CN-121982110-A - External parameter calibration method and device for road side camera, electronic equipment and storage medium

CN121982110ACN 121982110 ACN121982110 ACN 121982110ACN-121982110-A

Abstract

The application discloses an external parameter calibration method and device for a road side camera, electronic equipment and a storage medium, and belongs to the technical field of camera calibration. The method comprises the steps of obtaining image coordinates, high-precision positioning coordinates and a course angle of a target vehicle, wherein the image coordinates are determined by detecting the target vehicle from a vehicle image acquired by a camera to be calibrated, the high-precision positioning coordinates are acquired by high-precision positioning equipment arranged on the target vehicle, determining target geographic coordinates corresponding to the image coordinates according to the high-precision positioning coordinates, the course angle and the relative position relation between the high-precision positioning equipment and the target vehicle, and calibrating external parameters of the camera to be calibrated according to a data pair consisting of the image coordinates and the target geographic coordinates. The application can improve the calibration precision of the external parameters of the camera.

Inventors

LI YANXI
YU ZHONGTENG
XU WENLONG
CHEN JUNJIANG
BAO KEXIN

Assignees

中信科智联科技有限公司

Dates

Publication Date: 20260505
Application Date: 20251212

Claims (10)

1. The external parameter calibration method of the road side camera is characterized by comprising the following steps of: Acquiring image coordinates, high-precision positioning coordinates and course angles of a target vehicle, wherein the image coordinates are determined by detecting the target vehicle from a vehicle image acquired by a camera to be calibrated, and the high-precision positioning coordinates are acquired by high-precision positioning equipment configured on the target vehicle; determining a target geographic coordinate corresponding to the image coordinate according to the high-precision positioning coordinate, the course angle and the relative position relation between the high-precision positioning equipment and the target vehicle; And performing external parameter calibration on the camera to be calibrated according to the data pair consisting of the image coordinates and the target geographic coordinates.
2. The method of claim 1, wherein the determining the target geographic coordinates corresponding to the image coordinates based on the high-definition location coordinates, the heading angle, and the relative positional relationship of the high-definition location device and the target vehicle comprises: determining a boundary model of the target vehicle under a geographic coordinate system according to the high-precision positioning coordinates, the course angle, the size of the target vehicle and the relative position relation; and determining target geographic coordinates corresponding to the image coordinates from the boundary model.
3. The method of claim 2, wherein the determining a boundary model of the target vehicle in a geographic coordinate system based on the high-precision positioning coordinates, the heading angle, the size of the target vehicle, and the relative positional relationship comprises: Determining a first chassis center point coordinate of the target vehicle according to the high-precision positioning coordinate, the course angle and the relative position relation; and determining a boundary model of the target vehicle under a geographic coordinate system according to the size, the course angle and the first chassis center point coordinate.
4. A method according to claim 2 or 3, wherein the image coordinates are the lower edge centre point coordinates of a 2D detection frame; The determining the target geographic coordinates corresponding to the image coordinates from the boundary model comprises: and determining a target point with the minimum distance between the target point and the position coordinate from the boundary model according to the position coordinate of the camera to be calibrated, and taking the geographic coordinate of the target point as the target geographic coordinate.
5. The method according to claim 4, wherein determining the target point with the smallest distance to the position coordinates from the boundary model according to the position coordinates of the camera to be calibrated comprises: And constructing a connecting line between the position coordinates and the central point coordinates of the boundary model, determining an intersection point of the normal line of the connecting line and the boundary model, and determining the intersection point with the smallest distance between the intersection point and the position coordinates as the target point.
6. A method according to claim 2 or 3, wherein the image coordinates are second chassis centre point coordinates of a 3D detection frame; The determining the target geographic coordinates corresponding to the image coordinates from the boundary model comprises: and determining the center point coordinates of the boundary model, and determining the center point coordinates as the target geographic coordinates.
7. The method of claim 1, wherein the image coordinates are second chassis center coordinates of a 3D inspection box; The determining the target geographic coordinate corresponding to the image coordinate according to the high-precision positioning coordinate, the course angle and the relative position relation between the high-precision positioning device and the target vehicle comprises the following steps: Determining a first chassis center point coordinate of the target vehicle according to the high-precision positioning coordinate, the course angle and the relative position relation; And determining the first chassis center point coordinate as the target geographic coordinate.
8. An external parameter calibration device of a road side camera is characterized by comprising: The system comprises an acquisition module, a calibration module and a calibration module, wherein the acquisition module is used for acquiring image coordinates, high-precision positioning coordinates and course angles of a target vehicle, the image coordinates are determined by detecting the target vehicle from a vehicle image acquired by a camera to be calibrated, and the high-precision positioning coordinates are acquired by high-precision positioning equipment configured on the target vehicle; The geographic coordinate determining module is used for determining target geographic coordinates corresponding to the image coordinates according to the high-precision positioning coordinates, the course angle and the relative position relation between the high-precision positioning equipment and the target vehicle; And the external parameter calibration module is used for performing external parameter calibration on the camera to be calibrated according to the data pair consisting of the image coordinates and the target geographic coordinates.
9. An electronic device comprising a processor, a memory and a program or instruction stored on the memory and executable on the processor, which when executed by the processor, implements the steps of the method for calibrating a road side camera according to any of claims 1-7.
10. A readable storage medium, wherein a program or instructions is stored on the readable storage medium, which when executed by a processor, implements the steps of the method for calibrating a road side camera according to any of claims 1-7.

