanning range.

[0102] The preset scanning range can be determined by the server in advance according to the recognition requirements, or according to the performance of the laser radar. For example, the preset scanning range of a general laser radar is a 360° scanning range. The radar point cloud data is the point cloud data obtained after the laser radar scans the surrounding environment. The laser radar can be various types of laser radars. When the laser radar is used to collect point cloud data in a road environment, the laser radar can be installed on any marker, for example, the laser radar can be installed on a tree trunk or a lamp pole.

[0103] Specifically, when the laser radar scans the surrounding environment within a preset scanning range, the laser radar outputs radar point cloud data and sends the radar point cloud data to a base station connected to the laser radar. After the base station receives the radar point cloud data, it can send the radar point cloud data to the server, and the server then identifies objects in the surrounding environment of the base station by analyzing the radar point cloud data.

[0104] S1002. Obtaining, from the map point cloud data of the preset scanning range, the map point cloud data of the to-be-matched area corresponding to the preset scanning range; the accuracy of the map point cloud data is greater than a preset accuracy threshold.

[0105] Among them, the preset accuracy threshold can be determined by the server according to the actual measurement accuracy requirements. The accuracy of the map point cloud data described in this embodiment is greater than the preset accuracy threshold. Therefore, when the preset accuracy threshold is high, the map point cloud data is high-precision map point cloud data. The area to be matched corresponds to the area involved in the preset scanning range of the laser radar. It should be noted that the coordinate system of the map point cloud data is the world coordinate system.

[0106] Specifically, before calibrating the lidar, high-precision map point cloud data can be obtained first, and when the preset scanning range of the lidar is determined, the map point cloud data within the preset scanning range can be further extracted from the map point cloud data according to the preset scanning range as the map point cloud data of the area to be matched, so that the radar point cloud data output by the lidar can be aligned according to the map point cloud data of the area to be matched, thereby realizing the calibration of the lidar.

[0107] S1003, matching the map point cloud data of the area to be matched and the radar point cloud data to obtain calibration parameters of the laser radar; the map point cloud data of the area to be matched and the radar point cloud data within a preset scanning range contain the same object to be matched.

[0108] Wherein, the calibration parameters include the longitude, latitude, altitude, rotation angle around longitude, rotation angle around latitude, and rotation angle around altitude of the origin of the laser radar coordinate system. Optionally, the object to be matched can represent different types of objects such as lane lines, lamp poles, and vehicles. Specifically, when the map point cloud data of the area to be matched is obtained based on the above steps, the features in the map point cloud data of the area to be matched and the features in the radar point cloud data can be matched first using the original calibration parameters to obtain a matching result, and then the matching result is adjusted by adjusting the original calibration parameters so that the matching result meets the preset standard, and the adjusted calibration parameters are output to end the calibration process. It should be noted that when matching the map point cloud data and the radar point cloud data of the area to be matched, the prerequisite is that the map point cloud data of the area to be matched and the radar point cloud data within the preset scanning range need to contain the same object to be matched, so that it can be determined whether the matching result meets the preset standard based on the same object to be matched. Specifically, it can be determined whether the matching result meets the preset condition by calculating the coordinate distance between the point cloud points on the object to be matched in the radar point cloud data and the map point cloud data. At this time, the preset condition can be set to the minimum coordinate distance, that is, the matching result is determined to meet the preset condition, or the distance can be set to be less than a preset threshold, that is, the matching result is determined to meet the preset condition.

[0109] In the above laser radar calibration method, by obtaining the radar point cloud data of the laser radar within the preset scanning range, and then obtaining the map point cloud data of the to-be-matched area corresponding to the preset scanning range from the map point cloud data with an accuracy greater than the preset accuracy threshold according to the preset scanning range, the map point cloud data of the to-be-matched area and the radar point cloud data are matched to obtain the calibration parameters of the laser radar. Since the map point cloud data is high-precision map point cloud data, the laser radar is calibrated using the high-precision map point cloud data and the radar point cloud data, which realizes the calibration of the laser radar using high-precision data and can improve the accuracy of the calibration. Compared with the traditional method of calibrating the laser radar using a specific positioning device, the calibration method described in the embodiment of the present disclosure will not affect the accuracy of the calibration due to the low accuracy of the positioning device, and will not affect the efficiency of the calibration due to the instability of the accuracy of the positioning device. Therefore, the calibration method provided in the embodiment of the present disclosure can improve the accuracy of the calibration and at the same time improve the efficiency of the calibration.

[0110] In practical applications, the laser radar can use the calibration parameters obtained in the above calibration process to convert the point cloud data obtained by the radar point cloud data into the coordinate system of the map point cloud data. Usually, the coordinate position of the map point cloud data is based on longitude and latitude. On this basis, after the laser radar obtains the radar point cloud data, it can obtain the absolute position coordinates (longitude and latitude) according to the above calibration parameters. Since most road scene interactions are based on absolute position coordinates, the above calibration process is conducive to the widespread application of the laser radar.

[0111] Optionally, under the premise that the absolute position coordinates of the target can be obtained, the position coordinates of the origin of the laser radar coordinate system enable the server to implement position recognition, type recognition, attribute recognition and other recognition work of the target object to be identified based on the absolute position coordinates of the target object to be identified in combination with the corresponding recognition algorithm, thereby achieving the purpose of detecting the target object. Therefore, it can be widely used in any field that requires target recognition, such as vehicle recognition, obstacle recognition, road detection, etc. in the field of autonomous driving navigation.

[0112] In one embodiment, before the above S1003 "matching the map point cloud data of the to-be-matched area with the radar point cloud data to obtain the calibration parameters of the laser radar", Figure 3 The method described in the embodiment also includes the step of removing dynamic radar point cloud data from the radar point cloud data to obtain static radar point cloud data.

[0113] The dynamic radar point cloud data includes the point cloud data of objects in the radar point cloud data that are in a moving state, such as the point cloud data of a moving vehicle. The static radar point cloud data includes the point cloud data of objects in the radar point cloud data that are in a stationary state, such as a roadside lamp post.

[0114] Specifically, when the server obtains the radar point cloud data output by the lidar, it can further perform elimination processing on the radar point cloud data. Specifically, the point cloud data belonging to moving objects in the radar point cloud data, i.e., dynamic radar point cloud data, is first determined, and then the dynamic radar point cloud data is eliminated from the radar point cloud data. The point cloud data belonging to stationary objects, i.e., static radar point cloud data, is retained, so that the server can then calibrate the lidar according to the static radar point cloud data.

[0115] In the above embodiment, since the objects in the static radar point cloud data are all stationary, the error of the static radar point cloud data acquired by the lidar is relatively small compared to the dynamic radar point cloud data, thereby improving the calibration accuracy of the server when calibrating the lidar based on the static radar point cloud data.

[0116] Specifically, when the server obtains the static radar point cloud data, the static radar point cloud data can be used to calibrate the laser radar. Therefore, the above S1003 specifically includes: matching the map point cloud data of the area to be matched with the static radar point cloud data to obtain the calibration parameters of the laser radar.

[0117] When the server obtains the static radar point cloud data based on the above steps, it can match the features in the static radar point cloud data with the features in the map point cloud data of the area to be matched to obtain a matching result, and then adjust the original calibration parameters so that the matching result meets the preset standard, output the adjusted calibration parameters, and end the calibration process. Optionally, the original calibration parameters can be obtained by measurement, or they can be the current calibration parameters of the laser radar. Optionally, the point cloud in the static radar point cloud data can be matched with the point cloud in the map point cloud data of the area to be matched to obtain a matching result, and then adjust the original calibration parameters so that the matching result meets the preset standard, output the adjusted calibration parameters, and end the calibration process. Optionally, the original calibration parameters can be obtained by measurement, or they can be the current calibration parameters of the laser radar. .

[0118] Based on the implementation of S1003 described in the above embodiment, the embodiment of the present disclosure also provides a specific implementation method of the implementation, such as Figure 4 As shown, the specific implementation method includes: including:

[0119] S1004. Extract features from the static radar point cloud data to obtain a first feature set; the first feature set includes at least two first features.

[0120] The features in the static radar point cloud data represent static objects in the surrounding environment scanned by the laser radar. For example, the features may be the sidelines of the road, markers around the road, trees, lamp poles, etc. The first features included in the first feature set may be all features extracted from the static radar point cloud data, or may be part of the extracted features. For example, the road and the lamp poles beside the road are extracted from the static radar point cloud data, and the corresponding first feature set includes the two first features of the road and the lamp poles beside the road.

[0121] Specifically, when the server obtains the static radar point cloud data, it can extract all the features in the static radar point cloud data through the existing feature extraction algorithm, or extract some features in the static radar point cloud data according to the matching requirements, thereby obtaining at least two extracted features, that is, a first feature set including at least two first features. The above feature extraction algorithm can use a neural network feature extraction algorithm, or other feature extraction algorithms, which are not limited here.

[0122] S1005. Extract features from the map point cloud data of the area to be matched to obtain a second feature set.

[0123] The features in the map point cloud data of the area to be matched represent objects within the area covered by the map, such as the edge lines of the roads in the map, markers around the roads, trees, lamp posts, etc. The second features included in the second feature set may be all features extracted from the map point cloud data, or may be part of the extracted features. For example, the road and the lamp posts beside the road are extracted from the map point cloud data, and the corresponding second feature set includes the two second features of the road and the lamp posts beside the road.

[0124] Specifically, when the server obtains the map point cloud data, it can also correspondingly obtain all or part of the features in the map point cloud data; optionally, the server can also extract all the features in the map point cloud data through an existing feature extraction algorithm, or extract part of the features in the map point cloud data according to the matching requirements, thereby obtaining at least two extracted features, that is, a second feature set containing at least two second features. It should be noted that the number of second features contained in the second feature set may be the same as or different from the number of first features.

[0125] S1006. Match the first feature set with the second feature set to obtain calibration parameters of the laser radar.

[0126] When the server obtains the first feature set and the second feature set based on the above steps, it can match each first feature in the first feature set with each second feature in the second feature set to obtain a set of matched first features and second features, or multiple sets of matched first features and second features, to obtain a matching result, and then adjust the original calibration parameters so that the matching result meets the preset standard, output the adjusted calibration parameters, and end the calibration process. The relevant information of the above features can be the location coordinates, direction, size, heading angle, and other information of the feature.

[0127] The above disclosed embodiment realizes the calibration of the laser radar based on the matching features in the static radar point cloud data and the map point cloud data. Since the features in the map point cloud data are precise features, the calibration accuracy can be improved by calibrating the laser radar using high-precision features. Moreover, since the features in the map point cloud data are easy to obtain and do not require additional equipment to obtain, compared with the traditional calibration method that requires additional positioning equipment for positioning, the calibration method described in this embodiment can also reduce the calibration cost.

[0128] In one embodiment, the calibration parameters include the longitude, latitude, altitude, rotation angle around longitude, rotation angle around latitude, and rotation angle around altitude of the origin of the coordinate system of the radar point cloud data. The above S1006 "matching the first feature set with the second feature set to obtain the calibration parameters of the laser radar" is as follows: Figure 5 As shown, including:

[0129] S1007. Obtain a first projection line segment of a line segment between two first features in the first feature set on a preset plane in the radar coordinate system, and obtain a first projection angle between the first projection line segment and a corresponding coordinate axis.

[0130] The radar coordinate system may be a rectangular coordinate system. The preset plane is a plane where any two coordinate axes in the radar coordinate system are located. For example, the coordinate axes of the radar coordinate system include: X-axis, Y-axis, and Z-axis, and the corresponding preset planes include: XY plane, YZ plane, and XZ plane.

[0131] Specifically, when the server obtains the first feature set, any two first features can be selected from the first feature set, and then the two first features can be connected in the radar coordinate system according to the position coordinates of the two first features to obtain a line segment between the two first features, and then the line segment is projected onto a preset plane to obtain a first projection line segment. Further, the coordinate axis corresponding to the preset plane is selected to obtain a first projection angle between the coordinate axis and the first projection line segment. For example, if the preset plane is an XZ plane, the coordinate axis corresponding to the XZ plane is the Z axis, and accordingly, the angle between the first projection line segments of the two first features on the XZ plane and the corresponding Z axis is the first projection angle; if the preset plane is a YZ plane, the coordinate axis corresponding to the YZ plane is the Y axis, and accordingly, the angle between the first projection line segments of the two first features on the YZ plane and the corresponding Y axis is the first projection angle; if the preset plane is an XY plane, the coordinate axis corresponding to the XY plane is the X axis, and accordingly, the angle between the first projection line segments of the two first features on the XY plane and the corresponding X axis is the first projection angle.

[0132] S1008. Obtain a second projection line segment of a line segment between two second features in the second feature set on a preset plane in the geographic coordinate system, and obtain a second projection angle between the second projection line segment and the corresponding coordinate axis; the types of the two second features in the second feature set are the same as the types of the two first features in the first feature set.

[0133] Among them, the preset plane is the plane where any two coordinate axes in the geographic coordinate system are located. For example, the coordinate axes of the geographic coordinate system include: longitude axis, latitude axis, altitude axis, and the corresponding preset planes include: longitude plane, latitude plane, altitude plane.

[0134] Specifically, when the server obtains the second feature set, two second features can be selected from the second feature set, and then the two second features can be connected in the geographic coordinate system according to the position coordinates of the two second features to obtain a line segment between the two second features, and then the line segment is projected onto a preset plane to obtain a second projection line segment. Further, a coordinate axis corresponding to the preset plane is selected to obtain a second projection angle between the coordinate axis and the second projection line segment. For example, if the preset plane is an altitude plane, the coordinate axis corresponding to the altitude plane is the altitude axis, and accordingly, the angle between the first projection line segments of the two first features on the altitude plane and the corresponding altitude axis is the first projection angle; if the preset plane is a latitude plane, the coordinate axis corresponding to the latitude plane is the latitude axis, and accordingly, the angle between the first projection line segments of the two first features on the latitude plane and the corresponding latitude axis is the first projection angle; if the preset plane is a longitude plane, the coordinate axis corresponding to the longitude plane is the longitude axis, and accordingly, the angle between the first projection line segments of the two first features on the longitude plane and the corresponding longitude axis is the first projection angle. It should be noted that the types of the two second features selected here are the same as the types of the two first features selected in the above-mentioned first feature set. For example, if the two first features selected are roads and lamp poles, then the corresponding two second features in the second feature set are also roads and lamp poles.

[0135] S1009. Perform a difference operation on the first projection angle and the second projection angle to obtain a rotation angle of the origin of the laser radar coordinate system; the rotation angle of the origin of the laser radar coordinate system includes a rotation angle around longitude, a rotation angle around latitude, and a rotation angle around altitude.

[0136] When the server obtains the first projection angle and the second projection angle based on the above steps, the first projection angle and the second projection angle are further differenced, and the difference angle after the difference is used as the rotation angle of the calibrated laser radar. When the line segment between the two first features or the line segment between the two second features is projected on the preset plane in the respective coordinate system, the preset planes of projection are different, and the coordinate axes corresponding to the preset planes are different, which correspond to different rotation angles.

