WO2022199440A1

WO2022199440A1 - Roadside radar calibration method and apparatus, computer device, and storage medium

Info

Publication number: WO2022199440A1
Application number: PCT/CN2022/081142
Authority: WO
Inventors: 魏吉敏; 张长隆; 佘咸宁; 王泽涛
Original assignee: 长沙智能驾驶研究院有限公司
Priority date: 2021-03-26
Filing date: 2022-03-16
Publication date: 2022-09-29
Also published as: CN115128552A

Abstract

The present application relates to a roadside radar calibration method and apparatus, a computer device, and a storage medium. The method comprises: acquiring vehicle traveling coordinate data on a road for a period of time collected by a roadside radar; extracting vehicle traveling coordinate data on each lane from the vehicle traveling coordinate data; fitting the vehicle traveling coordinate data on each lane to obtain radar coordinate information of a lane center line in a radar coordinate system; acquiring first positioning coordinate information of the lane center line in a positioning coordinate system; and performing parameter calibration on the roadside radar according to the radar coordinate information and the first positioning coordinate information of the lane center line. The method is simple to operate and is convenient.

Description

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

technical field

The present application relates to the technical field of intelligent transportation, and in particular, to a roadside radar calibration method, device, computer equipment and storage medium.

Background technique

With the development of the intelligent transportation system and the intelligent networked automobile industry, the roadside perception system plays an increasingly important role. It senses the road in real time by arranging sensors (including cameras, millimeter-wave radar, lidar, etc.) Traffic information and real-time transmission of perception information to vehicles on the road can effectively make up for the blind spot of vehicle perception and improve the safety of traffic.

In the intelligent traffic scenario, for the roadside radar, it is necessary to obtain the positioning data of the target, and the data of the roadside perception is represented by the radar coordinate system. Therefore, the parameters of the roadside radar need to be calibrated. The traditional way of calibrating the roadside radar requires the coordination of a calibration object (such as a corner reflector) with a positioning function on the road, which is cumbersome to operate, and the calibration process is time-consuming and labor-intensive.

SUMMARY OF THE INVENTION

Based on this, it is necessary to provide a roadside radar calibration method, device, computer equipment and storage medium that can be convenient and quick to address the above technical problems.

A roadside radar calibration method, the method comprising:

Obtain the vehicle driving coordinate data on the road for a period of time collected by the 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 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 system;

The parameters of the roadside radar are calibrated according to the radar coordinate information of the lane center line and the first positioning coordinate information.

In one embodiment, extracting vehicle driving coordinate data on each lane from the vehicle driving coordinate data, including:

acquiring an area of interest in the vehicle driving coordinate data delineated according to the distribution characteristics of the lanes and the coordinate changes of the vehicle driving, and the area of interest corresponds to the lane area;

According to the region of interest, the vehicle travel coordinate data on each lane is extracted.

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

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

The first positioning coordinate information of the lane center line in the positioning coordinate system obtained by the positioning vehicle traveling in each lane is acquired.

In one embodiment, the vehicle driving coordinate data on each lane is fitted to obtain the radar coordinate information of the lane center line in the radar coordinate system, including:

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;

Sampling the trajectory of the lane centerline in the roadside radar coordinate system to obtain radar coordinate information of the lane centerline in the roadside radar coordinate system.

In one embodiment, performing parameter calibration on the roadside radar according to the radar coordinate information of the lane centerline and the first positioning coordinate information, including:

According to the radar coordinate information, convert the coordinate point of the lane center line to the positioning coordinate system, and obtain the positioning coordinate point of the coordinate point after the conversion of the positioning coordinate system;

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

The calibration parameters of the roadside radar are obtained with the goal of minimizing the distance between the transformed positioning coordinate point and the first positioning coordinate point.

In one of the embodiments, the objective function of the target satisfies the following constraints: the distance difference between the first distance and the second distance satisfies a distance deviation threshold, and the first distance is the converted location point and the road The distance between the positioning coordinate point of the side radar in the positioning coordinate system; the second distance is the distance between the radar coordinate point and the radar of the lane center line in the radar coordinate system.

