Precision evaluation method and device for joint calibration parameters, server and computer readable storage medium

Abstract

The invention relates to a precision evaluation method and device for joint calibration parameters, a server and a computer readable storage medium. The method comprises the steps: mapping a point cloud corresponding to laser point cloud data to an image according to a to-be-evaluated joint calibration parameter of a laser radar relative to a camera, and obtaining a mapping point cloud; and then calculating the overlapping area of the same target between the laser point cloud target frame and the image recognition target frame on the image, and performing precision evaluation on the to-be-evaluated joint calibration parameters of the laser radar relative to the camera through the overlapping area. The larger the overlapping area is, the higher the alignment accuracy of the point cloud corresponding to the laser point cloud data and the image shot by the camera in the space is, namely, the higher the accuracy of the joint calibration parameter to be evaluated is. Therefore, by adopting the precision evaluation method for the joint calibration parameters, human eyes are not needed for judgment, the precision evaluation efficiency of the joint calibration parameters is improved, and waste of manpower and material resources is avoided.

Description

technical field [0001] The present application relates to the technical field of camera calibration, and in particular to a method and device for evaluating the accuracy of joint calibration parameters, a server, and a computer-readable storage medium. Background technique [0002] With the continuous development of automatic driving or unmanned driving technology, automatic driving or unmanned driving will gradually enter people's daily life and bring convenience to people's life. Among them, the core problem faced by automatic driving or unmanned driving technology is: the vehicle's visual perception ability is insufficient, and it cannot form a comprehensive perception of the overall road traffic environment, so that the driving safety of the vehicle cannot be fully guaranteed. [0003] In recent years, there have been solutions to improve the visual perception of vehicles through lidar and cameras. Obviously, in this scheme, the accuracy of the calibration results obtai...

AI Technical Summary

Problems solved by technology

Among them, the core problem faced by automatic driving or unmanned driving technology is: the vehicle's visual perception ability is insufficient, and it is impossible to form a comprehensive perception of the overall road traffic environment, so that the driving safety of the vehicle cannot be fully guaranteed

[0004] The traditional accuracy evaluation method often needs to use human eyes to judge the coincidence degree of the edge of the laser point cloud and the edge of the image. Obviously, the method of human eye judgment is easily affected by subjective consciousness and has low efficiency, which is a serious waste of manpower and material resources.

Images