Roadside Radar Calibration Method, Device, Computer Equipment and Storage Medium

Abstract

The present application relates to a roadside radar calibration method, device, computer device, and storage medium. The method includes: obtaining vehicle driving coordinate data on a road for a period of time collected by a roadside radar; extracting vehicle driving coordinate data on each lane from the vehicle driving coordinate data; fitting the vehicle driving coordinate data on each lane to obtain radar coordinate information of the lane centerline in the radar coordinate system; obtaining first positioning coordinate information of the lane centerline in the positioning coordinate system; and calibrating parameters of the roadside radar according to the radar coordinate information and the first positioning coordinate information of the lane centerline. The method is simple to operate and has convenience.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent transportation, and particularly to a roadside radar calibration method, device, computer device, and storage medium. Background Art

[0002] With the development of intelligent transportation systems and intelligent connected vehicle industries, roadside perception systems play an increasingly important role. By deploying sensors (including cameras, millimeter-wave radars, lidars, etc.) on the roadside to sense traffic information on the road in real time and sending the sensed information to vehicles traveling on the road in real time, it can effectively make up for the blind spots of on-vehicle perception and improve the safety of traffic passing.

[0003] In the intelligent transportation scenario, for roadside radars, it is necessary to obtain the positioning data of targets, and the data sensed by the roadside is represented in the radar coordinate system. Therefore, it is necessary to calibrate the parameters of the roadside radar. The traditional method of calibrating the roadside radar requires the cooperation of calibration objects with positioning functions (such as corner reflectors) on the road, which is cumbersome to operate and time-consuming and laborious in the calibration process. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a roadside radar calibration method, device, computer device, and storage medium that can be convenient and fast.

[0005] A roadside radar calibration method, the method includes:

[0006] Obtain the vehicle driving coordinate data on the road for a period of time collected by the roadside radar;

[0007] Extract the vehicle driving coordinate data on each lane from the vehicle driving coordinate data;

[0008] Fit the vehicle driving coordinate data on each lane to obtain the radar coordinate information of the lane centerline in the radar coordinate system;

[0009] Obtain the first positioning coordinate information of the lane centerline in the positioning coordinate system;

[0010] Calibrate the parameters of the roadside radar according to the radar coordinate information and the first positioning coordinate information of the lane centerline.

[0011] In one embodiment, extracting the vehicle driving coordinate data on each lane from the vehicle driving coordinate data includes:

[0012] Obtain the region of interest in the vehicle driving coordinate data delimited according to the distribution characteristics of the lanes and the coordinate changes of the vehicle driving, and the region of interest corresponds to the lane region;

[0013] Extract the vehicle driving coordinate data on each lane according to the region of interest.

[0014] In one embodiment, the obtaining of the first positioning coordinate information of the lane center line in the positioning coordinate system includes:

[0015] Obtain the first positioning coordinate information of the lane center line in the positioning coordinate system from a high-precision map.

[0016] In one embodiment, the obtaining of the first positioning coordinate information of the lane center line in the positioning coordinate system includes:

[0017] Obtain the first positioning coordinate information of the lane center line in the positioning coordinate system collected when the positioning vehicle drives on each lane.

[0018] In one embodiment, the fitting of the vehicle driving coordinate data on each lane to obtain the radar coordinate information of the lane center line in the radar coordinate system includes:

[0019] Perform polynomial fitting on the vehicle driving coordinate data on each lane to obtain the trajectory of the lane center line in the roadside radar coordinate system;

[0020] Sample the trajectory of the lane center line in the roadside radar coordinate system to obtain the radar coordinate information of the lane center line in the roadside radar coordinate system.

[0021] In one embodiment, parameter calibration of the roadside radar according to the radar coordinate information and the first positioning coordinate information of the lane center line includes:

[0022] According to the radar coordinate information, convert the coordinate points of the lane center line to the positioning coordinate system to obtain the converted positioning coordinate points of the coordinate points in the positioning coordinate system;

[0023] Obtain the first positioning coordinate point closest to the converted coordinate point in the first positioning coordinate information;

[0024] Taking minimizing the distance between the converted positioning coordinate point and the first positioning coordinate point as the goal, obtain the calibration parameters of the roadside radar.

[0025] In one embodiment, the objective function of the goal satisfies the following constraint conditions: the distance difference between the first distance and the second distance satisfies the distance deviation threshold, where the first distance is the distance between the converted positioning point and the positioning coordinate point of the roadside radar in the positioning coordinate system; the second distance is the distance between the radar coordinate point of the lane center line in the radar coordinate system and the radar.