[0137] For example, if the preset plane in the radar coordinate system is the XZ plane, the coordinate axis corresponding to the XZ plane is the Z axis, the preset plane in the geographic coordinate system is the altitude plane, the coordinate axis corresponding to the altitude plane is the altitude axis, and the rotation angle of the laser radar is the rotation angle around the latitude; if the preset plane in the radar coordinate system is the YZ plane, the coordinate axis corresponding to the YZ plane is the Y axis, the preset plane in the geographic coordinate system is the latitude plane, the coordinate axis corresponding to the latitude plane is the latitude axis, and the rotation angle of the laser radar is the rotation angle around the longitude; if the preset plane in the radar coordinate system is the XY plane, the coordinate axis corresponding to the XY plane is the X axis, the preset plane in the geographic coordinate system is the longitude plane, the coordinate axis corresponding to the longitude plane is the longitude axis, and the rotation angle of the laser radar is the rotation angle around the altitude.

[0138] In one embodiment, the above S1006 "matching the first feature set with the second feature set to obtain the calibration parameters of the laser radar" is as follows: Figure 6 As shown, including:

[0139] S1010. Match each first feature in the first feature set with each second feature in the second feature set to obtain target first features and target second features that belong to the same type.

[0140] When the server obtains the first feature set and the second feature set based on the above steps, it can filter out the first feature and the second feature of the same type from the first feature set and the second feature set, and use the filtered out first feature as the target first feature, and use the filtered out second feature as the target second feature. Of course, any type of features can be filtered out during the filtering, as long as the filtered out first feature and the second feature are of the same type. For example, the first feature belonging to the lamp pole type is filtered out from the first feature set, and the second feature belonging to the lamp pole type is also filtered out from the second feature set.

[0141] S1011. Determine the position coordinates of the origin of the laser radar coordinate system according to the position coordinates of the first feature of the target and the position coordinates of the second feature of the target; the position coordinates include longitude, latitude, and altitude.

[0142] When the server selects the first feature and the second feature of the target based on the above steps, the position coordinates of the first feature and the second feature of the target can be obtained. Because the position coordinates of the first feature of the target are relative quantities in the radar coordinate system, and the position coordinates of the second feature of the target are absolute quantities in the geographic coordinate system, the position coordinates of the first feature and the second feature of the target are substituted into the corresponding radian calculation formula to calculate the position coordinates of the origin of the laser radar coordinate system; the position coordinates include longitude, latitude, and altitude. The above method calculates the position coordinates of the origin of the laser radar coordinate system of the laser radar through the position coordinates of the same feature in the radar coordinate system and the position coordinates in the geographic coordinate system. The laser radar can be calibrated by simple calculations, and the method is easy to implement.

[0143] In actual applications, when the laser radar scans the surrounding environment to obtain point cloud data, it is usually a horizontal scan, but there are also cases where it is not a horizontal scan. In this case, it is necessary to correct the position coordinates of the first feature extracted from the point cloud data, and then determine the position coordinates of the origin of the laser radar coordinate system based on the corrected position coordinates. Therefore, this embodiment also provides an implementation method of the above-mentioned S1011.

[0144] like Figure 7 As shown, the above S1011 "determine the position coordinates of the origin of the laser radar coordinate system according to the position coordinates of the first feature of the target and the position coordinates of the second feature of the target" includes:

[0145] S1012, substituting the rotation angle into a preset cosine function to obtain a value of the cosine function, and correcting the position coordinates of the first feature of the target according to the value of the cosine function to obtain corrected position coordinates of the first feature of the target.

[0146] This embodiment relates to a specific calculation method for correcting the position coordinates of the first feature of the target. Specifically, the rotation angle can be substituted into the following relationship (1) for calculation to obtain the corrected position coordinates of the first feature of the target:

[0147] A' = A × cos(θ) (1);

[0148] In the above formula, A represents the position coordinate of the first feature of the target, which can represent one of the X coordinate, Y coordinate, and Z coordinate of the first feature of the target; A' represents the corrected position coordinate of the first feature of the target, corresponding to A. θ represents the rotation angle of the laser radar; if A represents the X coordinate, the corresponding θ represents the rotation angle around the altitude, and the corresponding A' represents the corrected X coordinate; if A represents the Y coordinate, the corresponding θ represents the rotation angle around the longitude, and the corresponding A' represents the corrected Y coordinate; if A represents the Z coordinate, the corresponding θ represents the rotation angle around the latitude, and the corresponding A' represents the corrected Z coordinate.

[0149] S1013. Determine the position coordinates of the origin of the laser radar coordinate system according to the corrected position coordinates of the first feature of the target and the position coordinates of the second feature of the target.

[0150] After the base station corrects the position coordinates of the first feature of the target based on the above steps, the method described in S1011 can be used to determine the position coordinates of the origin of the laser radar coordinate system according to the corrected position coordinates of the first feature of the target and the position coordinates of the second feature of the target. The specific method is described in the above S1011 and will not be repeated here.

[0151] The above method determines the position coordinate translation vector of the origin of the laser radar coordinate system through the corrected position coordinates of the first feature of the target and the position coordinates of the second feature of the target, thereby eliminating the error of the laser radar in obtaining radar point cloud data under non-horizontal scanning conditions, thereby improving the accuracy of the obtained calibration parameters.

[0152] Specifically, the position coordinates of the origin of the laser radar coordinate system include: longitude, latitude, and altitude. When the base station executes the above step S1013, the longitude of the origin of the laser radar coordinate system is determined specifically according to the X coordinate in the position coordinates of the first feature of the target after correction and the longitude coordinate in the position coordinates of the second feature of the target; the latitude of the origin of the laser radar coordinate system is determined according to the Y coordinate in the position coordinates of the first feature of the target after correction and the latitude coordinate in the position coordinates of the second feature of the target; the altitude of the origin of the laser radar coordinate system is determined according to the Z coordinate in the position coordinates of the first feature of the target after correction and the altitude coordinate in the position coordinates of the second feature of the target. The above-mentioned methods for determining the longitude, latitude, and altitude can be found in the description of the aforementioned S1011, which will not be repeated here.

[0153] In one embodiment, a specific implementation of the above S1002 is also provided, such as Figure 8 As shown, the above S1002 "obtaining map point cloud data of a to-be-matched area corresponding to the preset scanning range from the map point cloud data within the preset scanning range" includes:

[0154] S1014. Determine the initial origin according to the installation position of the laser radar.

[0155] The initial origin refers to the position coordinates of the lidar in the map point cloud data.

[0156] Specifically, when determining which map point cloud data in the map point cloud data to extract as the map point cloud data of the area to be matched, the initial origin of the laser radar can be determined in the map point cloud data according to the actual installation position of the laser radar, so that the server can then determine the area to be matched in the map point cloud data according to the initial origin. The actual installation position of the laser radar can be any position. For example, in actual applications, the laser radar is installed on a lamp pole, then the lamp pole is found in the map point cloud data, and then the position of the lamp pole is determined as the initial origin of the laser radar.

[0157] S1005 , taking the initial origin as the center, selecting map point cloud data within a preset scanning range from the map point cloud data as map point cloud data of the area to be matched.

[0158] After the server determines the initial origin of the laser radar based on the above steps, it can use the initial origin as the center to obtain corresponding map point cloud data in the area within the preset scanning range around the initial origin, and use the obtained map point cloud data as the map point cloud data of the area to be matched.

[0159] The above method determines the initial origin of the laser radar on a high-precision map through the actual installation position of the laser radar, so that the map point cloud data of the area to be matched can correspond to the radar point cloud data of the laser radar within the preset scanning range, thereby improving the accuracy of subsequent matching results, thereby improving the accuracy of the calibration process.

[0160] In practical applications, when multiple roadside laser radars are used to measure a target object, it is usually necessary to align the multiple roadside laser radars so that the server can spatially synchronize the point cloud data obtained by the multiple roadside laser radars, thereby realizing target detection, target tracking or environmental perception based on the point cloud data of multiple roadside laser radars. However, the current alignment method has the problem of inaccurate alignment. To address this problem, the present application provides a multi-base station alignment method.

[0161] That is, the above S12 is a method for the server to register multiple base stations. The following embodiment describes the process in detail, as follows: In one embodiment, a multi-base station registration method is provided, such as Fig. 9 As shown, the method includes:

[0162] S1201. Obtain radar point cloud data and corresponding map point cloud data of each base station; the accuracy of the map point cloud data is greater than a preset accuracy threshold.

[0163] Among them, the radar point cloud data is the point cloud data obtained after the laser radar of the base station scans the surrounding environment, and the radar point cloud data is used to characterize the distance information of each object in the surrounding environment. The laser radar can be various types of laser radars. When the laser radar is used to collect point cloud data in the road environment, the laser radar can be installed on any marker. For example, the laser radar can be installed at a preset roadside position, such as on a mounting frame or on a lamp pole. The preset accuracy threshold can be determined by the base station according to the actual measurement accuracy requirements. The map point cloud data is the map point cloud data to be matched. The map point cloud data can be the map point cloud data in the area where the base station is located, or it can be the map point cloud data in the scanning area involved in the laser radar within the scanning range. The accuracy of the map point cloud data described in this embodiment is greater than the preset accuracy threshold. Therefore, when the preset accuracy threshold is high, the map point cloud data is high-precision map point cloud data.

[0164] Specifically, the base station can obtain the map point cloud data in the database, or obtain the above map point cloud data in other ways, which are not limited here. At the same time, the base station can start the laser radar to scan the surrounding area within a preset scanning range, thereby obtaining radar point cloud data through the data collected by the laser radar.

[0165] S1202, iteratively executing matching of the radar point cloud data of each base station with the corresponding map point cloud data according to each base station, obtaining the matching result of the position coordinates of the origin of the laser radar coordinate system, adjusting the original registration parameters of each base station according to the matching result, until the output matching result meets the preset conditions, and outputting the adjusted registration parameters of each base station. The registration parameters of the base station include the longitude, latitude, altitude, rotation angle around longitude, rotation angle around latitude, and rotation angle around altitude of the origin of the base station coordinate system.

[0166] Among them, the radar point cloud data and the map point cloud data contain the same objects to be matched. The objects to be matched can represent different types of objects such as lane lines, lamp poles, and vehicles. The position coordinates of the origin of the laser radar coordinate system include longitude coordinates, latitude coordinates, and altitude coordinates. Specifically, when each base station obtains the map point cloud data and the radar point cloud data based on the above steps, it can send these data to the server, and then the server matches the features in the map point cloud data with the features of the objects to be matched extracted from the radar point cloud data to obtain a matching result, and then adjusts the original calibration parameters so that the matching results meet the preset standards, and finally outputs the adjusted registration parameters of each base station. The position coordinates of the origin of the laser radar coordinate system are optional, and the position coordinates of the point cloud in the map point cloud data and the point cloud in the radar point cloud data can also be matched to obtain a matching result, and then the original calibration parameters are adjusted so that the matching results meet the preset standards, and finally the adjusted registration parameters of each base station are output.

[0167] After obtaining the above-mentioned registration parameters of each base station, the registration parameters can be used to convert the data obtained by each base station into the coordinate system of the map point cloud data (world coordinate system) through calculation. It should be noted that in addition to the lidar, each base station can also include other sensors, such as cameras, millimeter-wave radars, etc. These sensors constitute an information perception system. The system will be calibrated during operation to obtain calibration parameters, which can enable the data of each sensor in the system to be converted to the same coordinate system (spatial synchronization process), for example, the image obtained by the camera can be converted to the coordinate system of the lidar.

[0168] S1203: Calculate relative registration parameters of each base station according to the registration parameters of each base station.

[0169] The relative registration parameters can be used to convert the data of other base stations into the coordinate system of this base station, thereby achieving spatial synchronization based on the coordinate system of this base station.

[0170] Specifically, after the server obtains the registration parameters of each base station based on the above steps, it can further perform difference calculation on the registration parameters of each base station to obtain the relative configuration parameters between each base station. Then, the server can realize the registration of each base station based on the obtained relative configuration parameters between each base station.

[0171] In the above registration method, by acquiring the radar point cloud data and the corresponding map point cloud data of each base station, the radar point cloud data of each base station is matched with the corresponding map point cloud data according to a single base station, and the matching result of the position coordinates of the origin of the laser radar coordinate system is obtained. The original registration parameters of each base station are adjusted according to the matching result until the output matching result meets the preset conditions, and the adjusted registration parameters of each base station are output, and then the relative registration parameters of each base station are calculated according to the registration parameters of each base station. Since the registration parameters of each base station are obtained by matching the high-precision map point cloud data and the radar point cloud data, the laser radar is calibrated using high-precision data, so the accuracy of the registration parameters of each base station is high, and the accuracy of the relative registration parameters obtained according to the registration parameters of each base station is also high, which greatly improves the accuracy of multiple base stations when performing registration.

[0172] In one embodiment, a method is provided for each base station to obtain the above map point cloud data, such as Fig.10 As shown, the method includes:

[0173] S1205, obtaining original map point cloud data of each base station; the accuracy of the original map point cloud data is greater than a preset accuracy threshold.

[0174] The original map point cloud data may be the map data in the area where each base station is located, or the map data in the preset scanning range area of ​​the laser radar on each base station. Specifically, each base station may obtain its own original map point cloud data in the database, or may obtain its own original map point cloud data by other means, which are not limited here. The accuracy of the original map point cloud data is the same as that of the map point cloud data.

[0175] S1206, obtaining map point cloud data of an area within a preset scanning range from the original map point cloud data according to the actual installation position of the laser radar of each base station and the preset scanning range of the laser radar as map point cloud data.

[0176] The preset scanning range can be determined in advance by each base station according to the identification requirements, or can be determined according to the performance of the laser radar on each base station. For example, the preset scanning range of a general laser radar is a 360° scanning range. Specifically, each base station can determine the initial origin of its own laser radar in its own original map point cloud data according to the actual installation location of its own laser radar. Then, with the initial origin as the center, the map point cloud data of the area within the preset scanning range is selected from the respective original map point cloud data as the map point cloud data corresponding to each base station.

[0177] It should be noted that in the above process, when determining which map point cloud data in the original map point cloud data to extract as map point cloud data, the initial origin of the laser radar of each base station can be determined in the original map point cloud data according to the actual installation position of the laser radar of each base station, so that each base station can then determine the corresponding area of ​​the map point cloud data in the original map point cloud data according to the initial origin. Among them, the actual installation position of the laser radar can be any position. For example, in actual applications, the laser radar is installed on a lamp pole, then the lamp pole is found in the original map point cloud data, and then the position of the lamp pole is determined as the initial origin of the laser radar. After each base station determines the initial origin of the laser radar based on the above steps, it can obtain the corresponding map point cloud data on the area within the preset scanning range around the initial origin with the initial origin as the center, and use the obtained map point cloud data as the map point cloud data.

[0178] The above method determines the initial origin of the laser radar on a high-precision map through the actual installation position of the laser radar, so that the map point cloud data can correspond to the radar point cloud data within the preset scanning range of the laser radar, thereby improving the matching degree of the subsequent matching of the map point cloud data and the radar point cloud data, thereby improving the accuracy of the subsequent laser radar calibration.

[0179] In one embodiment, before the above S1202 "matching the radar point cloud data of each base station with the corresponding map point cloud data to obtain the matching result of the position coordinates of the origin of the laser radar coordinate system", Fig. 9 The method described in the embodiment also includes the step of removing dynamic radar point cloud data from the radar point cloud data to obtain static radar point cloud data.

