Active Stereo Vision System Calibration Method

Abstract

The invention belongs to the technical field of service robots, and specifically relates to a calibration method for an active stereo vision system, aiming to solve the problem that it is difficult to achieve high-quality calibration when the optical centers of each camera in the active stereo vision system deviate from the corresponding rotation axis. The method includes obtaining the first image, the second image, the third image, the fourth image, the fifth image, and the sixth image; obtaining the relative poses before and after rotation of each camera of the active stereo vision system; obtaining the corresponding rotation axis of each camera The rotation vector; combined with the rotation vector and rotation angle corresponding to the rotation axis of each camera, obtain the pose of the rotation axis of each camera in the corresponding predefined initial position coordinate system; obtain the initial position of the first camera and the second camera Then the relative pose between the rotation axis of the first camera and the rotation axis of the second camera is obtained; the external parameters of the active stereo vision system are updated online. The invention improves the calibration quality of the active stereo vision system.

Description

technical field [0001] The invention belongs to the technical field of service robots, and in particular relates to an active stereo vision system calibration method. Background technique [0002] In recent years, service robots have been widely used in helping the elderly and the disabled, medical treatment, and automatic driving. The robot obtains the depth information of the scene through stereo vision, providing a solid foundation for environmental perception. To use stereo vision to perceive the environment, it is necessary to know the spatial relationship between the two cameras in the stereo vision system, which requires effective calibration of the stereo vision system to obtain the external parameters of the stereo vision system. According to whether the relative pose between the cameras is variable, the stereo vision system is divided into a fixed stereo vision system and an active stereo vision system, in which the relative pose between the cameras of the fixed st...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problem that it is difficult to achieve high-quality calibration when the optical center of each camera in the active stereo vision system deviates from the corresponding rotation axis, the present invention proposes a calibration method for the active stereo vision system , including the following steps:

Images