[0026] A roadside radar calibration device, the device includes:

[0027] A data acquisition module, configured to obtain vehicle driving coordinate data on a road for a period of time collected by a roadside radar;

[0028] A lane data extraction module, configured to extract vehicle driving coordinate data on each lane from the vehicle driving coordinate data;

[0029] A fitting module, configured to fit the vehicle driving coordinate data on each lane to obtain radar coordinate information of the lane centerline in the radar coordinate system;

[0030] A positioning information acquisition module, configured to obtain first positioning coordinate information of the lane centerline in the positioning coordinate system;

[0031] A calibration module, configured to calibrate parameters of the roadside radar according to the radar coordinate information and the first positioning coordinate information of the lane centerline.

[0032] A computer device, comprising a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0033] Obtain vehicle driving coordinate data on a road for a period of time collected by a roadside radar;

[0034] Extract vehicle driving coordinate data on each lane from the vehicle driving coordinate data;

[0035] Fit the vehicle driving coordinate data on each lane to obtain radar coordinate information of the lane centerline in the radar coordinate system;

[0036] Obtain first positioning coordinate information of the lane centerline in the positioning coordinate system;

[0037] Calibrate parameters of the roadside radar according to the radar coordinate information and the first positioning coordinate information of the lane centerline.

[0038] A computer-readable storage medium, on which a computer program is stored, where the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0039] Obtain vehicle driving coordinate data on a road for a period of time collected by a roadside radar;

[0040] Extract vehicle driving coordinate data on each lane from the vehicle driving coordinate data;

[0041] Fit the vehicle driving coordinate data on each lane to obtain radar coordinate information of the lane centerline in the radar coordinate system;

[0042] Obtain first positioning coordinate information of the lane centerline in the positioning coordinate system;

[0043] Calibrate the roadside radar according to the radar coordinate information and the first positioning coordinate information of the lane center line.

[0044] The above roadside radar calibration method, device, computer device and storage medium are based on the vehicle driving coordinate data collected by the roadside radar, fit to obtain the radar coordinate information of the lane center line in the radar coordinate system, obtain the first positioning coordinate information of the lane center line in the positioning coordinate information, and calibrate the roadside radar according to the coordinate information of the lane line in the two coordinate systems. In this method, the radar coordinate information of the lane center line in the radar coordinate system is obtained by lane segmentation and fitting according to the data collected by the roadside radar, without the need for other calibration objects, so it can be directly processed using the radar data of ordinary vehicles. This method is simple to operate and has convenience. Brief Description of the Drawings

[0045] Figure 1 It is an application environment diagram of the roadside radar calibration method in an embodiment;

[0046] Figure 2 It is a flowchart of the roadside radar calibration method in an embodiment;

[0047] Figure 3 It is a schematic diagram of vehicle driving coordinate data in an embodiment;

[0048] Figure 4 It is a schematic diagram of the region of interest in vehicle driving coordinate data in an embodiment;

[0049] Figure 5 In an embodiment, according to Figure 4 The schematic diagram of the vehicle driving coordinate data on the lane extracted from the region of interest;

[0050] Figure 6 It is a schematic diagram of the structure of roadside radar calibration in an embodiment;

[0051] Figure 7 It is an internal structure diagram of a computer device in an embodiment. Detailed Description of the Embodiments

[0052] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below with reference to 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.

[0053] The roadside radar calibration method provided by the present application can be applied to the application environment as Figure 1 shown. As Figure 1As shown in the figure, it includes a roadside unit 104 set on one side of a road 102, an edge computing unit 106 connected to the roadside unit 104 through a network, and a vehicle 108 traveling on the road. During calibration, the roadside radar collects the vehicle travel coordinate data of vehicles traveling on the road for a period of time and sends it to the edge computing unit 106, and the edge computing unit processes it to implement the roadside radar calibration method.

[0054] In one embodiment, as Figure 2 shown, a roadside radar calibration method is provided. Taking the edge computing unit in Figure 1 as an example for illustration, it includes the following steps:

[0055] Step 202, obtain the vehicle travel coordinate data of vehicles on the road collected by the roadside radar for a period of time.