[0180] The dynamic radar point cloud data includes the point cloud data of objects in the radar point cloud data that are in a moving state, such as the point cloud data of a moving vehicle. The static radar point cloud data includes the point cloud data of objects in the radar point cloud data that are in a stationary state, such as a roadside lamp post.

[0181] Specifically, when the server obtains the radar point cloud data output by the laser radar on each base station, the radar point cloud data can be further eliminated. Specifically, the point cloud data belonging to moving objects in the radar point cloud data, i.e., dynamic radar point cloud data, is first determined, and then the dynamic radar point cloud data is eliminated from the radar point cloud data, and the point cloud data belonging to stationary objects, i.e., static radar point cloud data, is retained, so that the server can calibrate the laser radar on each base station according to the static radar point cloud data. It should be noted that the map point cloud data usually contains static point cloud data, so this embodiment does not need to eliminate the map point cloud data. However, if the map point cloud data obtained by the base station contains dynamic point cloud data, this embodiment also provides a method for eliminating the map point cloud data, which is consistent with the method used to eliminate the dynamic radar point cloud data. For details, please refer to the above description.

[0182] In the above embodiment, since the objects in the static radar point cloud data are all stationary, the error of the static radar point cloud data acquired by the lidar is relatively small compared to the dynamic radar point cloud data, thereby improving the calibration accuracy of the server when calibrating the lidar based on the static radar point cloud data.

[0183] Specifically, when the server obtains the above-mentioned static radar point cloud data, the static radar point cloud data can be used to calibrate the laser radars on each base station. Therefore, the above-mentioned "matching the radar point cloud data of each base station with the corresponding map point cloud data to obtain the matching result of the position coordinates of the origin of the laser radar coordinate system" in S1202 specifically includes: matching the static radar point cloud data with the corresponding map point cloud data to obtain the matching result of the position coordinates of the origin of the laser radar coordinate system.

[0184] When the server obtains the static radar point cloud data based on the above steps, it can match the features in the static radar point cloud data with the features in the map point cloud data, and then obtain the position calibration of the lidar by analyzing the matched features; optionally, it can also match the point cloud in the static radar point cloud data with the point cloud in the map point cloud data, and then obtain the position calibration of the lidar by analyzing the matched point cloud.

[0185] Based on the implementation of S1202 described in the above embodiment, the disclosed embodiment also provides a specific implementation method of the above-mentioned "matching the static radar point cloud data with the corresponding map point cloud data to obtain the position coordinate matching result of the origin of the laser radar coordinate system", such as Fig.11 As shown, the specific implementation method includes: including:

[0186] S1207. Extract features from the static radar point cloud data to obtain a first feature set; the first feature set includes at least two first features.

[0187] The features in the static radar point cloud data represent static objects in the surrounding environment scanned by the laser radar. For example, the features may be the sidelines of the road, markers around the road, trees, lamp poles, etc. The first features included in the first feature set may be all features extracted from the static radar point cloud data, or may be part of the extracted features. For example, the road and the lamp poles beside the road are extracted from the static radar point cloud data, and the corresponding first feature set includes the two first features of the road and the lamp poles beside the road.

[0188] Specifically, when the server obtains the static radar point cloud data, it can extract all the features in the static radar point cloud data through the existing feature extraction algorithm, or extract some features in the static radar point cloud data according to the matching requirements, thereby obtaining at least two extracted features, that is, a first feature set including at least two first features. The above feature extraction algorithm can use a neural network feature extraction algorithm, or other feature extraction algorithms, which are not limited here.

[0189] S1208. Extract features from the map point cloud data to obtain a second feature set.

[0190] The features in the map point cloud data represent objects within the area covered by the map, such as the edge of the road in the first map, markers, trees, lamp posts around the road, etc. The second features included in the second feature set can be all features extracted from the map point cloud data, or part of the extracted features. For example, the road and the lamp posts beside the road are extracted from the map point cloud data, and the corresponding second feature set includes the two second features of the road and the lamp posts beside the road.

[0191] Specifically, when the server obtains the map point cloud data, it can also correspondingly obtain all or part of the features in the map point cloud data; optionally, the server can also extract all the features in the map point cloud data through an existing feature extraction algorithm, or extract part of the features in the map point cloud data according to the matching requirements, thereby obtaining at least two extracted features, that is, a second feature set containing at least two second features. It should be noted that the number of second features contained in the second feature set may be the same as or different from the number of first features.

[0192] S1209: Match the first feature set with the second feature set to obtain a matching result of the position coordinates of the origin of the laser radar coordinate system.

[0193] When the server obtains the first feature set and the second feature set based on the above steps, it can match each first feature in the first feature set with each second feature in the second feature set to obtain a set of matched first features and second features, or multiple sets of matched first features and second features, and then obtain the matching result of the position coordinates of the first laser radar by analyzing the relevant information of the matched first features and second features. The relevant information of the above features can be information such as the position coordinates, direction, size, heading angle, etc. of the feature.

[0194] The above disclosed embodiment realizes the calibration of the laser radar based on the matching features in the static radar point cloud data and the map point cloud data. Since the features in the map point cloud data are precise features, the calibration accuracy can be improved by calibrating the laser radar using high-precision features. Moreover, since the features in the map point cloud data are easy to obtain and do not require additional equipment to obtain, compared with the traditional calibration method that requires additional positioning equipment for positioning, the calibration method described in this embodiment can also reduce the calibration cost, thereby reducing the subsequent registration cost of multiple base stations.

[0195] In one embodiment, a specific implementation of the above S1209 is provided, such as Fig.12 As shown, the method includes:

[0196] S1210. Obtain a first projection line segment of a line segment between two first features in the first feature set on a preset plane in the radar coordinate system, and obtain a first projection angle between the first projection line segment and a corresponding coordinate axis.

[0197] The radar coordinate system may be a rectangular coordinate system. The preset plane is a plane where any two coordinate axes in the radar coordinate system are located. For example, the coordinate axes of the radar coordinate system include: X-axis, Y-axis, and Z-axis, and the corresponding preset planes include: XY plane, YZ plane, and XZ plane.

[0198] Specifically, when the server obtains the first feature set, any two first features can be selected from the first feature set, and then the two first features can be connected in the radar coordinate system according to the position coordinates of the two first features to obtain a line segment between the two first features, and then the line segment is projected onto a preset plane to obtain a first projection line segment. Further, the coordinate axis corresponding to the preset plane is selected to obtain a first projection angle between the coordinate axis and the first projection line segment. For example, if the preset plane is an XZ plane, the coordinate axis corresponding to the XZ plane is the Z axis, and accordingly, the angle between the first projection line segments of the two first features on the XZ plane and the corresponding Z axis is the first projection angle; if the preset plane is a YZ plane, the coordinate axis corresponding to the YZ plane is the Y axis, and accordingly, the angle between the first projection line segments of the two first features on the YZ plane and the corresponding Y axis is the first projection angle; if the preset plane is an XY plane, the coordinate axis corresponding to the XY plane is the X axis, and accordingly, the angle between the first projection line segments of the two first features on the XY plane and the corresponding X axis is the first projection angle.

[0199] S1211. Obtain a second projection line segment of a line segment between two second features in the second feature set on a preset plane in the geographic coordinate system, and obtain a second projection angle between the second projection line segment and the corresponding coordinate axis; the types of the two second features in the second feature set are the same as the types of the two first features in the first feature set.

[0200] Among them, the preset plane is the plane where any two coordinate axes in the geographic coordinate system are located. For example, the coordinate axes of the geographic coordinate system include the longitude axis, the latitude axis and the altitude axis, and the corresponding preset planes include: the longitude plane, the latitude plane and the altitude plane.

[0201] Specifically, when the server obtains the second feature set, two second features can be selected from the second feature set, and then the two second features can be connected in the geographic coordinate system according to the position coordinates of the two second features to obtain a line segment between the two second features, and then the line segment is projected onto a preset plane to obtain a second projection line segment. Further, a coordinate axis corresponding to the preset plane is selected to obtain a second projection angle between the coordinate axis and the second projection line segment. For example, if the preset plane is an altitude plane, the coordinate axis corresponding to the altitude plane is the altitude axis, and accordingly, the angle between the first projection line segments of the two first features on the altitude plane and the corresponding altitude axis is the first projection angle; if the preset plane is a latitude plane, the coordinate axis corresponding to the latitude plane is the latitude axis, and accordingly, the angle between the first projection line segments of the two first features on the latitude plane and the corresponding latitude axis is the first projection angle; if the preset plane is a longitude plane, the coordinate axis corresponding to the longitude plane is the longitude axis, and accordingly, the angle between the first projection line segments of the two first features on the longitude plane and the corresponding longitude axis is the first projection angle. It should be noted that the types of the two second features selected here are the same as the types of the two first features selected in the above-mentioned first feature set. For example, if the two first features selected are roads and lamp poles, then the corresponding two second features in the second feature set are also roads and lamp poles.

[0202] S1212. Perform a difference operation on the first projection angle and the second projection angle to obtain a rotation angle of the origin of the laser radar coordinate system.

[0203] Among them, the rotation angle of the origin of the laser radar coordinate system includes: the rotation angle around the longitude, the rotation angle around the latitude, and the rotation angle around the altitude. Specifically, when the base station obtains the first projection angle and the second projection angle based on the above steps, the first projection angle and the second projection angle are further differenced, and the difference angle after the calculation is used as the rotation angle of the calibrated laser radar. When the line segment between the two first features or the line segment between the two second features is projected on the preset planes in their respective coordinate systems, the preset planes of projection are different, and the coordinate axes corresponding to the preset planes are different, which correspond to different rotation angles.

[0204] For example, if the preset plane in the radar coordinate system is the XZ plane, the coordinate axis corresponding to the XZ plane is the Z axis, the preset plane in the geographic coordinate system is the altitude plane, the coordinate axis corresponding to the altitude plane is the altitude axis, and the rotation angle of the origin of the lidar coordinate system is the rotation angle around the latitude; if the preset plane in the radar coordinate system is the YZ plane, the coordinate axis corresponding to the YZ plane is the Y axis, the preset plane in the geographic coordinate system is the latitude plane, the coordinate axis corresponding to the latitude plane is the latitude axis, and the rotation angle of the origin of the lidar coordinate system is the rotation angle around the longitude; if the preset plane in the radar coordinate system is the XY plane, the coordinate axis corresponding to the XY plane is the X axis, the preset plane in the geographic coordinate system is the longitude plane, the coordinate axis corresponding to the longitude plane is the longitude axis, and the rotation angle of the origin of the lidar coordinate system is the rotation angle around the altitude.

[0205] S1213. Obtain a matching result of the position coordinates of the origin of the laser radar coordinate system according to the rotation angle of the origin of the laser radar coordinate system, the first feature set, and the second feature set.

[0206] The position coordinates of the origin of the laser radar coordinate system described in this embodiment include longitude, latitude, and altitude. Specifically, when the server obtains the rotation angle of the origin of the laser radar coordinate system based on the above steps, the rotation angle of the origin of the laser radar coordinate system can be used to correct the position coordinates of the features in the first feature set, and then the corrected first feature set and the second feature set are matched to obtain a set of matched first features and second features, or multiple sets of matched first features and second features, and then the position coordinates of the origin of the laser radar coordinate system are obtained by analyzing the relevant information of the matched first features and second features.

[0207] Further, in one embodiment, a specific implementation of the above S1213 is provided, such as Fig.13 As shown, the method includes:

[0208] S1214. Match each first feature in the first feature set with each second feature in the second feature set to obtain target first features and target second features that belong to the same type.

[0209] Specifically, when the server obtains the first feature set and the second feature set based on the above steps, it can filter out the first feature and the second feature of the same type from the first feature set and the second feature set, and use the filtered out first feature as the target first feature, and use the filtered out second feature as the target second feature. Of course, any type of features can be filtered out during the filtering, as long as the filtered out first feature and the second feature are of the same type. For example, the first feature belonging to the lamp pole type is filtered out from the first feature set, and the second feature belonging to the lamp pole type is also filtered out from the second feature set.

[0210] S1215. Correct the position coordinates of the first feature of the target according to the value of the cosine function of the rotation angle to obtain corrected position coordinates of the first feature of the target.

[0211] This embodiment relates to a specific calculation method for correcting the position coordinates of the first feature of the target. Specifically, the rotation angle can be substituted into the following relationship (1) for calculation to obtain the corrected position coordinates of the first feature of the target:

[0212] A' = A × cos(θ) (1);

[0213] In the above formula, A represents the position coordinate of the first feature of the target, which can represent one of the X coordinate, Y coordinate, and Z coordinate of the first feature of the target; A' represents the corrected position coordinate of the first feature of the target, corresponding to A. θ represents the rotation angle of the origin of the laser radar coordinate system; if A represents the X coordinate, the corresponding θ represents the rotation angle around the altitude, and the corresponding A' represents the corrected X coordinate; if A represents the Y coordinate, the corresponding θ represents the rotation angle around the longitude, and the corresponding A' represents the corrected Y coordinate; if A represents the Z coordinate, the corresponding θ represents the rotation angle around the latitude, and the corresponding A' represents the corrected Z coordinate.

[0214] S1216. Determine the matching result of the position coordinates of the origin of the laser radar coordinate system according to the corrected position coordinates of the first feature of the target and the position coordinates of the second feature of the target.

[0215] Specifically, after the server corrects the position coordinates of the first feature of the target based on the above steps, the method described in S1209 can be used to determine the position coordinates of the origin of the laser radar coordinate system according to the corrected position coordinates of the first feature of the target and the position coordinates of the second feature of the target, thereby obtaining a matching result of the position coordinates of the origin of the laser radar coordinate system. For the specific method, please refer to the description of S1209 above, which will not be repeated here.

[0216] When the position coordinates of the origin of the above-mentioned laser radar coordinate system include longitude, latitude and altitude, when the base station executes the above-mentioned step S1216, the longitude of the origin of the laser radar coordinate system is determined specifically according to the X coordinate in the position coordinates of the first feature of the target after correction and the longitude coordinate in the position coordinates of the second feature of the target; the latitude of the origin of the laser radar coordinate system is determined according to the Y coordinate in the position coordinates of the first feature of the target after correction and the latitude coordinate in the position coordinates of the second feature of the target; the altitude of the origin of the laser radar coordinate system is determined according to the Z coordinate in the position coordinates of the first feature of the target after correction and the altitude coordinate in the position coordinates of the second feature of the target. The methods for determining the above-mentioned longitude, latitude and altitude can be referred to the description of the above-mentioned S1213, which will not be repeated here.

[0217] The above method determines the position coordinates of the origin of the laser radar coordinate system through the corrected position coordinates of the first feature of the target and the position coordinates of the second feature of the target, eliminating the error of the laser radar in obtaining radar point cloud data under non-horizontal scanning conditions, thereby improving the accuracy of subsequent calibration of the laser radar based on the radar point cloud data.

[0218] In practical applications, before the server identifies the target object based on the radar point cloud data, it is necessary to remove the background data belonging to non-road in the radar point cloud data, and then further identify the target object to improve the accuracy of target object identification. However, the current method of removing background data from point cloud data has the problem of low accuracy. To address this problem, the present application provides a method for determining a target region of interest, which is used to accurately determine the target region of interest, so as to improve the accuracy of target object identification performed later on the target region of interest.