A roadside radar calibration device, the device comprising:

The acquisition module is used to acquire the vehicle traveling coordinate data on the road for a period of time collected by the roadside radar;

a lane data extraction module for extracting vehicle travel coordinate data on each lane from the vehicle travel coordinate data;

a fitting module, used for fitting the vehicle driving coordinate data on each lane to obtain the radar coordinate information of the lane center line in the radar coordinate system;

a positioning information acquisition module, used for acquiring the first positioning coordinate information of the lane center line in the positioning coordinate system;

A calibration module, configured to perform parameter calibration on the roadside radar according to the radar coordinate information of the lane center line and the first positioning coordinate information.

A computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

A computer-readable storage medium on which a computer program is stored, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

The above roadside radar calibration method, device, computer equipment and storage medium, 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, and obtain the lane center line in the positioning coordinate information. The first positioning coordinate information is used to calibrate 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 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 to assist other calibration objects, so it can be directly processed by the radar data of ordinary vehicles. , the method is simple and convenient.

Description of drawings

1 is an application environment diagram of a roadside radar calibration method in one embodiment;

2 is a schematic flowchart of a roadside radar calibration method in one embodiment;

3 is a schematic diagram of vehicle travel coordinate data in one embodiment;

4 is a schematic diagram of a region of interest in vehicle driving coordinate data in one embodiment;

5 is a schematic diagram of vehicle traveling coordinate data on a lane extracted according to the region of interest of FIG. 4 in one embodiment;

6 is a schematic structural diagram of roadside radar calibration in one embodiment;

FIG. 7 is a diagram of the internal structure of a computer device in one embodiment.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application will be described in further 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, but not to limit the present application.

The roadside radar calibration method provided in this application can be applied to the application environment shown in FIG. 1 . As shown in FIG. 1 , it includes a roadside unit 104 disposed 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 running on the road. During calibration, the roadside radar collects vehicle travel coordinate data of vehicles traveling on the road for a period of time, and sends the data to the edge computing unit 106, where the edge computing unit processes and implements the roadside radar calibration method.

In one embodiment, as shown in FIG. 2 , a roadside radar calibration method is provided, and the method is applied to the edge computing unit in FIG. 1 as an example to illustrate, including the following steps:

Step 202 , acquiring coordinate data of vehicle traveling on the road for a period of time collected by the roadside radar.

The roadside radar can be millimeter wave radar and lidar. The location 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 the vehicles on the road for a period of time, and expresses the coordinate data of the vehicle at each time in the form of data points in the radar coordinate system to obtain the vehicle driving coordinate data, that is, the vehicle driving coordinate data is the roadside radar coordinates of the vehicle. According to the coordinate data of the vehicle's driving motion in the roadside radar coordinate system, according to the vehicle's driving coordinate data in the form of data points in the roadside radar coordinate system, through the continuity of the changes of the vehicle's coordinate points, the vehicle's driving trajectory in this time period can be obtained. The vehicle driving coordinate data in one embodiment is shown in FIG. 3 , and the coordinate position of the vehicle is represented by data points.

Among them, the vehicle is a vehicle running on the road, which can be an ordinary vehicle, and there is no need to clear the road environment for calibration, nor to set up specific networked vehicle cooperation for calibration. The traditional calibration method requires only the only connected vehicle to drive on the intersection or road during calibration, and the traffic situation on the open intersection or road cannot be controlled. The calibration method of the present application has no special requirements on the traffic conditions on the intersection or road, and only requires that there are normal vehicles driving at the intersection or road, which reduces the requirements for traffic control during calibration and improves the convenience of operation, so that the method is suitable for use. In urban intersections and various traffic sections of expressways, it is not affected by the traffic flow of the road section where the roadside radar is located.

Step 204 , extracting vehicle traveling coordinate data on each lane from the vehicle traveling coordinate data.

Roads are divided into lanes. Lanes, also known as lanes and lanes, are roads used for vehicles to travel. There are settings on general roads and highways. If a road has three lanes, it has three lanes, and the vehicle can drive in three lanes.

Through the vehicle travel coordinate data, the vehicle travel coordinate data on the lane is identified.

In one embodiment, the roadside radar data and the position data of the lane line can be fused, and the lane line can be marked on the vehicle traveling coordinate data, so as to extract the vehicle traveling coordinate data on the lane.

