Area-Based Hierarchical Binocular Stereo Matching Algorithm

A hierarchical stereo matching algorithm with adaptive threshold is presented. The backwards matching strategy with disparity predetermined and the adaptive matching threshold updating method based on candidates matching points are two core components of the algorithm. First, found those initial match points under a predetermined disparity using an initial matching threshold. Second, updated the threshold value by analyzing statistical characteristics of those initial matching points. Then obtained reliable match points using the updated threshold, and removed false matching points by morphological filtering. Third, selected the next predetermined disparity to repeat the above operations. Finally, produced the smooth disparity map using Gaussian filtering operations. Experimental results in the standard test gallery show that the proposed algorithm is more accurate and can generate wider disparity map than traditional methods, and has better utility values.