TITLE:
Research on Stereo Matching Technology Based on Binocular Vision
AUTHORS:
Chang Su, Gongquan Tan, Yufeng Luo
KEYWORDS:
Binocular Stereo Vision, Checkerboard Calibration, Binocular Camera Calibration, Stereo Matching, Gray Scale Transformation
JOURNAL NAME:
Open Access Library Journal,
Vol.6 No.9,
September
20,
2019
ABSTRACT: With the rapid development of machine vision, binocular stereo vision based on the principle of parallax has gradually become the core of scientific re-search. This paper briefly presents the background and research significance, elaborates the research status of binocular vision robot at home and abroad and studies the checkerboard calibration method, and uses Matlab to complete binocular camera calibration. Stereo matching technology is the core and most difficult part of binocular stereoscopic 3D reconstruction research. Firstly, the image acquired after calibration is enhanced by gray scale transformation to make the image clearness optimal, and then use NCC (normalization cross-compilation). The algorithm performs the matching of left and right image pairs in the Matlab environment to generate an optimal matching disparity map.