Joint calibration method and system and calibration board

Abstract

The invention provides a joint calibration method and system and a calibration board, and belongs to the technical field of multi-sensor data fusion. The joint calibration method comprises the steps: firstly, adopting a laser radar to scan the calibration board to obtain original laser point cloud data, carrying out filtering and cross denoising processing on original laser point cloud data to obtain cross point cloud data, then extracting edge points of the cross point cloud data, obtaining a pose transformation matrix according to the edge points, and obtaining space coordinates of a circle center through the pose transformation matrix; and finally, obtaining the pose of the camera according to the space coordinate of the circle center and the ellipse center pixel coordinate obtained by detecting the calibration plate picture. According to the invention, the original laser point cloud data is subjected to filtering and cross denoising processing, so that the point cloud data, partially deviating from a real plane, of the laser radar due to the influence of materials, structures or noise and the like can be effectively removed, and the pose calibration precision is greatly improved.

Description

technical field [0001] The invention belongs to the technical field of multi-sensor data fusion, and more specifically relates to a joint calibration method, system and calibration board. Background technique [0002] Lidar and cameras are widely used in areas such as autonomous driving, 3D reconstruction, object detection, autonomous navigation, and remote sensing. These applications have high requirements for the reliability of surrounding perception. The three-dimensional space information of the target can be quickly obtained through the lidar; the camera can obtain high-quality two-dimensional images containing information such as various surface features, colors, and textures of the target. Therefore, the robustness of lidar to lighting makes up for the lack of cameras that are seriously affected by lighting conditions. On the contrary, the rich texture and high frame rate of the camera make up for the inherent low spatial resolution of lidar, so the two are very comp...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a joint calibration method, system and calibration board, aiming to solve the problems of insufficient calibration accuracy and large errors in the laser radar-camera system in the prior art

Images