[0219] That is, the above S13 is a process for the server to determine the target region of interest. The following embodiment describes the process in detail, as follows: (Note: the server can determine the target region of interest based on the received radar point cloud data, and the base station can also determine the target region of interest based on the received radar point cloud data, and the determination method is the same. After the base station determines the target region of interest, the base station can further identify the feature information of the target object in the target region of interest, and then send the feature information to the server for processing. The following embodiment takes the server determining the target region of interest as an example for explanation)

[0220] In one embodiment, a method for determining a target region of interest is provided, such as Fig.14 As shown, the method includes:

[0221] S1301, obtaining the spatial position of the laser radar according to the registration parameters and the point cloud data collected by the laser radar. The registration parameters are parameters obtained by registering the point cloud data with the first map, and the first map is map data of preset accuracy in point cloud format; the preset accuracy is greater than a preset accuracy threshold.

[0222] The preset accuracy threshold may be determined by the base station according to actual recognition accuracy requirements. The accuracy of the first map described in this embodiment is greater than the preset accuracy threshold. Therefore, when the preset accuracy threshold is high, the first map is high-precision map data. The spatial position of the laser radar represents the spatial position of the laser radar in the map data coordinate system, and the spatial position may include information such as the longitude, latitude, and altitude of the laser radar.

[0223] Specifically, the position coordinates of the laser radar in the point cloud data coordinate system can be first determined, and then the position coordinates of the laser radar in the point cloud data coordinate system can be converted to the map data coordinate system using the alignment parameters obtained by aligning the point cloud data collected by the laser radar with the first map to obtain the spatial position of the laser radar.

[0224] S1302. Determine the scanning range of the laser radar according to the spatial position of the laser radar and the scanning radius of the laser radar.

[0225] The scanning radius of the laser radar can be determined by the base station in advance according to the recognition requirements, or according to the performance of the laser radar. Specifically, when the base station obtains the spatial position of the laser radar, it can use the spatial position as the center and the scanning radius of the laser radar as the radius to determine the scanning range of the laser radar. For example, when the laser radar scans at 360°, the base station can determine the scanning range of a circular area based on the spatial position and scanning radius of the laser radar.

[0226] S1303. Determine a target area of ​​interest according to the scanning range of the laser radar and the target area in the second map; the target area is determined by vector data of the second map; and the second map is map data in vector format.

[0227] Among them, the second map in vector format contains descriptive information of objects such as road sidelines, road centerlines, zebra crossing control locations, zebra crossing types, etc. The base station can obtain map data with an accuracy greater than a preset accuracy threshold from a database or by other means, and then convert the map data into a second map in vector format for subsequent use. It is understood that when converting the map data into a first map in point cloud format and a second map in vector format, the accuracy of the first map and the second map is guaranteed to be the same as the map data. The target area contains vector data representing objects such as roads, zebra crossings, lamp poles, road markers, vehicles, etc. The target area of ​​interest is the area to be identified. Specifically, when the base station obtains the scanning range of the laser radar and the second map based on the above steps, the target area in the second map can be further intersected with the scanning range of the laser radar to obtain a target area of ​​interest containing all vector data in the target area, and the base station can also obtain a target area of ​​interest containing part of the vector data in the target area. It is understood that the base station can select the target area in the second map to customize a suitable target area of ​​interest according to actual recognition requirements.

[0228] In the above-mentioned method for determining the target area, the spatial position of the laser radar is obtained according to the registration parameters and the point cloud data collected by the laser radar, and the scanning range of the laser radar is determined according to the spatial position of the laser radar and the scanning radius of the laser radar, and then the target area of ​​interest is determined according to the scanning range of the laser radar and the target area in the second map. Among them, the registration parameters are parameters obtained by aligning the point cloud data with the first map, the first map is map data of preset accuracy in point cloud format, and the target area with a preset accuracy greater than a preset accuracy threshold is determined by vector data in the second map, and the second map is the map data in vector format. In the above-mentioned method, since the first map is high-precision map data, the scanning range of the laser radar is obtained by aligning the high-precision first map and point cloud data, which can improve the accuracy of the scanning range, and further improve the accuracy of determining the target area of ​​interest according to the scanning range.

[0229] In one embodiment, an implementation of the above S1303 is provided, such as Fig.15 As shown, the above S1303 "determining the target area of ​​interest according to the scanning range of the laser radar and the target area in the second map" includes:

[0230] S1305. Determine a scanning range outline on a second map according to the scanning range of the laser radar.

[0231] When the base station obtains the scanning range of the laser radar, it can further determine the scanning range contour according to the area range corresponding to the scanning range on the second map. Specifically, the contour of the area range corresponding to the scanning range on the second map can be directly determined as the scanning range contour. Optionally, the contour of the area range corresponding to the scanning range on the second map can be corrected first, and then the corrected contour can be determined as the scanning range contour. Optionally, the scanning range of the laser radar can be narrowed down according to the actual geographical environment, and then the scanning range contour can be determined according to the area range corresponding to the scanning range of the laser radar after the narrowing down. For example, in combination with the actual geographical environment, it is found that the scanning range of the laser radar contains an invalid area range, so the invalid area range is removed from the scanning range of the laser radar, that is, the scanning range of the laser radar is narrowed down, and the narrowed scanning range of the laser radar contains the valid area range. The invalid area can be determined according to the actual recognition needs. For example, the invalid area can be an area containing data belonging to objects such as mountains and buildings.

[0232] Optionally, the specific method for determining the scanning range contour may include: taking the spatial position of the laser radar as the center, horizontally projecting the scanning range on the second map to obtain the scanning range contour. That is, firstly projecting the scanning range on the second map horizontally to obtain a contour formed by connecting the farthest points of the projection area, and then determining the contour as the scanning range contour.

[0233] S1306: Perform an intersection operation on the target area and the scanning range contour to obtain a target region of interest.

[0234] Specifically, after the base station determines the target area in the second map, it further directly performs an intersection operation on the target area and the scanning range contour obtained above to obtain the target area of ​​interest. Fig.16 As shown, if the target area includes the road edge a and the edge b of the area occupied by the lamp pole, and the scanning range contour is a circular contour c, then after performing an intersection operation on the road edge a and the edge b of the area occupied by the lamp pole and the scanning range contour c, the target area of ​​interest d can be obtained.

[0235] The above embodiment obtains the target region of interest by performing an intersection operation on the target region and the scanning range contour. Since the target region contains vector data of the target object to be identified, the target region of interest obtained after the intersection operation effectively removes redundant vector data of non-target objects to be identified, thereby realizing the extraction of the target region of interest containing the target object to be identified.

[0236] In one embodiment, another implementation of the above S1306 is provided, such as Fig.17 As shown, the above S1306 "performing an intersection operation on the target area and the scanning range contour to obtain the target region of interest" includes:

[0237] S1307: Select the outline of the area where the target vector data is located from the vector data contained in the target area.

[0238] Among them, the target vector data can be determined according to user needs or identification needs. For example, if it is necessary to identify the roads in the target area, the corresponding target vector data is the vector data representing the roads. Specifically, when the base station determines the outline of the area where the target vector data is located according to the identification needs or user needs, the outline of the area where the target vector data is located is selected from the target area obtained in the second map, so that the target area of ​​interest can be determined based on the outline of the area where the target vector data is located. Optionally, the target vector data may include at least one of vector data representing motor vehicle roads, vector data of pedestrian roads, vector data of roadside markers, and vector data of vehicles.

[0239] S1308, performing an intersection operation on the outline of the area where the target vector data is located and the outline of the scanning range to obtain the target region of interest.

[0240] When the base station obtains the contour of the area where the target vector data is located based on the above steps, it can directly perform an intersection operation on the contour of the area where the target vector data is located and the contour of the scanning range to obtain the target area of ​​interest. Fig.18 As shown, if the contour of the area where the target vector data is located is the road sideline L1, and the scanning range contour is the circular contour L2, then after performing an intersection operation on the road sideline L1 and the scanning range contour L2, the target area of ​​interest L3 can be obtained.

[0241] In the method described in the above embodiment, since the target vector data can be specified by the user, the data processing method provided in this embodiment can set the target area of ​​interest according to user needs, thereby narrowing the recognition range when identifying the target object later, thereby improving the accuracy of identifying the target object.

[0242] In one embodiment, Fig.14 The method described in the embodiment, such as Fig.19 As shown, it also includes:

[0243] S1309. According to the target region of interest, extract the point cloud data within the target region of interest from the point cloud data collected by the laser radar.

[0244] When the base station obtains the target area of ​​interest based on the above implementation, the point cloud data contained in the target area of ​​interest can be extracted from the point cloud data collected by the lidar. Specifically, the base station can use the existing segmentation algorithm to extract the point cloud data in the target area of ​​interest from the point cloud data collected by the lidar.

[0245] S1310 : Identify objects in the target region of interest based on the point cloud data in the target region of interest.

[0246] When the base station obtains the point cloud data in the target region of interest, it can use the existing recognition or analysis algorithm to analyze based on the point cloud data, so as to obtain the relevant attribute information of the objects contained in the target region of interest. Since the target region of interest determined by the method described in the above implementation is relatively accurate, the data contained in the target region of interest is valid, which avoids the interference problem caused by invalid data when the base station identifies the objects in the target region of interest, and improves the accuracy of the base station in identifying objects. At the same time, it also reduces the process of invalid data recognition by the base station during the object recognition process, and improves the efficiency of the base station in identifying objects.

[0247] In actual applications, when the server (information processing platform) identifies the target object in the radar scanning area corresponding to each base station and obtains the characteristic information of the target object, the server usually displays the target object in the radar scanning area corresponding to each base station. However, during the display, there is usually a scanning blind area between the radar scanning areas corresponding to each base station, which causes the server to be unable to effectively obtain the target object in the scanning blind area, so that when the server displays the target objects in the radar scanning areas corresponding to each base station at the same time, there is a problem of discontinuous display. To address this problem, the present application also provides a data acquisition method for perceiving blind areas, which can solve the problem of discontinuous display of characteristic information due to the presence of blank areas. The following embodiment describes the process in detail.

[0248] In one embodiment, a method for acquiring data of a perception blind area is provided, such as Fig. 20 As shown, the method includes: (Note: After the server identifies the target object, it can further process the feature information of the target object to display the features of the target object in the corresponding sensing area of ​​each base station on the display screen, which can be applied in the fields of navigation, automatic driving, etc. The following embodiment takes the server as an example for explanation)

[0249] S1401, determining whether there is a perception blind area between the perception areas corresponding to the base stations in the target area of ​​interest;

[0250] Among them, the perception blind area is the area between the perception areas that the laser radar on each base station cannot scan when scanning the surrounding area. Specifically, the server first obtains the range and position of the perception area corresponding to each base station, and further determines whether there is a scanning blind area between the perception areas of each radar according to the range and position of the perception area corresponding to each base station. If so, the range and position of the scanning blind area are determined as the range and position of the perception blind area. Specifically, the perception area of ​​each base station can be first converted to the same coordinate system using the alignment parameters of each base station, and then it is determined whether there is a perception blind area between the perception areas corresponding to each base station according to the position of each base station in the same coordinate system. Optionally, the alignment parameters of each base station can be obtained by executing steps S1201-S1202 in the above text of this application. For details, please refer to the relevant description above, which will not be repeated here.

[0251] S1402: If there are blank areas between the perception areas corresponding to the base stations, identify feature information of the target object in the perception areas corresponding to the base stations, and generate feature information of the target object in the perception blind area based on the feature information of the target object of each base station.

[0252] The target object refers to an object to be identified, which may be one object to be identified or multiple objects to be identified, which is not limited here. The feature information may represent the size, type, position, moving speed, heading angle, moving direction and other information that can describe the target object. The feature information of the target object in this embodiment represents the feature information of the target object identified by the base station or server based on the point cloud data output by the laser radar.

[0253] When the server has determined the perception blind spots between multiple base stations based on the above steps and obtained the feature information of the target objects of each base station, the server can predict the feature information of the target object in the perception blind spot by analyzing the feature information of the target object in the perception area corresponding to each base station; optionally, the server may first select the feature information of the target object in the perception area that meets the preset conditions, and then predict the feature information of the target object in the perception blind spot by analyzing the feature information of the target object in the perception area that meets the preset conditions; the above preset conditions may be predetermined by the server, for example, the preset condition may be the perception area closest to the perception blind spot, or it may be the perception area containing the moving target object.

[0254] In the above-mentioned data acquisition method for the perception blind area, the server determines whether there is a perception blind area between the perception areas corresponding to each base station. If so, the server predicts the characteristic information of the target object in the perception blind area based on the characteristic information of the target object of each base station. Since the server makes predictions based on the characteristic information of the target object in the perception area corresponding to each base station, and the characteristic information of the target object in the perception area corresponds to the actual scene, the characteristic information of the target object predicted by the above-mentioned method is more consistent with the actual environment information. Compared with the traditional method of only adding static background data in the perception blind area, the data acquisition method for the perception blind area described in this embodiment can achieve a more accurate prediction of the target object.

[0255] In one embodiment, a specific implementation of the above S1402 is provided, such as Fig.21 As shown, the above S1402 "generating characteristic information of the target object in the perception blind area according to the characteristic information of the target object of each base station" includes:

[0256] S1403, extracting feature information of target objects in a target area from feature information of target objects of each base station; the target area is a perception area adjacent to the perception blind area.

[0257] Specifically, when the server obtains feature information of target objects within perception areas corresponding to multiple base stations, and there is a perception blind spot between the perception areas corresponding to these multiple base stations, the server can further determine the perception area adjacent to the perception blind spot, that is, the target area, and then extract the feature information of the target objects within the target area from the feature information of the target objects within the multiple perception areas, so as to subsequently perform prediction based on the feature information of the target objects within the target area.

[0258] S1404, generating feature information of the target object in the perception blind area according to the feature information of the target object in the target area.

[0259] When the server obtains the characteristic information of the target object in the target area based on the above steps, the characteristic information of the target object in the perception blind area can be predicted by analyzing the characteristic information of the target object in the target area. Optionally, the server may first select the characteristic information of the target object in the target area that meets the preset conditions, and then predict the characteristic information of the target object in the perception blind area by analyzing the characteristic information of the target object in the target area that meets the preset conditions; the above preset conditions may be predetermined by the server, for example, the preset conditions may be a target area containing movement. In this embodiment, the target object in the perception blind area is predicted based on the characteristic information of the target object in the target area, and since the target area is a perception area adjacent to the perception blind area, the characteristic information of the target object in the target area is closer to the characteristic information of the target object in the perception blind area, and therefore the accuracy of predicting the characteristic information of the target object in the blank area based on the characteristic information of the target object in the target area is higher.

[0260] Furthermore, in one embodiment, a specific implementation of the above S1404 is provided, such as Fig. 22 As shown, the above S1404 "generating characteristic information of the target object in the perception blind area according to the characteristic information of the target object in the target area" includes:

[0261] S1405, determining whether there is feature information predicted at the last moment for the target object in the perception blind spot; if there is no feature information predicted at the last moment for the target object in the perception blind spot, executing step S1406; if there is feature information predicted at the last moment for the target object in the perception blind spot, executing step S1407.