Description

External parameter calibration method and device for road side camera, electronic equipment and storage medium Technical Field The application belongs to the technical field of camera calibration, and particularly relates to an external parameter calibration method and device for a road side camera, electronic equipment and a storage medium. Background The road side sensing system is a core component of vehicle-road coordination and intelligent traffic, and the sensing precision of the road side sensing system is highly dependent on the calibration accuracy of camera external parameters (namely the conversion relation between a camera coordinate system and a geographic coordinate system). At present, the main stream of calibration point set acquisition modes is a vehicle driving dotting method, namely, a vehicle carrying high-precision positioning equipment is driven in a camera view field, and image coordinates and geographic coordinates of the vehicle are synchronously acquired and used for calculating an external parameter matrix. In the prior art, when the road side camera external parameter calibration is performed, the vehicle image acquired by the camera can be detected by adopting a 2D target detection algorithm or a 3D target detection algorithm. As shown in fig. 1, a vehicle in a vehicle image is identified through a 2D target detection algorithm (such as YOLO and the like), a 2D detection frame is acquired, the center point of the lower edge of the detection frame is taken as an image coordinate reference point of the vehicle, and meanwhile, geographic coordinates measured by vehicle RTK equipment at the moment are acquired through time synchronization, and the two coordinates are directly paired for external parameter calculation. As shown in fig. 2, a 3D bounding box of the vehicle in the image is acquired by adopting a 3D object detection algorithm, and a chassis center point of the 3D bounding box is used as an image coordinate reference point of the vehicle. Also, the image coordinate reference point is paired with the geographic coordinates measured by the RTK device. The corresponding relation between the image coordinates and the geographic coordinate reference points in the physical world is ignored in the prior art, so that the calibration precision of the external parameters of the camera is insufficient. The center point of the lower edge of the 2D detection frame actually corresponds to the midpoint position of the contact line between the lower edge of the rectangular detection frame and the ground in the picture of the vehicle, the RTK point is only a mounting point of high-precision positioning equipment, the two points are separated in space, and fundamental system errors can be introduced by direct pairing, so that the calibration precision of the external parameters of the camera is insufficient. Based on the coordinate registration of the 3D bounding box, due to the possible deviation in the RTK installation process, the position deviation exists between the chassis center point of the 3D bounding box and the image coordinate reference point, and the camera external parameter calibration precision is affected. Disclosure of Invention The embodiment of the application aims to provide an external parameter calibration method and device for a road side camera, electronic equipment and a storage medium, which can solve the problem of insufficient external parameter calibration precision of the camera. In order to solve the technical problems, the application is realized as follows: In a first aspect, an embodiment of the present application provides an external parameter calibration method for a roadside camera, where the method includes: Acquiring image coordinates, high-precision positioning coordinates and course angles of a target vehicle, wherein the image coordinates are determined by detecting the target vehicle from a vehicle image acquired by a camera to be calibrated, and the high-precision positioning coordinates are acquired by high-precision positioning equipment configured on the target vehicle; determining a target geographic coordinate corresponding to the image coordinate according to the high-precision positioning coordinate, the course angle and the relative position relation between the high-precision positioning equipment and the target vehicle; And performing external parameter calibration on the camera to be calibrated according to the data pair consisting of the image coordinates and the target geographic coordinates. In a second aspect, an embodiment of the present application provides an external parameter calibration device for a roadside camera, including: The system comprises an acquisition module, a calibration module and a calibration module, wherein the acquisition module is used for acquiring image coordinates, high-precision positioning coordinates and course angles of a target vehicle, the image coordinates are determined by detecting the target