In one embodiment, the area of interest in the vehicle driving coordinate data delineated according to the distribution characteristics of the lanes and the coordinate changes of the vehicle is obtained, and the area of interest corresponds to the lane area; Vehicle travel coordinate data.

Among them, the distribution characteristics of the lanes include the number of lanes and the characteristics of the lane curve. 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 feature refers to the shape of the lane corresponding to the detection range of the roadside radar. The lane shape usually matches the road shape. The lane curve feature reflects the curvature of the lane line of the lane, for example, the lane in one area is a straight line, and the lane in one area is a curve with a certain curvature.

However, the distribution characteristics of the vehicle lanes can only roughly determine the lane data and shape, and cannot realize the segmentation of the vehicle travel coordinate data of the lanes.

Further, in this embodiment, according to the vehicle traveling coordinate data expressed in the form of data points in the roadside radar coordinate system, the vehicle traveling trajectory in this time period can be obtained through the continuity of the vehicle coordinate point changes. Therefore, combined with the coordinate changes of the vehicle driving and the distribution characteristics of the lanes embodied in the vehicle driving coordinate data, an area of interest corresponding to the vehicle driving coordinate data range driving along the fixed lane is delineated in the vehicle driving coordinate data, and driving along the fixed lane. The vehicle driving coordinate data of , must be in the lane area, therefore, the area of interest corresponds to the lane area, and specifically, the area of interest is within the range of the lane area.

For the vehicle driving coordinate data in FIG. 3 , the area of interest delineated in the vehicle driving coordinate data is shown in FIG. Among them, according to the coordinate change of vehicle driving, area A and area B indicate that there is a lane change, and according to the coordinate change of vehicle driving according to the lane distribution characteristics, two interest areas C and D in FIG. 4 can be determined. The shape of , represents the two lanes on the road, and the coordinate points in the area of interest are the coordinate data of the vehicle traveling along the fixed lane. The vehicle driving coordinate data of the corresponding lane extracted from the region of interest is shown in FIG. 5 . Compared with the complete vehicle driving coordinate data in FIG. 4 , the coordinate data of vehicles changing lanes are excluded.

In practical applications, based on the vehicle driving coordinate data, according to the distribution characteristics of the lanes detected by the roadside radar, combined with experience, the vehicle driving coordinate data range is demarcated along the fixed lane to obtain the area of interest.

Generally speaking, extracting the coordinates of the centerlines of multiple lanes in the roadside radar coordinate system requires clustering the coordinates of the targets detected by the roadside radar. Common clustering methods include k-means, DBSCAN clustering, etc. Due to the irregularity of the target area detected by the roadside radar, the k-means method cannot be used for clustering, and at the same time, different lanes are in the roadside radar coordinate system due to vehicle lane changes. There is a connection in , so it cannot be distinguished by DBSCAN clustering method. Aiming at the difficulty of extracting the lane center line in the roadside radar coordinate system, in this embodiment, the area of interest in the vehicle driving coordinate data is delineated according to the distribution characteristics of the lane and the coordinate changes of the vehicle driving, and then according to the interest area The area extracts the vehicle traveling coordinate data on the lane, and can eliminate the coordinate data of the lane changing lane to obtain the vehicle traveling coordinate data of at least one lane. By adopting this method, it is not necessary to cluster the coordinates of the targets detected by the roadside radar, and it is only necessary to extract the coordinate data of the vehicles traveling along the fixed lane according to the region of interest, and then the coordinate data of the vehicles on at least one segmented lane can be obtained. .

Step 206 , fitting the vehicle traveling coordinate data on each lane to obtain the radar coordinate information of the lane center line in the radar coordinate system.

The fitting method may be polynomial fitting. Specifically, polynomial fitting is performed on the vehicle driving coordinate data in each lane to obtain the trajectory of the lane center line in the roadside radar coordinate system; the trajectory of the lane center line in the roadside radar coordinate system is sampled to obtain the lane center The radar coordinate information of the line in the roadside radar coordinate system. Specifically, by performing polynomial fitting on the roadside coordinate data corresponding to each lane, the trajectory of the lane centerline in the roadside radar coordinate system can be obtained.

y _radar = a+b*x _radar +c*x _radar ² +d*x _radar ³

Among them, the polynomial parameters a, b, c, d in the formula can be obtained by the least square method. After obtaining the polynomial trajectory of each lane, evenly select N (N is an integer greater than 3) sampling points in each lane to realize the sampling of the lane centerline in the roadside radar coordinate system, and obtain N roadsides for each lane centerline radar coordinates

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

The positioning coordinate system refers to the coordinate system that realizes the positioning function. For example, the positioning coordinate system can be the GPS coordinate system that realizes GPS positioning. The GPS coordinate system is the WGS-84 coordinate system (World Geodetic System 1984 Coordinate System, an The positioning coordinate system can also be the Beidou coordinate system for realizing Beidou positioning, or the GLONASS coordinate system.

