External parameter calibration method, device and equipment and storage medium

Abstract

The invention provides an external parameter calibration method, device and equipment, and a storage medium, relates to the technical field of automatic driving, and is mainly used for calibration of a laser radar and a camera in scene analysis. The method comprises the following steps: acquiring laser feature point clouds from the 0th frame to the Nth frame; converting the laser coordinates of the laser feature point clouds from the first frame to the (N-1) th frame into the laser coordinates of the laser feature point cloud of the Nth frame; converting the laser feature point cloud with the laser coordinate of the Nth frame into a laser feature point cloud with a camera coordinate, converting the laser feature point cloud with the camera coordinate into a laser feature point cloud with a pixel coordinate, and displaying the laser feature point cloud with the pixel coordinate; and when the laser feature point cloud displayed by the pixel coordinates and the image pixel points of the pixel coordinates are displayed to coincide within a preset error, generating an external parameter matrix between the laser coordinates and the pixel coordinates. According to the method, the external parameter calibration cost of the laser radar and the camera can be reduced, and the external parameter calibration precision can be improved.

Description

technical field [0001] The present application relates to the field of automatic driving technology, and in particular to an external parameter calibration method, device and equipment, and a storage medium, which can be applied to scenes such as ports, expressways, logistics, mines, closed parks, or urban traffic. Background technique [0002] In areas such as autonomous driving, robotics, and 3D scene reconstruction, scene analysis is often required. The more and more used scenario for scene analysis is to use multi-camera sensors and multi-laser sensors to capture the same scene data, then fuse scene data from different sources, and analyze the scene through the fused scene data to improve the effect of scene analysis. For example, self-driving cars rely on various sensors to perceive the environment. Among the various sensors, lidar is used for obstacle distance measurement, and cameras are used to perceive information such as the color and texture of obstacles. By fusin...

AI Technical Summary

Problems solved by technology

[0004] However, this external parameter calibration scheme uses scene characteristics as the medium, and it is easy to introduce indirect errors to affect the accuracy of external parameter calibration. At the same time, the cost of building a specific calibration scene is also high.

Images