Stereo matching algorithm based on adaptive weight and local entropy
Tian Chen, Wenguo Li · 2017
Stereo matching is one of the research directions of binocular stereo vision system. In this paper, a novel adaptive local stereo matching algorithm is proposed. Firstly, the cost function calculation is redefined according to the gray similarity and the spatial similarity. Then, the data smoothing term is introduced and the penalty coefficient is determined by the local entropy of the image. Finally, the initial disparity map of the cost aggregation is analyzed by using the left-right consistency check and weight median filter to perform disparity refinement. The algorithm uses four international standard stereo image pairs provided by Middlebury website. The experiment shows that the proposed algorithm can get more accurate disparity map.