[0262] Among them, the feature information predicted at the last moment refers to the feature information of the target object sent by multiple base stations or the feature information of the target object identified at the last moment received by the server at the last moment, and when there is a perception blind spot between the perception areas corresponding to the multiple base stations, the server predicts the feature information of the target object in the perception blind spot and obtains the feature information. The step described in this embodiment is a judgment step, which is used to judge whether the feature information predicted at the last moment exists in the perception blind spot of the target object. If the result of the judgment is that the feature information predicted at the last moment does not exist in the perception blind spot of the target object, it means that the server did not predict the target object in the perception blind spot at the last moment, that is, no target object moved into the perception blind spot at the last moment, then the target object at the last moment may be moving towards the perception blind spot, or is already at the boundary of the perception blind spot. Correspondingly, if the result of the judgment is that the feature information predicted at the last moment exists in the perception blind spot of the target object, it means that the server has predicted the target object in the perception blind spot at the last moment, that is, a target object moved into the perception blind spot at the last moment, then the target object at the current moment may still be moving in the perception blind spot, or is about to move out of the perception blind spot. The following steps describe the different operations performed by the server under the above two judgment results.

[0263] S1406: Based on the feature information of the target object in the target area, predict and generate feature information of the target object in the perception blind area at the current moment, and store the feature information.

[0264] This embodiment involves a situation where the server determines that the target object does not have the feature information predicted at the previous moment within the perception blind spot. In this case, after obtaining the feature information of the target object in the target area, the server can directly predict the feature information of the target object in the perception blind spot at the current moment by analyzing the feature information of the target object in the target area, obtain the prediction result, and store the prediction result for use in predicting the feature information of the target object in the perception blind spot at the next moment.

[0265] S1407. Determine whether it is necessary to predict the feature information of the target object in the target area at the current moment in the perception blind spot based on the feature information of the target object in the target area. If it is necessary to predict the feature information of the target object in the perception blind spot at the current moment, execute step S1408. If it is not necessary to predict the feature information of the target object in the perception blind spot at the current moment, execute step S1409.

[0266] This embodiment involves a situation where the server determines that the target object exists in the perception blind spot with the feature information predicted at the previous moment, because in this case it means that the target object at the current moment may still be moving in the perception blind spot, or moving out of the perception blind spot. If the target object is still moving in the perception blind spot, it means that the target object at the current moment is also in the perception blind spot. Then at the current moment, the server needs to continue to predict the feature information of the target object in the perception blind spot. If the target object moves out of the perception blind spot, then at the current moment, there is no need to predict the feature information of the target object in the perception blind spot, because the target object has moved out of the perception blind spot and entered the perception area corresponding to the base station, and does not belong to the perception blind spot. The server can obtain the feature information of the target object through the data reported by the base station.

[0267] S1408. Based on the feature information of the target object predicted at the previous moment, the feature information of the target object in the perception blind spot at the current moment is predicted and stored.

[0268] The server involved in this embodiment needs to predict the characteristic information of the target object in the perception blind spot at the current moment. In this case, the server directly obtains the characteristic information of the target object predicted at the previous moment from the stored information, and then predicts the characteristic information of the target object in the perception blind spot at the current moment by analyzing the characteristic information of the target object predicted at the previous moment, and stores the predicted characteristic information at the same time, so as to be used when predicting the characteristic information of the target object in the perception blind spot at the next moment. For example, if the target object is a vehicle, the server can obtain the speed and driving direction of the vehicle predicted at the previous moment, and then when predicting the driving information of the vehicle at the current moment, the server can use the speed and driving direction as the speed and driving direction of the vehicle predicted at the current moment.

[0269] S1409. Stop prediction.

[0270] The server involved in this embodiment does not need to predict the feature information of the target object in the blank area at the current moment. In this case, the server directly stops the prediction, that is, does not predict the feature information of the target object in the blank area.

[0271] In one embodiment, a specific implementation of the above S1406 is provided, such as Fig.23 As shown, the above S1406 "predicting and generating characteristic information of the target object in the perception blind area at the current moment according to the characteristic information of the target object in the target area" includes:

[0272] S1410. Determine whether there is a target object at the boundary of the perception blind area based on feature information of the target object in the target area; if there is a target object at the boundary of the perception blind area, execute step S1411; if there is no target object at the boundary of the perception blind area, execute step S1412.

[0273] This embodiment involves the situation that the server did not predict the target object in the perception blind spot at the last moment. In this case, it means that the target object at the last moment may be moving towards the perception blind spot, and the corresponding target object at the current moment is not in the perception blind spot, or the target object at the last moment is already at the boundary of the perception blind spot, and the corresponding target object at the current moment has entered the perception blind spot. Because these two situations may exist, the server needs to further determine which situation it is, so as to perform different prediction operations according to different situations. In this embodiment, the server can determine whether the target object at the current moment is in the perception blind spot by judging whether there is a target object at the boundary of the perception blind spot. If there is a target object at the boundary of the perception blind spot, it means that the target object at the current moment is in the perception blind spot. If there is no target object at the boundary of the perception blind spot, it means that the target object at the current moment is not in the perception blind spot.

[0274] S1411. Predicting feature information of the target object within the perception blind area at the current moment based on feature information of the target object at the boundary of the perception blind area.

[0275] This embodiment involves a situation where the server determines that there is a target object at the boundary of a perception blind spot, that is, the target object at the current moment is in the perception blind spot. In this case, the server extracts feature information of the target object at the boundary of the perception blind spot from feature information of the target object in the target area, and then predicts feature information of the target object in the perception blind spot at the current moment based on the extracted feature information.

[0276] S1412, selecting preset background data from the target area and filling it into the perception blind area at the current moment.

[0277] Among them, the background data may be data containing only static data, or may contain other data except the target object. This embodiment involves the situation that the server determines that there is no target object at the boundary of the perception blind area, that is, the target object at the current moment is not in the perception blind area. In this case, the server may first determine the background data connected with the perception blind area from the target area, for example, the corresponding background data in the area formed when the boundary of the perception blind area is extended to the target area. Then, the background data is directly filled into the perception blind area at the current moment, so that even if there is no moving target object in the perception blind area, it can contain valid data.

[0278] The method described in this embodiment can effectively predict the data in the perception blind area regardless of whether the perception blind area contains a moving target object. Therefore, this method is suitable for data prediction in various scenarios and has high applicability.

[0279] In one embodiment, a specific implementation of the above S1407 is provided, such as Fig.24 As shown, the above S1407 "determine whether it is necessary to predict the characteristic information of the target object in the perception blind area at the current moment according to the characteristic information of the target object in the target area" includes:

[0280] S1413. Determine whether a target object corresponding to the feature information predicted at the last moment appears in the target area based on the feature information of the target object in the target area. If a target object corresponding to the feature information predicted at the last moment does not appear in the target area, execute step S1414. If a target object corresponding to the feature information predicted at the last moment appears in the target area, execute step S1415.

[0281] This embodiment involves the situation that the server has predicted the target object in the perception blind area at the last moment. In this case, it means that the target object at the last moment is in the perception blind area, then the target object at the current moment may still move in the perception blind area, or move out of the perception blind area. Because these two situations may exist, the server needs to further determine which situation it is, so as to perform different prediction operations according to different situations. In this embodiment, the server can determine whether the target object at the current moment is still in the perception blind area by judging whether the target object corresponding to the feature information predicted at the last moment appears in the target area. If the target object corresponding to the feature information predicted at the last moment appears in the target area, it means that the target object at the last moment has moved out of the perception blind area at the current moment and entered the perception area corresponding to the base station adjacent to the perception blind area; if the target object corresponding to the feature information predicted at the last moment does not appear in the target area, it means that the target object at the last moment is still moving in the perception blind area at the current moment.

[0282] S1414: Determine the feature information of the target object in the perception blind area at the current moment that needs to be predicted.

[0283] This embodiment involves a situation where the server determines that a target object corresponding to feature information predicted at a previous moment does not appear in the target area. In this case, the server needs to continue predicting feature information of the target object in the perception blind spot at the current moment.

[0284] S1415. Determine that there is no need to predict feature information of the target object within the perception blind spot at the current moment.

[0285] This embodiment involves a situation where the server determines that a target object corresponding to feature information predicted at a previous moment appears in a target area. In this case, the server does not need to predict feature information of the target object in the perception blind area at the current moment.

[0286] The above method implements different operations of the server to predict the feature information in the perception blind area according to different application scenarios, thereby realizing the prediction of the feature information of the target object when the target object is about to move into the perception blind area, the prediction of the feature information of the target object when the target object is moving in the perception blind area, and the prediction of the feature information of the target object when the target object moves out of the perception blind area. Since the trajectory of the target object in the perception blind area in various scenarios is taken into account, the information predicted by the above prediction method is highly accurate.

[0287] In practical applications, when the server (information processing platform) identifies the target object in the sensing area corresponding to each base station and obtains the characteristic information of the target object, the server usually displays the target object in the sensing area corresponding to each base station. However, when displaying, there are usually overlapping areas between the sensing areas corresponding to the base stations, which leads to repeated display of the target object in the later stage, resulting in poor display effect. To address this problem, the present application also provides a data processing method that can solve the problem of repeated display of characteristic information of the target object due to the existence of overlapping areas. The following embodiment describes the process in detail.

[0288] In one embodiment, Fig.25 As shown, a method for obtaining data in an overlapping area is also provided, and the method is applied to Figure 1 The server in the example is used to illustrate. Fig. 20 After step S1401 of embodiment, the method further comprises the steps of:

[0289] S1416: Determine whether there is an overlapping area between the sensing areas corresponding to the base stations in the target area of ​​interest.

[0290] Specifically, the server first obtains the range and position of the perception area corresponding to each base station, and further determines whether there are overlapping or overlapping areas between the perception areas according to the range and position of the perception area corresponding to each base station. If so, the range and position of the overlapping or overlapping area are determined as the range and position of the overlapping area. Specifically, the perception area of ​​each base station can be first converted to the same coordinate system using the alignment parameters of each base station, and then it is determined whether there are overlapping areas between the perception areas corresponding to each base station according to the position of each base station in the same coordinate system. Optionally, the alignment parameters of each base station can be obtained by executing steps S1201-S1202 in the above text of this application. For details, please refer to the relevant description above, which will not be repeated here.

[0291] S1417: If there is an overlapping area between the perception areas corresponding to the base stations, identify the feature information of the target objects in the perception areas corresponding to the base stations, and perform deduplication processing on the target objects in the overlapping area according to the feature information of the target objects sent by the base stations.

[0292] When the server has determined the overlapping area between multiple base stations based on the above steps and obtained the characteristic information of the target object sent by each base station, it can determine whether there are duplicate target objects in the overlapping area by analyzing the characteristic information of the target object in the perception area corresponding to each base station. If there are duplicate target objects, one target object is retained in the overlapping area and the other duplicate target objects are removed.

[0293] In the above-mentioned overlapping area data acquisition method, the server determines whether there is an overlapping area between the sensing areas corresponding to each base station. If so, the server performs deduplication processing on the target objects in the overlapping area according to the characteristic information of the target objects sent by each base station. Since the characteristic information of the target object contains information on various characteristics of the target object, the method of determining repeated target objects in the overlapping area based on the characteristic information of the target object can improve the accuracy of deduplication.

[0294] In one embodiment, a specific implementation of the above S702 is provided, such as Fig.26 As shown, the above S1417 of “de-duplicating the target objects in the overlapping area according to the feature information of the target objects sent by each base station” includes:

[0295] S1418. Extract feature information of the target object in the overlapping area from the feature information of the target object sent by each base station.

[0296] Specifically, when the server obtains feature information of target objects from multiple base stations and there is an overlapping area between the perception areas corresponding to these multiple base stations, the server can further extract the feature information of the target objects in the overlapping area, so as to then determine whether there is a duplicate target object based on the feature information of the target objects in the overlapping area.

[0297] S1419: Detect whether there is a repeated target object in the overlapping area according to the feature information of the target object in the overlapping area through the preset judgment conditions.

[0298] Among them, the preset judgment condition can be determined by the server in advance according to the actual judgment requirements. For example, if the type of the target object is relatively unique, whether the target object belongs to the same type can be used as the preset judgment condition. Specifically, when the server obtains the characteristic information of the target object in the overlapping area based on the above steps, it can further compare or analyze the characteristic information of each target object in the overlapping area to determine whether the characteristic information of each target object can meet the requirements of the preset judgment condition. If there is a target object that can meet the requirements of the preset judgment condition, it is determined that the target object that meets the requirements of the preset judgment condition is a repeated target object. If there is no target object that can meet the requirements of the preset judgment condition, it is determined that there is no repeated target object in the overlapping area.

[0299] S1420: If there are duplicate target objects in the overlapping area, deduplication processing is performed on the target objects in the overlapping area.

[0300] This embodiment relates to a situation where the server determines that there are duplicate target objects in the overlapping area. In this case, the server directly performs a deduplication process on the target objects in the overlapping area.

[0301] Optionally, the characteristic information of the target object may include the center point position of the target object, the type of the target object, and the heading angle of the target object. Different characteristic information may correspond to different methods of detecting whether there are repeated target objects in the overlapping area. The following embodiments exemplify four detection methods.

[0302] The first detection method is: the characteristic information of the target object may include the center point position of the target object, such as Fig. 27 As shown, the above S1419 "detecting whether there are repeated target objects in the overlapping area according to the characteristic information of the target objects in the overlapping area by using the preset determination conditions" includes:

[0303] S1421. Calculate the distance between the center points of any two target objects in the overlapping area.

[0304] When the server obtains the feature information of the target objects in the overlapping area, it can arbitrarily select two target objects as the target objects to be determined, extract the center points of the two target objects from the feature information of the two target objects, and then calculate the distance between the center points of the two target objects.

[0305] S1422. Determine whether the distance is less than a preset distance threshold. If the distance is less than the preset distance threshold, execute step S1423. If the distance is greater than or equal to the preset distance threshold, execute step S1424.

[0306] The preset distance threshold can be determined by the server according to the recognition accuracy. This embodiment involves a judgment step in which the server judges whether the distance between the center points of two target objects is less than the preset distance threshold. If the distance is less than the preset distance threshold, it means that the probability that the two target objects belong to the same target object is very high; if the distance is greater than or equal to the preset distance threshold, it means that the probability that the two target objects belong to the same target object is very low. The server then performs different operations according to different judgment results.

[0307] S1423: Determine that the two target objects are duplicate target objects.

[0308] This embodiment relates to a situation where the server determines that the distance is less than a preset distance threshold. In this situation, the server directly determines that the two target objects are duplicate target objects.

[0309] S1424: Determine that the two target objects are not duplicate target objects.

[0310] This embodiment relates to a case where the server determines that the distance is greater than or equal to a preset distance threshold. In this case, the server directly determines that the two target objects are not duplicate target objects.

[0311] The above method enables the server to directly determine whether two target objects belong to the same target object based on the center point positions of the target objects. The method is simple and practical.

[0312] The second detection method is: the characteristic information of the target object may include the center point position of the target object and the type of the target object, such as Fig.28 As shown, the above S1419 "detecting whether there are repeated target objects in the overlapping area according to the characteristic information of the target objects in the overlapping area by using the preset determination conditions" includes:

[0313] S1425. Calculate the distance between the center points of any two target objects in the overlapping area.