[0056] The roadside radar can be a millimeter-wave radar and a lidar. The position information of the target collected by the roadside radar is based on the roadside radar coordinate system, such as the millimeter-wave radar coordinate system or the lidar coordinate system. The roadside radar collects the radar data of vehicles on the road for a period of time, and represents the coordinate data of the vehicles at each time in the form of data points in the radar coordinate system to obtain the vehicle travel coordinate data, that is, the vehicle travel coordinate data is the coordinate data of the vehicle travel movement of the vehicle in the roadside radar coordinate system. According to the vehicle travel coordinate data represented in the form of data points in the roadside radar coordinate system, the travel trajectory of the vehicle during this period can be obtained through the continuity of the change of the coordinate points of the vehicle. The vehicle travel coordinate data in one embodiment is as Figure 3 shown, and the coordinate position of the vehicle is represented by data points.

[0057] Among them, the vehicle is a vehicle traveling on the road, which can be an ordinary vehicle, and there is no need to clear the road environment for calibration, nor to set specific connected vehicles for calibration. In the traditional calibration method, only a unique connected vehicle is required to travel at an intersection or on a road during calibration, and the traffic conditions at the open intersection or on the road cannot be controlled. The calibration method of the present application has no special requirements for the traffic conditions at intersections or on roads, and only requires that there are normal vehicles traveling at intersections or on roads, which reduces the requirements for traffic control during calibration and improves the operation convenience, so that this method is applicable to various traffic sections of urban intersections and highways and is not affected by the traffic flow of the section where the roadside radar is located.

[0058] Step 204, extract the vehicle travel coordinate data on each lane from the vehicle travel coordinate data.

[0059] The road has lane divisions. A lane, also known as a traffic lane or a carriageway, is a road used for vehicles to travel. It is set on general roads and highways. For example, if a road has three lanes, it has three lanes and vehicles can travel in the three lanes.

[0060] Identify the vehicle driving coordinate data on the lane by analyzing the vehicle driving coordinate data.

[0061] In one implementation, the roadside radar data can be fused with the position data of the lane lines, and the lane lines can be marked on the vehicle driving coordinate data to extract the vehicle driving coordinate data on the lane.

[0062] In one implementation, obtain the region of interest in the vehicle driving coordinate data delimited according to the distribution characteristics of the lanes and the coordinate changes of the vehicle driving. The region of interest corresponds to the lane region; according to the region of interest, extract the vehicle driving coordinate data on each lane.

[0063] Among them, the distribution characteristics of the lanes include the number of lanes and the lane curve characteristics. The number of lanes refers to the number of lanes on the road. For example, the number of lanes corresponding to two lanes is 2, or the number of lanes corresponding to three lanes is 3. The lane curve characteristic is the shape of the lane corresponding to the detection range of the roadside radar. The lane shape usually coincides with the road shape. The lane curve characteristic reflects the curvature of the lane lines of the lane. For example, the lanes in one area are straight, and the lanes in another area are curves with a certain curvature.

[0064] However, the distribution characteristics of the lanes of the vehicle can only roughly determine the lane data and shape, and cannot achieve the segmentation of the vehicle driving coordinate data of the lanes.

[0065] Furthermore, in this embodiment, according to the vehicle driving coordinate data represented in the form of data points in the roadside radar coordinate system, the driving trajectory of the vehicle during this time period can be obtained through the continuity of the coordinate point changes of the vehicle. Therefore, combining the coordinate changes of the vehicle driving reflected by the vehicle driving coordinate data and the distribution characteristics of the lanes, delimit the region of interest corresponding to the range of the vehicle driving coordinate data of the vehicle driving along a fixed lane in the vehicle driving coordinate data. The vehicle driving coordinate data of the vehicle driving along a fixed lane must be within the lane region. Therefore, the region of interest corresponds to the lane region. Specifically, the region of interest is within the lane region.

[0066] For Figure 3 the vehicle driving coordinate data, combining the coordinate changes of the vehicle driving reflected by the vehicle driving coordinate data and the distribution characteristics of the lanes, the region of interest delimited in the vehicle driving coordinate data is shown in Figure Figure 4 as shown. Among them, according to the coordinate changes of the vehicle driving, regions A and B indicate that there are lane changes. According to the coordinate changes of the vehicle driving and the lane distribution characteristics, it can be determined Figure 4Two regions of interest C and D, where the shapes of the two regions of interest are the same, representing two lanes on the road, and the coordinate points within the region of interest are the driving coordinate data of vehicles traveling along a fixed lane. The vehicle driving coordinate data of the corresponding lane extracted from the region of interest is as follows Figure 5 as shown, relative to Figure 4 the complete vehicle driving coordinate data, the coordinate data of vehicles changing lanes is excluded.

