Design of Binocular Stereo Vision System with Parallel Optical Axesand Image 3D Reconstruction

Abstract

A binocular stereo vision system with parallel optical axes is established based on binocular stereo vision basic principle and parallel optical axes stereo vision model. The camera internal and external parameters are obtained based on the Tsai two-step calibration method. The image is preprocessed by using the Laplacian of Gaussian filter operator. The disparity map is obtained by using the constraint area-based stereo matching algorithm. According to the depth information from the parallax map, the three-dimensional reconstruction of the tree image is completed.