Depth and occlusion recovery in motion stereo

Motion stereo is a convenient method for depth recovery. However, since it employs a sequence of motion images, the surface occlusion problem is exacerbated. This paper presents an improved cooperative stereo matching algorithm based on the analysis of several occlusion models, and some preliminary experimental results.

[1]  Ray A. Jarvis,et al.  A Perspective on Range Finding Techniques for Computer Vision , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  James J. Little,et al.  Direct evidence for occlusion in stereo and motion , 1990, Image Vis. Comput..

[3]  D Marr,et al.  Cooperative computation of stereo disparity. , 1976, Science.

[4]  Ramakant Nevatia,et al.  Depth measurement by motion stereo , 1976 .

[5]  David Nitzan,et al.  Three-Dimensional Vision Structure for Robot Applications , 1988, IEEE Trans. Pattern Anal. Mach. Intell..