In one embodiment, the first positioning coordinate information of the lane center line in the positioning coordinate system is obtained from the high-precision map. At present, the domestic high-precision map adopts the OpenDRIVE format standard, and the OpenDRIVE format standard contains the WGS-84 coordinates corresponding to the centerline of each lane or virtual lane (intersection).

In one embodiment, the first positioning coordinate information of the lane center line in the positioning coordinate system obtained by the positioning vehicle traveling in each lane is acquired. Positioning vehicles with positioning functions, such as connected vehicles with RTK positioning function, can use the connected vehicles with RTK positioning function to drive once in each lane to obtain the WGS-84 coordinates of the center line of each lane (including longitude and latitude) .

Step 210: Perform parameter calibration on the roadside radar according to the radar coordinate information of the lane center line and the first positioning coordinate information.

Specifically, the radar coordinate information is the representation of the lane centerline in the roadside radar coordinate system, and the first positioning coordinate information is the representation of the lane centerline in the positioning coordinate system. According to the mapping relationship between the two, the roadside can be realized. The radar is calibrated relative to the parameters of the positioning system, so that the position information of the target collected by the roadside radar can be converted into 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, roadside radar calibration is ultimately to obtain the positioning position of the target (such as GPS positioning)

Specifically, according to the radar coordinate information, the coordinate point of the lane center line is converted to the positioning coordinate system, and the positioning coordinate point of the coordinate point after the conversion of the positioning coordinate system is obtained; after the conversion to the positioning coordinate system, in the first positioning coordinate information Obtain the first positioning coordinate point closest to the converted coordinate point; with the goal of minimizing the distance between the converted positioning coordinate point and the first positioning coordinate point, the calibration parameters of the roadside radar are obtained.

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

in,

Represents the x-coordinate and y-coordinate of the radar coordinate point of the ith point of the lane center line, the unit is m, lon _i represents the longitude in the positioning coordinate system mapped by the ith radar coordinate point of the lane center line, the unit is deg; lat _i Indicates the latitude in the positioning coordinate system of the ith radar coordinate mapping of the lane centerline, 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 parameter x=[a ₁ b ₁ c ₁ a ₂ b ₂ c ₂ ] in the above formula, so that the radar coordinates of the lane center line correspond to the first positioning coordinate information.

Specifically, the objective function of the following objectives is defined:

or

in,

is the point of the lane center line in the radar coordinate data obtained by the mapping relationship calculation after the transformation of the positioning coordinate system to locate the coordinate point,

Position the coordinates for the transformed point

A positioning coordinate point (including longitude and latitude) closest to the lane center line, that is, the first positioning point coordinate point, N is the total number of road radar coordinates corresponding to each selected lane center line, and M is the total number of lanes.

At the same time, the parameters of the objective function need to meet the following distance constraints: the distance difference between the first distance and the second distance satisfies the distance deviation threshold, and the first distance is the difference between the converted positioning point and the positioning coordinate point of the roadside radar in the positioning coordinate system. Distance; the second distance is the distance between the center line of the lane in the radar coordinate system and the radar coordinate point of the radar.

The distance constraints are specifically:

in,

Represents the second distance, that is, the distance from the ith radar coordinate point of the lane center line to the radar, in m, and gps _r is the positioning coordinate point (including longitude and latitude) of the roadside radar position in the positioning coordinate system. Obtained through GPS acquisition tool when the radar is installed.

Indicates the first distance, that is, the distance between the converted 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 thresholds of the distance deviation, respectively, which are adjusted according to the actual situation.

