A Stereo Matching Algorithm Based on Four-Moded Census and Relative Confidence Plane Fitting

A four-moded Census transform stereo matching algorithm using bidirectional constraint dynamic programming and relative confidence plane fitting is proposed to solve the problems of matching quality. Using the four-moded Census transform which adds a restrictive condition replaces traditional Census transform to improve matching accuracy and mean value of all pixels intensity replaces the center pixel intensity in the Census window to solve the problem of the center pixel distortion effectively, a refined initial local matching cost can be obtained. During the disparity optimization, the difficulty of disparity computation in textureless areas is overcome by the estimated condition and defined relative confident pixels. Experiment results show that a better dense matching map can be obtained by the proposed algorithm.