[0314] This step is the same as the content described in the aforementioned step S1421. For details, please refer to the aforementioned instructions and will not be repeated here.

[0315] S1426. Determine whether the distance is less than a preset distance threshold and whether the types of the two target objects are consistent. If the distance is less than the preset distance threshold and the types of the two target objects are consistent, execute step S1427. If the distance and type meet the conditions except "the distance is less than the preset distance threshold and the types of the two target objects are consistent", execute step S1428.

[0316] This embodiment involves a step in which the server determines whether the distance between the center points of two target objects is less than a preset distance threshold and whether the types of the two target objects are consistent. There are four possible application scenarios, namely, the distance is less than the preset distance threshold and the types of the two target objects are consistent; the distance is less than the preset distance threshold and the types of the two target objects are inconsistent; the distance is greater than or equal to the preset distance threshold and the types of the two target objects are consistent; the distance is greater than or equal to the preset distance threshold and the types of the two target objects are inconsistent. The server then performs different operations according to different possible application scenarios. If the distance is less than the preset distance threshold and the types of the two target objects are consistent, it means that the probability that the two target objects belong to the same target object is very high, and it is accurate to judge that the two target objects belong to the same target object at this time; if the distance and type meet the conditions other than "the distance is less than the preset distance threshold and the types of the two target objects are consistent", it means that the probability that the two target objects belong to the same target object is very small, and it is accurate to judge that the two target objects do not belong to the same target object at this time.

[0317] S1427: Determine that the two target objects are duplicate target objects.

[0318] This embodiment relates to a situation where the server determines that the distance is less than a preset distance threshold and the types of the two target objects are the same. In this case, the server directly determines that the two target objects are duplicate target objects.

[0319] S1428. Determine that the two target objects are not duplicate target objects.

[0320] This embodiment involves a situation where the server determines that the distance and type meet conditions other than "the distance is less than a preset distance threshold, and the types of the two target objects are the same". In this case, the server directly determines that the two target objects are not duplicate target objects.

[0321] The above method enables the server to determine whether two target objects belong to the same target object based on the superposition of two conditions: the center point position of the target object and the type of the target object, which is more accurate.

[0322] The third detection method is: the characteristic information of the target object may include the center point position of the target object and the heading angle of the target object, such as Fig.29 As shown, the above S1419 "detecting whether there are repeated target objects in the overlapping area according to the characteristic information of the target objects in the overlapping area by using the preset determination conditions" includes:

[0323] S1429: Calculate the distance between the center points of any two target objects in the overlapping area.

[0324] This step is the same as the content described in the aforementioned step S1421. For details, please refer to the aforementioned instructions and will not be repeated here.

[0325] S1430: Calculate the difference between the heading angles of the two target objects in the overlapping area.

[0326] When the server calculates the distance between the center points of the two target objects based on the above steps, it can further extract the heading angles of the two target objects from the feature information of the two target objects, and then calculate the difference between the heading angles of the two target objects.

[0327] S1431. Determine whether the distance is less than a preset distance threshold and whether the difference is less than a preset difference threshold. If the distance is less than the preset distance threshold and the difference is less than the preset difference threshold, execute step S1432. If the distance and the difference meet the conditions other than "the distance is less than the preset distance threshold and the difference is less than the preset difference threshold", execute step S1433.

[0328] Among them, the preset difference threshold can be determined by the server according to the recognition accuracy. For example, the preset difference threshold can be different angle values ​​such as 5°, 6°, 7°, etc., which are not limited here. This embodiment involves a judgment step in which the server judges whether the distance between the center point positions of two target objects is less than the preset distance threshold, and whether the difference between the heading angles of the two target objects is less than the preset difference threshold. There are four possible application scenarios, namely, the distance is less than the preset distance threshold, and the difference between the heading angles of the two target objects is less than the preset difference threshold; the distance is less than the preset distance threshold, and the difference between the heading angles of the two target objects is greater than or equal to the preset difference threshold; the distance is greater than or equal to the preset distance threshold, and the difference between the heading angles of the two target objects is less than the preset difference threshold; the distance is greater than or equal to the preset distance threshold, and the difference between the heading angles of the two target objects is greater than or equal to the preset difference threshold. The server then performs different operations according to different possible application scenarios. If the distance is less than the preset distance threshold, and the difference is less than the preset difference threshold, it means that the probability that the two target objects belong to the same target object is very high, and it is accurate to judge that the two target objects belong to the same target object; if the distance and the difference meet the conditions except "the distance is less than the preset distance threshold, and the difference is less than the preset difference threshold", it means that the probability that the two target objects belong to the same target object is very small, and it is accurate to judge that the two target objects do not belong to the same target object.

[0329] S1432: Determine that the two target objects are duplicate target objects.

[0330] This embodiment relates to a situation where the server determines that the distance is less than a preset distance threshold and the difference is less than a preset difference threshold. In this case, the server directly determines that the two target objects are duplicate target objects.

[0331] S1433: Determine that the two target objects are not duplicate target objects.

[0332] This embodiment involves a situation where the server determines that the distance and difference meet conditions other than "the distance is less than a preset distance threshold, and whether the difference is less than a preset difference threshold". In this case, the server directly determines that the two target objects are not duplicate target objects.

[0333] The above method enables the server to determine whether two target objects belong to the same target object based on the superposition of two conditions: the center point position of the target object and the heading angle of the target object, which is more accurate.

[0334] The fourth detection method is: the characteristic information of the target object may include the center point position of the target object, the type of the target object and the heading angle of the target object, such as Fig.30 As shown, the above S1419 "detecting whether there are repeated target objects in the overlapping area according to the characteristic information of the target objects in the overlapping area by using the preset determination conditions" includes:

[0335] S1434. Calculate the distance between the center points of any two target objects in the overlapping area.

[0336] This step is the same as the content described in the aforementioned step S1419. For details, please refer to the aforementioned instructions and will not be repeated here.

[0337] S1435: Calculate the difference between the heading angles of the two target objects in the overlapping area.

[0338] This step is the same as the content described in the aforementioned step S1430. For details, please refer to the aforementioned description and will not be repeated here.

[0339] S1436. Determine whether the distance is less than a preset distance threshold, whether the types of the two target objects are consistent, and whether the difference is less than a preset difference threshold. If the distance is less than the preset distance threshold, and the types of the two target objects are consistent and the difference is less than the preset difference threshold, execute step S1437. If the distance, type and difference meet the conditions except "the distance is less than the preset distance threshold, and the types of the two target objects are consistent and the difference is less than the preset difference threshold", execute step S1438.

[0340] This embodiment involves the server determining whether the distance between the center point positions of two target objects is less than a preset distance threshold, whether the difference between the heading angles of the two target objects is less than a preset difference threshold, and whether the types of the two target objects are consistent. There are many possibilities, which are not listed here one by one.

[0341] S1437: Determine that the two target objects are duplicate target objects.

[0342] This embodiment involves a situation where the server determines that the distance is less than a preset distance threshold, and the types of the two target objects are consistent and the difference is less than a preset difference threshold. In this case, the server directly determines that the two target objects are duplicate target objects.

[0343] S1438. Determine that the two target objects are not duplicate target objects.

[0344] This embodiment involves a situation where the server determines that the conditions other than "the distance is less than a preset distance threshold, and the types of the two target objects are consistent and the difference is less than a preset difference threshold" are other than the situation where the server directly determines that the two target objects are not duplicate target objects.

[0345] The above method enables the server to determine whether two target objects belong to the same target object based on the superposition of three conditions: the center point position of the target object, the type of the target object, and the heading angle of the target object, which is more accurate.

[0346] In one embodiment, a data processing method is also provided. Fig.31 As shown, based on Fig. 20 and Fig.25 The method described in the embodiment, after step S1404, the method further includes:

[0347] S1439. Display characteristic information of target objects in the perception area and perception blind area corresponding to each base station.

[0348] When the server is based on Fig. 20 and Fig.25The method described in the embodiment obtains the characteristic information of the target objects in the perception area corresponding to each base station, and deduplicates the target objects in the overlapping area according to the characteristic information of the target objects in the perception area corresponding to each base station, or predicts the characteristic information of the target objects in the perception blind area according to the characteristic information of the target objects in the perception area corresponding to each base station. The method described in this embodiment can further display the characteristic information of the target objects detected by the base station after deduplication and the predicted characteristic information in the perception blind area in one screen. It should be noted that the frequency of the server displaying the screen may be the same as the frequency of the laser radar data acquisition corresponding to the base station, or it may be different. For example, the frequency of the laser radar data acquisition is 10Hz / s, and the frequency of the server displaying the screen may also be 10Hz / s.

[0349] In the above method, since deduplication processing has been performed, the problem of repeated display of target objects due to overlapping radar scanning areas does not exist in the final displayed image. Moreover, since the characteristic information of the target object predicted by the server is displayed in the perception blind area, there is no discontinuity problem in the final displayed image, thereby improving the effect of image display.

[0350] In one embodiment, the present application also provides a target detection method, such as Fig.32 As shown, the method includes:

[0351] S1601, obtain the point cloud data of the laser radar and the corresponding vector data of the high-precision map.

[0352] Among them, the point cloud data of the laser radar refers to the data of the target object information recorded in the form of points through the laser radar scanning, and each point cloud data contains three-dimensional coordinates. High-precision map refers to an electronic map with higher precision and more data dimensions. The higher precision is reflected in the accuracy to the centimeter level, and the data dimension is more reflected in the fact that it includes surrounding static information related to traffic in addition to road information. The vector data of the high-precision map refers to the storage of a large amount of driving assistance information as structured data. This information can be divided into two categories. One is road data, such as lane information such as the location, type, width, slope and curvature of the lane line, and the other is fixed object information around the lane, such as traffic signs, traffic lights, lane height limits, sewer openings, obstacles and other road details.

[0353] Specifically, the server first obtains the point cloud data of the laser radar and the corresponding vector data of the high-precision map. Optionally, the server can obtain the point cloud data of the laser radar from the laser radar installed in the target area. Optionally, the server can obtain the high-precision map data of the target area from the high-precision map storage. Optionally, the vector data of the high-precision map data includes at least one of the road sideline, the road centerline, the road direction line and the zebra crossing. Optionally, the target area can be an intersection or a road on which the vehicle is traveling. Optionally, the laser radar can include an 8-line laser radar, a 16-line laser radar, a 24-line laser radar, a 32-line laser radar, a 64-line laser radar, a 128-line laser radar, and the like.

[0354] S1602: Use the calibration parameters of the laser radar to convert the coordinates of the point cloud data into the coordinate system of the high-precision map to obtain the point cloud data to be detected.

[0355] Among them, the calibration parameters of the laser radar include the longitude, latitude, altitude, rotation angle around longitude, rotation angle around latitude, and rotation angle around altitude of the origin of the laser radar coordinate system. Specifically, the server uses the calibration parameters of the laser radar to convert the coordinates of the point cloud data to the coordinate system of the high-precision map to obtain the point cloud data to be detected. Optionally, the server can use the calibration parameters of the laser radar to convert the origin coordinates of the laser radar to the coordinate system of the high-precision map, and then convert the coordinates of the point cloud data to the coordinate system of the high-precision map according to the corresponding coordinates of the origin coordinates of the laser radar in the coordinate system of the high-precision map to obtain the point cloud data to be detected.

[0356] S1603, performing target detection on the point cloud data to be detected to obtain a target detection result.

[0357] Specifically, the server performs target detection on the point cloud data to be detected obtained above to obtain a target detection result. Optionally, the server may use a preset roadside sensing detection algorithm to perform target detection on the point cloud data to be detected to obtain a target detection result. Optionally, the target object may be a car or a pedestrian. Optionally, the target detection result may include the position of the target object, the type of the target object, and the heading angle of the target object.

[0358] S1604: Determine whether there is any abnormality in the target detection result based on the vector data and traffic rules.

[0359] Specifically, the server determines whether there is an abnormality in the above target detection result based on the vector data and traffic rules of the high-precision map. Among them, the vector data of the high-precision map represents the road information in the target area. Optionally, the vector data of the high-precision map data includes at least one of the road sideline, the road centerline, the road direction line and the zebra crossing. It is understandable that due to the inaccurate ranging of the laser radar equipment, the laser radar data is seriously blocked by moving objects, and the laser radar data of the target far away from the laser radar is small, which will cause the roadside perception algorithm to have inaccurate detection of the laser radar data. Therefore, it is necessary to correct the target detection result. Exemplarily, if the target detection result is that the car is on the sideline of the road, and the vector data of the high-precision map data is that the car is in the middle of the road, the server will determine that the car should be located in the middle of the road based on the vector data and traffic rules of the high-precision map data, and the server determines that the target detection result is abnormal.

[0360] S1605: If the target detection result is abnormal, the target detection result is corrected using the vector data.

[0361] Specifically, if the server determines that the target detection result is abnormal, the vector data of the high-precision map is used to correct the target detection result. Continuing with the example that the target detection result is that the car is on the sideline of the road, and the vector data of the high-precision map data is that the car is in the middle of the road, the process of the server correcting the target detection result using the high-precision map data is to correct the car to the middle of the road.

[0362] In the above target detection method, the coordinates of the laser radar point cloud data can be converted into the coordinate system of the high-precision map by using the external parameters of the laser radar to obtain the point cloud data to be detected, so that target detection can be performed on the point cloud data to be detected to obtain the target detection result, and then the vector data of the high-precision map data and the traffic rules can be used to judge whether there is an abnormality in the target detection result. If there is an abnormality in the target detection result, the vector data of the high-precision map data can be used to correct the target detection result. Since the vector data of the high-precision map data represents the road information in the target area of ​​the laser radar point cloud data, the target detection result can be accurately corrected according to the vector data of the high-precision map data, thereby improving the accuracy of the corrected result.

[0363] In the above scenario of using the vector data of the high-precision map data to correct the target detection result, the target detection result includes the position of the target object. Fig.33 As shown, the above S1605 includes:

[0364] S1606: Determine the road position based on the vector data.

[0365] Specifically, the server determines the road position according to the vector data of the high-precision map data. Optionally, the server may determine the road position according to at least one of a road sideline, a road centerline, a road direction line, and a zebra crossing in the vector data of the high-precision map data. For example, the server may determine the road position according to the road direction line in the vector data of the high-precision map data.

[0366] S1607: Determine whether the target object is on the road according to the position of the target object.

[0367] Specifically, the server determines whether the target object is at the road position according to the position of the target object. Optionally, the server may compare the position of the target object with the road position to determine whether the target object is at the road position. For example, if the position of the target object is in the grass beside the road, the server determines that the target object is not at the road position.

[0368] S1608: If not, the position of the target object is corrected to the road position to obtain a corrected target detection result.

[0369] Specifically, if the server determines that the target object is not on the road, the server corrects the target object to the road to obtain a corrected target detection result. Optionally, the server can translate the target object to the road to obtain a corrected target detection result, or directly drag the target object in the roadside perception result to the road to obtain a corrected target detection result.

[0370] In this embodiment, the server can accurately determine the road position based on the vector data of the high-precision map data, and then can accurately judge whether the target object is at the road position based on the position of the target object. Therefore, the position of the target object can be accurately corrected to the road position based on whether the target object is at the road position, thereby obtaining a corrected target detection result, thereby improving the accuracy of the corrected target detection result.