Through the above objective function and distance constraints, nonlinear optimization methods (such as effective set method, sequential quadratic programming method, interior point method, genetic algorithm, particle swarm optimization, etc.) can be used to solve the optimal roadside radar calibration parameter x, so that The mapping relationship between the roadside radar coordinate system and the positioning coordinate system is obtained, and the roadside radar calibration is realized. This method can be applied to the calibration of roadside lidar, or the calibration of roadside millimeter-wave radar.

The above roadside radar calibration method, based on the vehicle driving coordinate data collected by the roadside radar, fits the radar coordinate information of the lane center line in the radar coordinate system, and obtains the first positioning coordinate information of the lane center line in the positioning coordinate information. The coordinate information of the lane line in the two coordinate systems is used to calibrate the parameters of the roadside radar. 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 to assist other calibration objects, so it can be directly processed by the radar data of ordinary vehicles. , the method is simple and convenient.

In practical applications, there are roadside radars and other roadside sensors calibration parameters during installation due to damage and replacement, vibration and unstable installation, thermal expansion and contraction in smart high-speed projects and urban intersection intelligent projects. It cannot be applied to the situation after the sensor changes, resulting in a large position error of the sensor detection target, which affects the effect of multi-sensor fusion. With the method of the present application, when the roadside radar needs to be re-calibrated due to re-installation, loosening, 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 of the road section. The information can realize the calibration of roadside radar.

It should be understood that although the various steps in the flowchart of FIG. 2 are shown in sequence according to the arrows, these steps are not necessarily executed in the sequence shown by the arrows. Unless explicitly stated herein, the execution of these steps is not strictly limited to the order, and these steps may be performed in other orders. Moreover, at least a part of the steps in FIG. 2 may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but may be executed at different times, and the execution sequence of these steps or stages is also It does not have to be performed sequentially, but may be performed alternately or alternately with other steps or at least a portion of the steps or stages within the other steps.

In one embodiment, as shown in FIG. 6, a roadside radar calibration device is provided, including:

The acquisition module 602 is used for acquiring the vehicle traveling coordinate data on the road for a period of time collected by the roadside radar;

A lane data extraction module 604, configured to extract vehicle travel coordinate data on each lane from the vehicle travel coordinate data;

The fitting module 606 is used for fitting the vehicle driving coordinate data on each lane to obtain the radar coordinate information of the lane center line in the radar coordinate system;

a positioning information obtaining module 608, configured to obtain the first positioning coordinate information of the lane center line in the positioning coordinate system;

The calibration module 610 is configured to perform parameter calibration on the roadside radar according to the radar coordinate information of the lane center line and the first positioning coordinate information.

The above roadside radar calibration device, based on the vehicle driving coordinate data collected by the roadside radar, fits to obtain the radar coordinate information of the lane center line in the radar coordinate system, and obtains the first positioning coordinate information of the lane center line in the positioning coordinate information. The coordinate information of the line in the two coordinate systems is used to calibrate the parameters of the roadside radar. 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 to assist other calibration objects, so it can be directly processed by the radar data of ordinary vehicles. , the method is simple and convenient.

In another embodiment, a lane data extraction module is configured to obtain an area of interest in the vehicle driving coordinate data delineated according to the distribution characteristics of the lane and the coordinate changes of vehicle driving, and the area of interest corresponds to the lane area; area, and extract the vehicle travel coordinate data on each lane.

In another embodiment, the positioning information obtaining module is configured to obtain the first positioning coordinate information of the lane center line in the positioning coordinate system from the high-precision map.

In another embodiment, the positioning information acquisition module is configured to acquire the first positioning coordinate information of the center line of the lane in the positioning coordinate system obtained by the positioning vehicle traveling in each lane and collecting.

In another embodiment, the fitting module is configured 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; the lane centerline is in the roadside radar coordinates The trajectory in the system is sampled to obtain the radar coordinate information of the lane center line in the roadside radar coordinate system.

In another embodiment, the calibration module is configured to convert the coordinate point of the lane center line to the positioning coordinate system according to the radar coordinate information, and obtain the positioning coordinate point of the coordinate point after the conversion of the positioning coordinate system; The first positioning coordinate point closest to the converted coordinate point is obtained from the information; the calibration parameters of the roadside radar are obtained with the goal of minimizing the distance between the converted positioning coordinate point and the first positioning coordinate point.

