Large Occlusion

A method for solving the stereo matching problem in the presence of large occlusion is presented. A data structure | the disparity space image | is de ned to facilitate the description of the e ects of occlusion on the stereo matching process and in particular on dynammic programming (DP) solutions that nd matches and occlusions simultaneously. We signi cantly improve upon existing DP stereo matching methods by showing that while some cost must be assigned to unmatched pixels, sensitivity to occlusion-cost and algorithmic complexity can be signi cantly reduced when highlyreliable matches, or ground control points, are incorporated into the matching process. The use of ground control points eliminates both the need for biasing the process towards a smooth solution and the task of selecting critical prior probabilities describing image formation. Finally, we describe how the detection of intensity edges can be used to bias the recovered solution such that occlusion boundaries will tend to be proposed along such edges, re ecting the observation that occlusion boundaries usually cause intensity discontinuities.