Parallel binocular stereo vision measurement system based on camera calibration

Abstract

A new set of parallel binocular vision measuring system which focuses on four key parts in stereo vision is implemented in this paper. Firstly, 3D grid target camera calibration method which has higher precision was used to obtain the camera parameters. Secondly, SURF feature detection was selected to get the feature points and the matching relations. Then, in order to improve the accuracy and efficiency of the matching, epipolar constraint and symmetry test were added in the system. And, on this basis, The Mid-point method algorithm was adopted to determine the three-dimensional information of the target ultimately in the last step. Experimental results show that the proposed method can build a complete and viable binocular stereo vision measurement system, and can improve the measurement accuracy in effect.