Wherein, the objective function of the target satisfies the following constraints: the distance difference between the first distance and the second distance satisfies the distance deviation threshold, and 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 and the radar of the lane center line in the radar coordinate system.

For the specific limitation of the roadside radar calibration device, reference may be made to the definition of the roadside radar calibration method above, which will not be repeated here. Each module in the above-mentioned roadside radar calibration device may be implemented in whole or in part by software, hardware and combinations thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of the above-mentioned modules.

In one embodiment, a computer device is provided, the computer device may be an edge computing unit, and an internal structure diagram of which may be shown in FIG. 7 . The computer device includes a processor, memory, and a communication interface connected by 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, an internal memory. The nonvolatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the execution of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for wired or wireless communication with an external terminal, and the wireless communication can be realized by WIFI, operator network, NFC (Near Field Communication) or other technologies. The computer program, when executed by the processor, implements a roadside radar calibration method.

Those skilled in the art can understand that the structure shown in FIG. 7 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided, including a memory and a processor, where a computer program is stored in the memory, and the processor implements the methods of the foregoing embodiments when the processor executes the computer program.

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, implements the methods of the foregoing embodiments.

Those skilled in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing 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 may include the processes of the above-mentioned method embodiments. Wherein, any reference to memory, storage, database or other media used in the various embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, or optical memory, and the like. Volatile memory may 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 (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM).

The technical features of the above embodiments can be combined arbitrarily. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features It is considered to be the range described in this specification.

The above examples only represent several embodiments of the present application, and the descriptions thereof are relatively specific and detailed, but should not be construed as a limitation on the scope of the invention patent. It should be pointed out that for those skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the scope of protection of the patent of the present application shall be subject to the appended claims.

Claims

A roadside radar calibration method, the method comprising:

Obtain the vehicle driving coordinate data on the road for a period of time collected by the 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 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 system;

The parameters of the roadside radar are calibrated according to the radar coordinate information of the lane center line and the first positioning coordinate information.
The method according to claim 1, wherein extracting the vehicle driving coordinate data on each lane from the vehicle driving coordinate data comprises:

acquiring an area of interest in the vehicle driving coordinate data delineated according to the distribution characteristics of the lanes and the coordinate changes of the vehicle driving, and the area of interest corresponds to the lane area;

According to the region of interest, the vehicle travel coordinate data on each lane is extracted.
The method according to claim 1, wherein the obtaining the first positioning coordinate information of the lane center line in the positioning coordinate system comprises:

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

The first positioning coordinate information of the lane center line in the positioning coordinate system obtained by the positioning vehicle traveling in each lane is acquired.
The method according to claim 1, wherein 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, comprising:

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;

Sampling the trajectory of the lane center line in the roadside radar coordinate system to obtain radar coordinate information of the lane center line in the roadside radar coordinate system.
The method according to claim 1, wherein the parameter calibration of the roadside radar according to the radar coordinate information of the lane center line and the first positioning coordinate information comprises:

According to the radar coordinate information, the coordinate point of the lane center line is converted to the positioning coordinate system, and the positioning coordinate point of the coordinate point after the conversion of the positioning coordinate system is obtained;

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

The calibration parameters of the roadside radar are obtained with the goal of minimizing the distance between the transformed positioning coordinate point and the first positioning coordinate point.
The method according to claim 6, wherein the objective function of the target satisfies the following constraints: the distance difference between the first distance and the second distance satisfies a distance deviation threshold, and the first distance is the converted The distance between the 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 and the radar of the lane center line in the radar coordinate system.
A roadside radar calibration device, characterized in that the device comprises:

The acquisition module is used to acquire the vehicle traveling coordinate data on the road for a period of time collected by the roadside radar;

a lane data extraction module for extracting vehicle travel coordinate data on each lane from the vehicle travel coordinate data;

a fitting module, used for fitting the vehicle driving coordinate data on each lane to obtain the radar coordinate information of the lane center line in the radar coordinate system;

a positioning information acquisition module, used for acquiring the first positioning coordinate information of the lane center line in the positioning coordinate system;

A calibration module, configured to perform parameter calibration on the roadside radar according to the radar coordinate information of the lane center line and the first positioning coordinate information.
A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, when the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
A computer-readable storage medium on which a computer program is stored, 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 7 are implemented.