[0371] In the above scenario of using the vector data of the high-precision map data to correct the target detection result, the target detection result includes the location of the target object and the type of the target object. Fig.34 As shown, the above S1605 includes:

[0372] S1609: Determine the road position based on the vector data.

[0373] Specifically, the server determines the road position according to the vector data of the high-precision map data. Optionally, the server may determine the road position according to at least one of a road sideline, a road centerline, a road direction line, and a zebra crossing in the vector data of the high-precision map data. For example, the server may determine the road position according to the road centerline in the vector data of the high-precision map data.

[0374] S1610: Determine the road type of the road where the target object is currently located according to the position of the target object and the road position.

[0375] Specifically, the server determines the road type of the road where the target object is currently located according to the position of the target object and the road position determined above. For example, if the target object is a car, the position of the target object is on the road, and the road position is the center line of the road, the server determines that the road type of the road where the target object is currently located is a motor vehicle lane.

[0376] S1611, determining a target road type corresponding to the target object according to a correspondence between the object type and the road type.

[0377] Specifically, the server determines the target road type corresponding to the target object according to the correspondence between the object type and the road type. Exemplarily, the correspondence between the object type and the road may be: if the object type is a car, the road type is a motor vehicle lane; if the object type is a pedestrian, the road type is a non-motor vehicle lane. Then, accordingly, if the target object is a car, the target road type corresponding to the target object determined by the server is a motor vehicle lane.

[0378] S1612, if the road type of the target object's current road is inconsistent with the target road type, the type of the target object is corrected to a type that matches the road type, and a corrected target detection result is obtained.

[0379] Specifically, if the server determines that the road type of the target object's current road is inconsistent with the target road type, the target object's type is corrected to match the road type of the target object's current road, and a corrected target detection result is obtained. Exemplarily, if the road type of the target object's current road is a non-motorized vehicle lane, the target road type is a motor vehicle lane, and the road type of the target object's current road is inconsistent with the target road type, the server corrects the target object's type to match the non-motorized vehicle lane, and a corrected target detection result is obtained.

[0380] In this embodiment, the server can accurately determine the road position based on the vector data of the high-precision map data, and can accurately determine the road type of the road where the target object is currently located based on the position of the target object and the road position determined above, so that the target road type corresponding to the target object can be accurately determined based on the correspondence between the object type and the road type. In this way, if the road type of the road where the target object is currently located is inconsistent with the target road type, the server can correct the type of the target object to a type that matches the road type, and accurately obtain the corrected target detection result, thereby improving the accuracy of the corrected target detection result.

[0381] In the above scenario of using the vector data of the high-precision map data to correct the target detection result, the roadside perception result includes the heading angle of the target object. Fig.35 As shown, the above S1605 includes:

[0382] S1613, based on the vector data of the high-precision map data, obtain the number of times the heading angle of the target object is greater than a preset threshold within a preset number of frames.

[0383] Specifically, the server obtains the number of times the heading angle of the target object is greater than a preset threshold within a preset number of frames based on the vector data of the high-precision map data. Optionally, the preset number of frames may be ten frames, the preset threshold may be 45 degrees, and the number of times the heading angle of the target object is greater than the preset threshold may be two or more times.

[0384] S1614, determining whether the number of times that the heading angle of the target object is greater than a preset threshold within a preset number of frames is greater than a preset number threshold.

[0385] Specifically, the server determines whether the number of times the heading angle of the target object is greater than the preset threshold within the preset number of frames is greater than the preset number threshold. For example, if the preset number threshold is three times, and the number of times the heading angle of the target object is greater than the preset threshold within the preset number of frames is four times, then the server determines that the number of times the heading angle of the target object is greater than the preset threshold within the preset number of frames is greater than the preset number threshold.

[0386] S1615: If yes, the heading angle of the target object is corrected to obtain a corrected target detection result.

[0387] Specifically, if the number of times the heading angle of the target object is greater than a preset threshold within a preset number of frames is greater than a preset number threshold, the server corrects the heading angle of the target object to obtain a correction result. Optionally, the server can correct the heading angle of the target object to a preset threshold to obtain a correction result.

[0388] In this embodiment, the server can accurately obtain the number of times the heading angle of the target object is greater than a preset threshold within a preset number of frames based on the vector data of the high-precision map data, and can then accurately determine whether the number of times the heading angle of the target object is greater than the preset threshold within the preset number of frames is greater than the preset number threshold; if the number of times the heading angle of the target object is greater than the preset threshold within the preset number of frames, the heading angle of the target object can be accurately corrected to obtain an accurately corrected target detection result, thereby improving the accuracy of the corrected target detection result.

[0389] In the above-mentioned scenario where the coordinates of the point cloud data are converted into the coordinate system of the high-precision map using the external parameters of the laser radar to obtain the point cloud data to be detected, in one embodiment, the above-mentioned method also includes: aligning the point cloud data of the laser radar according to the point cloud data of the high-precision map to obtain the aligned point cloud data.

[0390] Specifically, the server registers the point cloud data of the laser radar according to the point cloud data of the high-precision map to obtain the registered point cloud data. Optionally, the server can register the point cloud data of the laser radar with the point cloud data of the high-precision map to obtain the registration parameters, and according to the registration parameters, convert the point cloud data of the laser radar to the coordinate system corresponding to the point cloud data of the high-precision map to obtain the registered point cloud data. Furthermore, after obtaining the registered point cloud data, the server can use the calibration parameters of the laser radar to convert the coordinates of the registered point cloud data to the coordinate system of the high-precision map to obtain the point cloud data to be detected.

[0391] In this embodiment, the server can align the point cloud data of the lidar based on the point cloud data of the high-precision map to obtain the aligned point cloud data, and then use the calibration parameters of the lidar to convert the coordinates of the aligned point cloud data to the coordinate system of the high-precision map to obtain the point cloud data to be detected, thereby improving the accuracy of the point cloud data to be detected.

[0392] In one embodiment, the present application also provides a method for monitoring laser radar positioning. This embodiment uses the method applied to a computer device as an example. It is understandable that the method can also be applied to a server, and can also be applied to a system including a roadside radar and a server, and is implemented through the interaction between the roadside radar and the server. Fig.36 As shown, the method comprises the following steps:

[0393] S1701. Collect real-time point cloud data of a roadside radar in real time, and obtain first spatial information between a real-time target and a standard target based on the real-time point cloud data and the standard point cloud data.

[0394] The standard point cloud data is the point cloud data obtained by using a high-precision map. The real-time target is the target object determined based on the real-time point cloud data, and the standard target is the target object determined based on the standard point cloud data.

[0395] In this embodiment, the roadside radar may be a laser radar.

[0396] Among them, real-time point cloud data includes the absolute position of each static target in the roadside radar coverage area collected when the roadside radar is used in real time. Standard point cloud data includes a high-precision map of the lane level corresponding to the roadside radar coverage area saved in point cloud format in advance. The high-precision map in point cloud format records the absolute position of each static target object on the actual road surface. Real-time targets and standard targets are used to refer to static target objects in the coverage area. Static target objects include road sidelines, roadside markers, trees, lamp poles, etc.

[0397] Optionally, the first spatial information can be used to characterize the positional relationship between the real-time target and the standard target when the roadside radar is used in real time, such as at least one of the offset angle of the real-time target relative to the standard target, the offset direction of the real-time target relative to the standard target, and the offset distance of the real-time target relative to the standard target.

[0398] Specifically, the computer device obtains real-time point cloud data collected by the roadside radar in real time, performs feature recognition on the real-time point cloud data to obtain a real-time target, and performs feature recognition on the pre-stored standard point cloud data to obtain a standard target, and matches to obtain the first spatial information between the real-time target and the standard target referring to the same static target object.

[0399] S1702: Compare the first spatial information with the initially obtained second spatial information.

[0400] The second spatial information is spatial information between an initial target and a standard target obtained based on initial point cloud data and standard point cloud data of the roadside radar initially collected.

[0401] The initial point cloud data includes the distance information of each static target object in the coverage area of ​​the roadside radar relative to the roadside radar itself, which is collected when the roadside radar is used for the first time. The initial target is a target object determined according to the standard point cloud data, and in this embodiment, it is used to refer to the static target object in the coverage area.

[0402] Optionally, the second spatial information can be used to characterize the positional relationship between the initial target and the standard target when the roadside radar is used for the first time, such as at least one of the offset angle of the initial target relative to the standard target, the offset direction of the initial target relative to the standard target, and the offset distance of the initial target relative to the standard target.

[0403] The first spatial information and the second spatial information include the same type of information. For example, if the first spatial information includes the offset angle of the real-time target relative to the standard target, the second spatial information also includes the offset angle of the initial target relative to the standard target.

[0404] S1703: Determine whether the roadside radar has positioning abnormality according to a comparison result between the first spatial information and the second spatial information.

[0405] Specifically, the computer device compares the first spatial information between the real-time target and the standard target obtained in real-time use with the second spatial information between the initial target and the standard target obtained by the roadside radar when it is used for the first time, and determines based on the comparison results whether the positioning of the roadside radar changes with the increase in usage time, resulting in positioning abnormalities.

[0406] In this embodiment, the computer device takes the standard point cloud data as the fundamental basis, obtains the first spatial information between the real-time target and the standard target according to the real-time point cloud data and the standard point cloud data obtained by real-time collection, and obtains the second spatial information between the initial target and the standard target according to the initial point cloud data and the standard point cloud data obtained by initial collection, compares the first spatial information and the second spatial information, and determines whether the real-time positioning of the roadside radar has changed relative to the initial positioning according to the comparison result, so as to realize the real-time detection of the positioning effect of the roadside radar, timely discover whether the positioning of the roadside radar is abnormal, and improve the efficiency of the roadside radar positioning monitoring.

[0407] In one embodiment, before real-time positioning monitoring of the roadside radar is performed, the second spatial information of the roadside radar when it is used for the first time needs to be obtained in advance, such as Fig.37 As shown, before S1701, the roadside radar positioning monitoring method further includes:

[0408] S1704, obtaining initial point cloud data, performing feature recognition on the initial point cloud data, obtaining initial targets, and obtaining relative positional relationships between the initial targets.

[0409] S1705. Perform feature recognition on the standard point cloud data to obtain a standard target.

[0410] Specifically, the computer device obtains the initial point cloud data in the coverage area collected by the roadside radar when it is used for the first time, performs feature recognition on the initial point cloud data to obtain the initial target, determines the relative position relationship between the initial targets according to the position of the geometric center of each initial target relative to the roadside radar, and performs feature recognition on the pre-stored standard point cloud data of the same coverage area to obtain the standard target.

[0411] S1706: Perform feature matching on the initial target and the standard target to obtain a corresponding relationship between the matched initial target and the standard target.

[0412] S1707: Obtain the absolute position of the standard target that matches the roadside radar origin in the initial target, and obtain the absolute position of the initial target based on the relative position relationship between the initial targets.

[0413] The roadside radar origin is the location where the roadside radar is set. The initial target includes the roadside radar origin. The absolute position includes absolute position coordinates, such as longitude and latitude coordinates, and may also include altitude, east-west rotation, north-south rotation, or vertical rotation.

[0414] In this embodiment, the above absolute position coordinates are the absolute position coordinates of the center point of the static target.

[0415] Specifically, the computer device performs feature matching on the initial target and the standard target to obtain the matched initial target and the standard target, as well as the corresponding relationship between the matched initial target and the standard target, and obtains the absolute position of the standard target that matches the origin of the roadside radar in the initial target. Fig.38 is the initial target obtained according to the initial point cloud map, M is the origin of the roadside radar, m is the remaining initial target except the origin M of the roadside radar, and each initial target m is at a distance l from the origin M of the roadside radar, and an offset angle α relative to the origin M of the roadside radar. After the computer device performs feature matching on the initial target and the standard target, it obtains the absolute position of the standard target matched with the origin of the roadside radar, such as the longitude and latitude coordinates. The computer device then obtains the absolute position of each initial target m based on the distance l and the offset angle α of each initial target m from the origin M of the roadside radar.

[0416] S1708. Obtain second spatial information between the matched initial target and the standard target according to the absolute position of the initial target and the absolute position of the standard target that matches the initial target.

[0417] Specifically, the computer device obtains the distance between the absolute positions of the matched initial target and the standard target as the second spatial information.

[0418] When the absolute position of the initial target is the longitude and latitude coordinates, the second spatial information between the initial target and the standard target is the distance between the longitude and latitude coordinates of the initial target and the longitude and latitude coordinates of the corresponding standard target.

[0419] In this embodiment, when the roadside radar is used for the first time, the computer device performs feature recognition on the collected initial point cloud data and the pre-stored standard point cloud data, obtains the initial target and the standard target respectively, uses feature matching to obtain the corresponding relationship between the matched initial target and the standard target, and the absolute position of the origin of the roadside radar in the initial target, and combines the relative position relationship between the initial targets to obtain the absolute position of each initial target, so that when the roadside radar is used for the first time, the second spatial information between the initial target and the standard target is determined by the absolute position of the matched initial target and the standard target. The first-time used roadside radar is accurately positioned, and the second spatial information can accurately reflect the difference between the roadside radar and the standard target when the positioning is accurate. This difference can be used as a reference standard to effectively monitor whether the roadside radar is abnormally positioned in subsequent real-time positioning, thereby improving the accuracy of positioning monitoring.

[0420] In one embodiment, when real-time positioning monitoring of a roadside radar is performed, the first spatial information needs to be obtained based on the real-time point cloud data collected by the roadside radar, such as Fig.39 As shown, S1701 includes:

[0421] S1709, obtain real-time point cloud data, perform feature recognition on the real-time point cloud data, obtain real-time targets, and obtain the relative position relationship between real-time targets. Specifically, the roadside radar can take its own position as the center and perform a 360° scan of the surrounding area to form a coverage area corresponding to the roadside radar, and collect real-time point cloud data of the coverage area. The computer device obtains the real-time point cloud data in the coverage area collected by the roadside radar when it is used in real time, performs feature recognition on the real-time point cloud data, obtains real-time targets, and determines the relative position relationship between real-time targets based on the position of the geometric center of each real-time target relative to the roadside radar.

[0422] S1710, obtaining the absolute position of the standard target that matches the roadside radar origin in the real-time target, and obtaining the absolute position of the real-time target based on the relative position relationship between the real-time targets.

[0423] Specifically, the computer device obtains the absolute position of the standard target that matches the roadside radar origin in the real-time target, and obtains the absolute position of each real-time target in combination with the relative position relationship between the real-time targets.

[0424] S1711. According to the correspondence between the matched initial target and the standard target, the absolute position of the standard target that matches the real-time target is obtained.

[0425] Among them, the real-time target corresponds one-to-one with the initial target and the static target referred to by the standard target.

[0426] S1712: Obtain first spatial information between the matched real-time object and the standard object according to the absolute position of the real-time object and the absolute position of the standard object that matches the real-time object.

[0427] Specifically, the computer device obtains the absolute position of the standard target that matches the real-time target based on the correspondence between the matched initial target and the standard target, combined with the one-to-one correspondence between the real-time target and the initial target, and obtains the distance between the absolute positions of the matched real-time target and the standard target as the first spatial information.