[0067] In practical applications, based on the vehicle driving coordinate data, by the staff, according to the distribution characteristics of the lanes within the detection range of the roadside radar, combined with experience, the range of the vehicle driving coordinate data of vehicles traveling along a fixed lane is delimited to obtain the region of interest.

[0068] Generally speaking, to extract the coordinates of the centerlines of multiple lanes in the roadside radar coordinate system, it is necessary to cluster the coordinates of the targets detected by the roadside radar. Common clustering methods include k-means, DBSCAN clustering, etc. Since the target areas detected by the roadside radar are irregular, the k-means method cannot be used for clustering. At the same time, due to vehicle lane changes, there are connections between different lanes in the roadside radar coordinate system, so the DBSCAN clustering method cannot be used to distinguish them. In view of the difficulties in extracting the lane centerlines in the roadside radar coordinate system, in this embodiment, by delimiting the region of interest in the vehicle driving coordinate data according to the distribution characteristics of the lanes and the coordinate changes of vehicle driving, and then extracting the vehicle driving coordinate data on the lanes according to the region of interest, the coordinate data of the lanes with lane changes can be excluded, and the vehicle driving coordinate data of at least one lane can be obtained. Using this method, there is no need to cluster the coordinates of the targets detected by the roadside radar. Only by extracting the vehicle driving coordinate data of vehicles traveling along a fixed lane according to the region of interest, the coordinate data of the vehicles on at least one segmented lane can be obtained.

[0069] Step 206: Fit the vehicle driving coordinate data on each lane to obtain the radar coordinate information of the lane centerline in the radar coordinate system.

[0070] Among them, the fitting method can be polynomial fitting. Specifically, perform polynomial fitting on the vehicle driving coordinate data on each lane to obtain the trajectory of the lane centerline in the roadside radar coordinate system; sample the trajectory of the lane centerline in the roadside radar coordinate system to obtain the radar coordinate information of the lane centerline in the roadside radar coordinate system. Specifically, the trajectory of the lane centerline in the roadside radar coordinate system can be obtained by performing polynomial fitting on the roadside coordinate data corresponding to each lane.

[0071] y radar = a + b * x radar + c * x radar 2 + d * x radar3

[0072] Among them, the polynomial parameters a, b, c, and d in the formula can be obtained by the least squares method. After obtaining the polynomial trajectories of each lane, N (N is an integer greater than 3) sampling points are evenly selected on each lane to realize the sampling of the lane center line in the roadside radar coordinate system, and each lane center line obtains N roadside radar coordinate points.

[0073] Step 208: Obtain the first positioning coordinate information of the lane center line in the positioning coordinate system.

[0074] The positioning coordinate system refers to the coordinate system for realizing the positioning function. For example, the positioning coordinate system can be the GPS coordinate system for realizing GPS positioning, and the GPS coordinate system is the WGS-84 coordinate system (World Geodetic System 1984 Coordinate System, a geocentric coordinate system adopted internationally). The positioning coordinate system can also be the Beidou coordinate system for realizing Beidou positioning, or the GLONASS coordinate system.

[0075] In one implementation, the first positioning coordinate information of the lane center line in the positioning coordinate system is obtained from the high-precision map. Currently, domestic high-precision maps adopt the OpenDRIVE format standard, and the OpenDRIVE format standard contains the WGS-84 coordinates corresponding to the center lines of each lane or virtual lanes (intersections).

[0076] In one implementation, the first positioning coordinate information of the lane center line collected when the positioning vehicle travels in each lane is obtained. The positioning vehicle has a positioning function, such as a connected vehicle with RTK positioning function. The connected vehicle with RTK positioning function can be used to drive in each lane once to obtain the WGS-84 coordinates (including longitude and latitude) of each lane center line.

[0077] Step 210: Calibrate the parameters of the roadside radar according to the radar coordinate information and the first positioning coordinate information of the lane center line.

