A joint calibration method and computer-readable storage medium based on lidar and camera

Abstract

This application relates to a joint calibration method based on laser radar and camera and a computer-readable storage medium. The joint calibration method includes the following steps: performing edge detection on the laser radar point cloud extracted by laser radar, extracting the edge points of the background part, and using the laser The depth difference of radar points finds the foreground edge points corresponding to each background edge point, and obtains the foreground edge points closer to the edge through multiple searches and comparisons, and then extracts the lidar edge point cloud and the circle in the edge image acquired by the camera at the same time Center and radius, calculate the translation vector between the camera and the lidar through the pinhole camera model, and search the calibration parameters in the neighborhood space of the obtained translation vector to find the calibration result that minimizes the projection error, which can be extracted with high precision The laser radar scans the points on the edge of the object, avoiding the problem of insufficient accuracy caused by the low resolution of the laser radar. Through the obtained precise edge points, more accurate calibration results can be obtained.

Description

technical field [0001] The present application relates to the field of calibration, and in particular to a joint calibration method based on laser radar and camera and a computer-readable storage medium. Background technique [0002] The fusion of lidar and camera is widely used in 3D reconstruction in robot vision, autonomous navigation and positioning, and drones. A single sensor has limitations, such as cameras are susceptible to light and blurred external environments, and lidar data points are sparse, and the fusion of the two can make up for their respective shortcomings. [0003] In order to fuse the information acquired by lidar and camera, joint calibration between the two is essential. The mutual conversion relationship between the two sensor space coordinate systems is determined through calibration, so that the information obtained by different sensors can be fused into a unified coordinate system. At present, most of the joint calibration methods between multi...

AI Technical Summary

Problems solved by technology

At present, most of the joint calibration methods between multi-line lidar and camera use some calibration objects with spatial geometric characteristics, and use the depth discontinuity of lidar points at the edge to extract points with sudden distance changes as edge points for calibration. The feature points are registered with the edge information extracted from the image, but due to the influence of the resolution of the lidar, the point of the distance mutation is not exactly at the edge of the object, so the obtained calibration edge point is not accurate, which affects the calibration accuracy of results

Images