[0428] Among them, the second spatial information is the distance between the longitude and latitude coordinates of the initial target and the corresponding matching standard target, and the first spatial information is the distance between the longitude and latitude coordinates of the real-time target and the corresponding matching standard target.

[0429] In this embodiment, after the roadside radar is used for the first time, the computer device performs feature recognition on the collected real-time point cloud data to obtain the real-time target, and determines the absolute position of the origin of the roadside radar in the real-time target based on the corresponding relationship between the initial target and the standard target, and obtains the absolute position of each real-time target in combination with the relative position relationship between the real-time targets. In the subsequent use of the roadside radar, the first spatial information between the target and the standard target is determined by the absolute position of the matched real-time target and the standard target. The first spatial information can reflect the real-time difference in spatial position between the real-time target and the standard target obtained in real time, so as to accurately monitor the real-time positioning of the roadside radar.

[0430] In one embodiment, by comparing the second spatial information obtained when the roadside radar is used for the first time with the first spatial information obtained by using the roadside radar in real time after the first use, it is determined whether the roadside radar has positioned abnormally, such as Fig.40 As shown, S1703 includes:

[0431] S1713: Obtain a difference between the second spatial information and the first spatial information.

[0432] S1714. Determine whether the roadside radar has positioning abnormality based on the difference.

[0433] Specifically, the computer device obtains the difference between the second spatial information and the first spatial information of the same static target, and can judge whether the roadside radar has positioning abnormality according to whether the difference is greater than a preset difference. If the obtained difference is greater than the preset difference, the roadside radar has positioning abnormality; if the obtained difference is less than or equal to the preset difference, the roadside radar has positioning normal.

[0434] Optionally, the computer device may obtain an average value or a maximum value of a difference between the second spatial information and the first spatial information corresponding to the static target, and determine whether the roadside radar positioning is abnormal based on whether the average value or the maximum value of the difference is greater than a preset difference.

[0435] In this embodiment, the computer device obtains the second spatial information between the initial target and the standard target obtained when the roadside radar is used for the first time, and the difference between the first spatial information between the real-time target and the standard target obtained in the real-time use of the roadside radar after the first use, and quantifies the positioning changes of the roadside radar during the first use and subsequent real-time use through the difference to improve the accuracy of the roadside radar positioning monitoring.

[0436] In one embodiment, in order to further improve the accuracy of roadside radar positioning monitoring, Fig.41 As shown, S1714 includes:

[0437] S1715. Obtain a ratio of the difference value to the second spatial information.

[0438] S1716: Determine whether the ratio meets a preset range.

[0439] If so, it is determined that the roadside radar positioning is normal.

[0440] If not, it is determined that the roadside radar positioning is abnormal.

[0441] Specifically, the computer device determines whether the roadside radar has abnormal positioning by obtaining the ratio of the above difference to the second spatial information and judging whether the ratio meets the preset range. For example, the second spatial information is the initial distance between the initial target and the standard target obtained when the roadside radar is used for the first time, and the first spatial information is the real-time distance between the real-time target and the standard target obtained when the roadside radar is used in real time later. The difference between the first spatial information and the second spatial information is the distance deviation between the initial distance and the real-time distance. The roadside radar compares the distance deviation with the initial distance to judge whether the ratio of the distance deviation to the initial distance meets the preset range of 2%. If the obtained ratio is within the preset range of 2%, that is, less than or equal to 2%, it is determined that the roadside radar positioning is normal; if the obtained ratio exceeds the preset range of 2%, that is, greater than 2%, it is determined that the roadside radar positioning is abnormal.

[0442] In this embodiment, the computer device further obtains the ratio of the difference between the first spatial information and the second spatial information and the second spatial information, and determines whether the roadside radar has a positioning abnormality caused by problems such as abnormal ranging, slow speed or point loss by judging whether the ratio meets a preset range. The applicability of the entire positioning monitoring method can be improved by judging the ratio, and the accuracy of the roadside radar positioning monitoring can be further improved.

[0443] In one embodiment, after determining that the roadside radar positioning is abnormal, the roadside radar positioning monitoring method further includes:

[0444] If the roadside radar positioning is abnormal, an abnormal alarm command is sent to the control platform.

[0445] Among them, the abnormal alarm instruction includes the radar number of the roadside radar that locates the abnormality.

[0446] Specifically, if the roadside radar positioning is abnormal, its own radar number is obtained, abnormal alarm information including its own radar number is generated, and the abnormal alarm information is sent to the control platform.

[0447] In this embodiment, after determining that the roadside radar positioning is abnormal, the computer equipment further sends abnormal alarm information to the control platform, so that relevant staff can promptly know the number of the roadside radar with abnormal positioning through the control platform, which is convenient for targeted maintenance of the roadside radar with abnormal positioning, thereby improving the maintenance efficiency of the roadside radar.

[0448] It should be understood that although Figure 2-41 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2-41 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0449] In one embodiment, Fig.42 As shown, a laser radar calibration device is provided, comprising: a first acquisition module 11, a second acquisition module 12 and a matching module 13, wherein:

[0450] The first acquisition module 11 is used to acquire radar point cloud data of the laser radar within a preset scanning range;

[0451] The second acquisition module 12 is used to acquire the map point cloud data of the to-be-matched area corresponding to the preset scanning range from the map point cloud data of the preset scanning range; the accuracy of the map point cloud data is greater than a preset accuracy threshold;

[0452] The matching module 13 is used to match the map point cloud data of the area to be matched with the radar point cloud data to obtain the calibration parameters of the laser radar; the map point cloud data of the area to be matched and the radar point cloud data within the preset scanning range contain the same object to be matched; the calibration parameters include the longitude, latitude, altitude, rotation angle around longitude, rotation angle around latitude, and rotation angle around altitude of the origin of the laser radar coordinate system.

[0453] For the specific definition of the laser radar calibration device, please refer to the definition of the laser radar calibration method above, which will not be repeated here. Each module in the above laser radar calibration device can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0454] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.43 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a laser radar calibration method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0455] Those skilled in the art will understand that Fig.43 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0456] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0457] Obtain radar point cloud data within the preset scanning range of the laser radar;

[0458] From the map point cloud data of the preset scanning range, obtaining the map point cloud data of the to-be-matched area corresponding to the preset scanning range; the accuracy of the map point cloud data is greater than a preset accuracy threshold;

[0459] The map point cloud data of the area to be matched and the radar point cloud data are matched to obtain the calibration parameters of the laser radar; the map point cloud data of the area to be matched and the radar point cloud data within the preset scanning range contain the same object to be matched; the calibration parameters include the longitude, latitude, altitude, rotation angle around longitude, rotation angle around latitude, and rotation angle around altitude of the origin of the laser radar coordinate system.

[0460] The above embodiment provides a computer device, whose implementation principle and technical effect are similar to those of the above method embodiment, and will not be repeated here.

[0461] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are further implemented:

[0462] Obtain radar point cloud data within the preset scanning range of the laser radar;

[0463] From the map point cloud data of the preset scanning range, obtaining the map point cloud data of the to-be-matched area corresponding to the preset scanning range; the accuracy of the map point cloud data is greater than a preset accuracy threshold;

[0464] The map point cloud data of the area to be matched and the radar point cloud data are matched to obtain the calibration parameters of the laser radar; the map point cloud data of the area to be matched and the radar point cloud data within the preset scanning range contain the same object to be matched; the calibration parameters include the longitude, latitude, altitude, rotation angle around longitude, rotation angle around latitude, and rotation angle around altitude of the origin of the laser radar coordinate system.

[0465] The above embodiment provides a computer-readable storage medium, whose implementation principle and technical effect are similar to those of the above method embodiment, and will not be repeated here.

[0466] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the embodiments of the present disclosure can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0467] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0468] The above-described embodiments only express several implementation methods of the embodiments of the present disclosure, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the embodiments of the present disclosure, and these all belong to the protection scope of the embodiments of the present disclosure. Therefore, the protection scope of the patent of the embodiments of the present disclosure shall be subject to the attached claims.

Claims

1. A laser radar calibration method, characterized in that: The method comprises: Obtain radar point cloud data within the preset scanning range of the laser radar; From the map point cloud data of the preset scanning range, obtaining the map point cloud data of the to-be-matched area corresponding to the preset scanning range; the accuracy of the map point cloud data is greater than a preset accuracy threshold; The features in the map point cloud data of the area to be matched and the features in the radar point cloud data are matched using original calibration parameters, and the original calibration parameters are adjusted according to the matching results, and the original calibration parameters corresponding to the matching results that meet the preset standards are determined as calibration parameters of the laser radar; the map point cloud data of the area to be matched and the radar point cloud data within the preset scanning range contain the same object to be matched; the calibration parameters include the longitude, latitude, altitude of the origin of the laser radar coordinate system and the rotation angle of the origin of the laser radar coordinate system, and the rotation angle includes the rotation angle around the longitude, the rotation angle around the latitude, and the rotation angle around the altitude; the rotation angle is determined by a first projection angle and a second projection angle, the first projection angle is the angle formed by a first projection line segment between two first features in the first feature set on a preset plane in the radar coordinate system, and the second projection angle is the angle formed by a second projection line segment between two second features in the second feature set on a preset plane in the geographic coordinate system, the first feature set is composed of static radar point cloud data, and the second feature set is composed of map point cloud data of the area to be matched.

2. The method according to claim 1, characterized in that Before matching the map point cloud data of the to-be-matched area with the radar point cloud data to obtain the calibration parameters of the laser radar, the method further includes: Eliminating dynamic radar point cloud data from the radar point cloud data to obtain the static radar point cloud data; The step of matching the map point cloud data of the to-be-matched area with the radar point cloud data to obtain calibration parameters of the laser radar includes: The map point cloud data of the area to be matched and the static radar point cloud data are matched to obtain the calibration parameters of the laser radar.

3. The method according to claim 2, characterized in that The step of matching the map point cloud data of the to-be-matched area with the static radar point cloud data to obtain calibration parameters of the laser radar includes: Extracting features from the static radar point cloud data to obtain the first feature set; the first feature set includes at least two first features; Extracting features from the map point cloud data of the to-be-matched area to obtain the second feature set; The first feature set is matched with the second feature set to obtain calibration parameters of the laser radar.

4. The method according to claim 3, characterized in that The matching the first feature set with the second feature set to obtain calibration parameters of the laser radar includes: Acquire a first projection line segment of a line segment between two first features in the first feature set on a preset plane in the radar coordinate system, and obtain a first projection angle between the first projection line segment and a corresponding coordinate axis; Obtaining a second projection line segment of a line segment between two second features in the second feature set on a preset plane in the geographic coordinate system, and obtaining a second projection angle between the second projection line segment and the corresponding coordinate axis; the types of the two second features in the second feature set are the same as the types of the two first features in the first feature set; The first projection angle and the second projection angle are differenced to obtain the rotation angle of the origin of the laser radar coordinate system.

5. The method according to claim 4, characterized in that If the preset plane in the radar coordinate system is an XZ plane, the coordinate axis corresponding to the XZ plane is the Z axis, the preset plane in the geographic coordinate system is an altitude plane, the coordinate axis corresponding to the altitude plane is the altitude axis, and the rotation angle of the origin of the laser radar coordinate system is the rotation angle around the latitude; If the preset plane in the radar coordinate system is the YZ plane, the coordinate axis corresponding to the YZ plane is the Y axis, the preset plane in the geographic coordinate system is the latitude plane, the coordinate axis corresponding to the latitude plane is the latitude axis, and the rotation angle of the origin of the laser radar coordinate system is the rotation angle around the longitude; If the preset plane in the radar coordinate system is the XY plane, the coordinate axis corresponding to the XY plane is the X axis, the preset plane in the geographic coordinate system is the longitude plane, the coordinate axis corresponding to the longitude plane is the longitude axis, and the rotation angle of the origin of the lidar coordinate system is the rotation angle around the altitude.

6. The method according to claim 4, characterized in that The calibration parameters also include the position coordinates of the origin of the laser radar coordinate system. The calibration parameters of the laser radar are obtained according to the first feature set and the second feature set, including: Matching each of the first features in the first feature set with each of the second features in the second feature set to obtain a target first feature and a target second feature that belong to the same type; The position coordinates of the origin of the laser radar coordinate system are determined according to the position coordinates of the first feature of the target and the position coordinates of the second feature of the target; the position coordinates include longitude, latitude, and altitude.

7. The method according to claim 6, characterized in that Determining the position coordinates of the origin of the laser radar coordinate system according to the position coordinates of the first feature of the target and the position coordinates of the second feature of the target includes: Substituting the rotation angle into a preset cosine function to obtain a value of the cosine function, and correcting the position coordinates of the first feature of the target according to the value of the cosine function to obtain corrected position coordinates of the first feature of the target; The position coordinates of the origin of the laser radar coordinate system are determined according to the corrected position coordinates of the first feature of the target and the position coordinates of the second feature of the target.

8. The method according to claim 7, characterized in that Determining the position coordinates of the origin of the laser radar coordinate system according to the position coordinates of the first feature of the target and the position coordinates of the second feature of the target includes: Determine the longitude of the origin of the laser radar coordinate system according to the corrected X coordinate in the position coordinates of the first feature of the target and the longitude coordinate in the position coordinates of the second feature of the target; Determine the latitude of the origin of the laser radar coordinate system according to the corrected Y coordinate in the position coordinates of the first feature of the target and the latitude coordinate in the position coordinates of the second feature of the target; The altitude of the origin of the laser radar coordinate system is determined according to the corrected Z coordinate in the position coordinates of the first feature of the target and the altitude coordinate in the position coordinates of the second feature of the target.

9. The method according to claim 1, characterized in that: The step of acquiring the map point cloud data of the to-be-matched area corresponding to the preset scanning range from the map point cloud data according to the preset scanning range includes: Determine the initial origin according to the installation position of the laser radar; Taking the initial origin as the center, map point cloud data within the preset scanning range is selected from the map point cloud data as the map point cloud data of the area to be matched.

10. A laser radar calibration device, characterized in that: The device comprises: The first acquisition module is used to acquire radar point cloud data of the laser radar within a preset scanning range; A second acquisition module is used to acquire, from the map point cloud data of the preset scanning range, the map point cloud data of the to-be-matched area corresponding to the preset scanning range; the accuracy of the map point cloud data is greater than a preset accuracy threshold; A matching module, used for matching features in the map point cloud data of the area to be matched with features in the radar point cloud data using original calibration parameters, adjusting the original calibration parameters according to the matching results, and determining the original calibration parameters corresponding to the matching results that meet the preset standards as calibration parameters of the laser radar; the map point cloud data of the area to be matched and the radar point cloud data within the preset scanning range contain the same object to be matched; the calibration parameters include the longitude, latitude, altitude of the origin of the laser radar coordinate system and the rotation angle of the origin of the laser radar coordinate system, and the rotation angle includes the rotation angle around the longitude, the rotation angle around the latitude, and the rotation angle around the altitude; the rotation angle is determined by a first projection angle and a second projection angle, the first projection angle is the angle formed by a first projection line segment between two first features in a first feature set on a preset plane in the radar coordinate system, the second projection angle is the angle formed by a second projection line segment between two second features in a second feature set on a preset plane in the geographic coordinate system, the first feature set is composed of static radar point cloud data, and the second feature set is composed of map point cloud data of the area to be matched.

11. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

12. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

Images