Stereo Matching for Slanted and Low Texture Plane: A Reliability Confidence Inference Approach

The aim of the stereo matching is to get the accurate disparity. But for the slanted and low textured plane, the ambiguity is increased. To get the more accurate disparity, most constraints are applied. In this paper, the statistical probability method (SPT) is applied to inferring disparity. The reliable confidence (RC) based on the SPT measures how the pixel disparity is reliable. The unreliable disparity of the pixel is inferred from reliable disparity through adjacent segment cooperative optimization. The adjacent segment geometric constraint and gradient information are incorporated into two new local and global energy functions respectively. Experimental results demonstrate the good performance of the proposed method.