[0078] Specifically, the radar coordinate information is the representation of the lane center line in the roadside radar coordinate system, and the first positioning coordinate information is the representation of the lane center line in the positioning coordinate system. According to the mapping relationship between the two, the parameter calibration of the roadside radar relative to the positioning system can be realized, so that the position information of the target collected by the roadside radar can be converted to the positioning system coordinate system by using the parameters, and the coordinates of the target in the positioning coordinate system can be directly input. That is to say, the final calibration of the roadside radar is to obtain the positioning position of the target (such as GPS positioning).

[0079] Specifically, according to the radar coordinate information, the coordinate points of the lane center line are converted into the positioning coordinate system to obtain the converted positioning coordinate points of the coordinate points in the positioning coordinate system; after being converted into the positioning coordinate system, the first positioning coordinate point closest to the converted coordinate points is obtained from the first positioning coordinate information; with the goal of minimizing the distance between the converted positioning coordinate points and the first positioning coordinate points, the calibration parameters of the roadside radar are obtained.

[0080] Among them, the mapping relationship between the roadside radar coordinate system and the positioning coordinate system is as follows:

[0081]

[0082] Among them, respectively represent the x coordinate and y coordinate of the radar coordinate point of the i-th point of the lane center line, with the unit of m, lon i represents the longitude in the positioning coordinate system mapped by the i-th radar coordinate point of the lane center line, with the unit of deg; lat i represents the latitude in the positioning coordinate system mapped by the i-th radar coordinate of the lane center line, a 1 , a 2 , b 1 , b 2 , c 1 , c 2 are calibration parameters. The key to the calibration process is how to obtain the calibration parameters x = [a 1 b 1 c 1 a 2 b 2 c 2 in the above formula to make the radar coordinates of the lane center line correspond to the first positioning coordinate information.

[0083] Specifically, an objective function with the following objective is defined:

[0084]

[0085] Or

[0086]

[0087] Among them, is the converted positioning coordinate point of the point on the lane center line in the radar coordinate data obtained through the mapping relationship, is the converted positioning coordinate point the positioning coordinate point (including longitude and latitude) closest to the lane center line among the converted positioning coordinate points, that is, the first positioning point coordinate point, N is the total number of road radar coordinates corresponding to each lane center line selected, and M is the total number of lanes.

[0088] Meanwhile, the parameters of the objective function need to satisfy the following distance constraint conditions: the distance difference between the first distance and the second distance satisfies the distance deviation threshold. The first distance is the distance between the transformed positioning point and the positioning coordinate point of the roadside radar in the positioning coordinate system; the second distance is the distance between the radar coordinate point of the lane centerline in the radar coordinate system and the radar.

[0089] The distance constraint conditions are specifically as follows:

[0090]

[0091] Among them, represents the second distance, that is, the distance from the i-th radar coordinate point of the lane centerline to the radar, with the unit of m, gps r is the positioning coordinate point (including longitude and latitude) of the location of the roadside radar in the positioning coordinate system, which is obtained through a GPS acquisition tool during radar installation. represents the first distance, that is, the distance between the transformed positioning point and the positioning coordinate point of the roadside radar in the positioning coordinate system. dist_th max and dist_th min are the upper and lower limit thresholds of the distance deviation, respectively, which are adjusted according to the actual situation.

[0092] By using the above objective function and distance constraint and adopting a non-linear optimization method (such as the active set method, sequential quadratic programming method, interior point method, genetic algorithm, particle swarm optimization, etc.), the optimal calibration parameter x of the roadside radar can be solved, so as to obtain the mapping relationship between the roadside radar coordinate system and the positioning coordinate system, and realize the calibration of the roadside radar. This method can be applied to the calibration of roadside lidar or roadside millimeter-wave radar.

[0093] The above-mentioned roadside radar calibration method is based on the vehicle driving coordinate data collected by the roadside radar, fits to obtain the radar coordinate information of the lane centerline in the radar coordinate system, obtains the first positioning coordinate information of the lane centerline in the positioning coordinate information, and calibrates the parameters of the roadside radar according to the coordinate information of the lane line in the two coordinate systems. In this method, the radar coordinate information of the lane centerline in the radar coordinate system is obtained by lane segmentation and fitting according to the data collected by the roadside radar, without the need for other calibration objects, so it can be directly processed using the radar data of ordinary vehicles. This method is simple to operate and has convenience.

