Abstract

A method for camera calibration in robotic binocular stereo vision is introduced in this paper. Camera calibration is a necessary step in 3D computer vision in order to extract metric information from 2D images. Being different from with single camera calibration, binocular stereo vision system not only need to ascertain intrinsic parameters, but also the relative position relation of two cameras. We compute it in two steps: first, we compute the intrinsic and initial extrinsic parameters of camera by Zhang Plane-based Calibration Method; Second, we suppose the intrinsic parameter is invariable, camera's moving parameters can be computed by self-calibration method, through finding the stereo matching point and calculating the fundamental matrix and essential matrix.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call