Stereo Matching for Slanted Plane

In this paper, two new energy functions are presented to handle the slanted plane. First, the gradient information is used to get the initial disparity in a local energy function. Second, a global energy function is incorporating segment geometric constraints. To overcome the fronto-parallel model errors, the segment adjacent segments cooperative optimization is used to infer the unreliable pixel disparity. Our method not only uses the color constancy constraint and first, second gradient information, but also incorporates the segment prior geometric coherence constraint. Experimental results on more challenging dataset demonstrate the good performance of the proposed method.