[0094] In practical applications, in intelligent highway projects and urban intersection intelligentization projects, due to reasons such as damage and replacement of roadside radars, vibration, insecure installation, and thermal expansion and contraction, the calibration parameters of roadside sensors such as roadside radars during installation cannot be applied to the situation after the sensors change, resulting in a large position error in the detection targets of the sensors and affecting the effect of multi-sensor fusion. By using the method of the present application, when the roadside radar needs to be recalibrated due to reinstallation, loosening, or thermal expansion and contraction, it is only necessary to collect the data of ordinary vehicles detected by the adjusted roadside radar for a period of time and the high-precision map information of this section to achieve the calibration of the roadside radar.

[0095] It should be understood that although Figure 2 the steps in the flowchart of Figure 2 are shown in sequence according to the indication of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover,

[0096] In one embodiment, as Figure 6 shown, a roadside radar calibration device is provided, including:

[0097] An acquisition module 602, configured to acquire the vehicle driving coordinate data on the road collected by the roadside radar for a period of time;

[0098] A lane data extraction module 604, configured to extract the vehicle driving coordinate data on each lane from the vehicle driving coordinate data;

[0099] A fitting module 606, configured to fit the vehicle driving coordinate data on each lane to obtain the radar coordinate information of the lane center line in the radar coordinate system;

[0100] A positioning information acquisition module 608, configured to acquire the first positioning coordinate information of the lane center line in the positioning coordinate system;

[0101] A calibration module 610, configured to calibrate the parameters of the roadside radar according to the radar coordinate information and the first positioning coordinate information of the lane center line.

[0102] The above roadside radar calibration device fits the radar coordinate information of the lane centerline in the radar coordinate system based on the vehicle driving coordinate data collected by the roadside radar, obtains the first positioning coordinate information of the lane centerline in the positioning coordinate information, and calibrates the parameters of the roadside radar according to the coordinate information of the lane line in the two coordinate systems. In this method, the radar coordinate information of the lane centerline in the radar coordinate system is obtained by lane segmentation and fitting based on the data collected by the roadside radar, without the need for other calibration objects, so it can be directly processed using the radar data of ordinary vehicles. This method is simple to operate and has convenience.

[0103] In another embodiment, the lane data extraction module is used to obtain the region of interest in the vehicle driving coordinate data delimited according to the distribution characteristics of the lane and the coordinate change of the vehicle driving, and the region of interest corresponds to the lane region; according to the region of interest, the vehicle driving coordinate data on each lane is extracted.

[0104] In another embodiment, the positioning information acquisition module is used to obtain the first positioning coordinate information of the lane centerline in the positioning coordinate system from the high-precision map.

[0105] In another embodiment, the positioning information acquisition module is used to obtain the first positioning coordinate information of the lane centerline in the positioning coordinate system collected by the positioning vehicle driving on each lane.

[0106] In another embodiment, the fitting module is used to perform polynomial fitting on the vehicle driving coordinate data on each lane to obtain the trajectory of the lane centerline in the roadside radar coordinate system; sample the trajectory of the lane centerline in the roadside radar coordinate system to obtain the radar coordinate information of the lane centerline in the roadside radar coordinate system.

[0107] In another embodiment, the calibration module is used to convert the coordinate points of the lane centerline to the positioning coordinate system according to the radar coordinate information to obtain the converted positioning coordinate points of the coordinate points in the positioning coordinate system; obtain the first positioning coordinate points closest to the converted coordinate points in the first positioning coordinate information; and take minimizing the distance between the converted positioning coordinate points and the first positioning coordinate points as the goal to obtain the calibration parameters of the roadside radar.

[0108] Among them, the objective function of the goal satisfies the following constraint conditions: the distance difference between the first distance and the second distance satisfies the distance deviation threshold, the first distance is the distance between the converted positioning point and the positioning coordinate point of the roadside radar in the positioning coordinate system; the second distance is the distance between the radar coordinate point of the lane centerline in the radar coordinate system and the radar.

[0109] For the specific limitations of the roadside radar calibration device, reference can be made to the limitations of the roadside radar calibration method in the foregoing text, which will not be elaborated here. Each module in the above-mentioned roadside radar calibration device can be implemented in whole or in part by software, hardware, and their combination. Each of 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 as to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0110] In one embodiment, a computer device is provided. The computer device can be an edge computing unit, and its internal structure diagram can be as Figure 7 shown. The computer device includes a processor, a memory, and a communication interface 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 communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a roadside radar calibration method.

[0111] Those skilled in the art can understand that Figure 7 the structure shown in

[0112] is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0113] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, it implements the methods of the above embodiments.

[0114] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. 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 various methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include at least one of non-volatile and volatile memories. 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. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0115] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, 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, it should be considered as the scope recorded in this specification.

[0116] The above embodiments only represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A roadside radar calibration method, the method comprises: Obtain the vehicle driving coordinate data on the road for a period of time collected by the roadside radar; Extract the vehicle driving coordinate data on each lane from the vehicle driving coordinate data; Fit the vehicle driving coordinate data on each lane to obtain the radar coordinate information of the lane centerline in the radar coordinate system; Obtain the first positioning coordinate information of the lane centerline in the positioning coordinate system; Calibrate the parameters of the roadside radar according to the radar coordinate information and the first positioning coordinate information of the lane centerline, wherein calibrating the parameters of the roadside radar according to the radar coordinate information and the first positioning coordinate information of the lane centerline includes: According to the radar coordinate information, convert the coordinate points of the lane centerline to the positioning coordinate system to obtain the converted positioning coordinate points of the coordinate points in the positioning coordinate system; Obtain the first positioning coordinate point closest to the converted positioning coordinate point in the first positioning coordinate information; Take minimizing the distance between the converted positioning coordinate point and the first positioning coordinate point as the target to obtain the calibration parameters of the roadside radar.

2. The method according to claim 1, wherein, extracting the vehicle driving coordinate data on each lane from the vehicle driving coordinate data includes: Obtain the region of interest in the vehicle driving coordinate data delimited according to the distribution characteristics of the lanes and the coordinate changes of the vehicle driving, and the region of interest corresponds to the lane region; Extract the vehicle driving coordinate data on each lane according to the region of interest.

3. The method according to claim 1, wherein, the obtaining the first positioning coordinate information of the lane centerline in the positioning coordinate system includes: Obtain the first positioning coordinate information of the lane centerline in the positioning coordinate system from the high-precision map.

4. The method according to claim 1, wherein, the obtaining the first positioning coordinate information of the lane centerline in the positioning coordinate system includes: Obtain the first positioning coordinate information of the lane centerline in the positioning coordinate system collected by the positioning vehicle driving on each lane.

5. The method according to claim 1, wherein, the fitting the vehicle driving coordinate data on each lane to obtain the radar coordinate information of the lane centerline in the radar coordinate system includes: Perform polynomial fitting on the vehicle driving coordinate data on each lane to obtain the trajectory of the lane centerline in the roadside radar coordinate system; Sample the trajectory of the lane centerline in the roadside radar coordinate system to obtain the radar coordinate information of the lane centerline in the roadside radar coordinate system.

6. The method according to claim 1, wherein, the objective function of the target satisfies the following constraint conditions: the distance difference between the first distance and the second distance satisfies the distance deviation threshold, the first distance is the distance between the converted positioning coordinate point and the positioning coordinate point of the roadside radar in the positioning coordinate system; the second distance is the distance between the radar coordinate point of the lane centerline in the radar coordinate system and the radar.

7. A roadside radar calibration device, wherein, the device includes: The acquisition module is used to obtain the vehicle driving coordinate data on the road for a period of time collected by the roadside radar; The lane data extraction module is used to extract the vehicle driving coordinate data on each lane from the vehicle driving coordinate data; The fitting module is used to fit the vehicle driving coordinate data on each lane to obtain the radar coordinate information of the lane center line in the radar coordinate system; The positioning information acquisition module is used to obtain the first positioning coordinate information of the lane center line in the positioning coordinate system; The calibration module is used to calibrate the parameters of the roadside radar according to the radar coordinate information and the first positioning coordinate information of the lane center line. Among them, the calibration module is further used to convert the coordinate points of the lane center line to the positioning coordinate system according to the radar coordinate information to obtain the converted positioning coordinate points of the coordinate points in the positioning coordinate system; obtain the first positioning coordinate point closest to the converted positioning coordinate point in the first positioning coordinate information; and take minimizing the distance between the converted positioning coordinate point and the first positioning coordinate point as the goal to obtain the calibration parameters of the roadside radar.

8. The device according to claim 7, wherein, the lane data extraction module is further used for: obtaining the region of interest in the vehicle driving coordinate data delimited according to the distribution characteristics of the lanes and the coordinate changes of the vehicle driving, the region of interest corresponding to the lane region; and extracting the vehicle driving coordinate data on each lane according to the region of interest.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, wherein, when the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, having a computer program stored thereon, wherein, when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images