Coarse-to-Fine Control Strategy for Matching Motion Stereo Pairs

This article proposes a slider stereo matching method, which employs a coarse-to-fine control strategy to overcome the false targets problem. At first, a stereo pair is taken at a short baseline, and a match is assigned to it. The resulting disparity map is then used to restrict search range and to predict occlusion for efficiently and reliably matching the succeeding stereo pair taken at a longer baseline. The system iterates the sliding and matching to obtain an enough disparity range.

[1]  D Marr,et al.  A computational theory of human stereo vision. , 1979, Proceedings of the Royal Society of London. Series B, Biological sciences.

[2]  Hans P. Moravec,et al.  The Stanford Cart and the CMU Rover , 1983, Proceedings of the IEEE.

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

[4]  T. Poggio,et al.  A computational theory of human stereo vision , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

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

[6]  Eric L. W. Grimson,et al.  From Images to Surfaces: A Computational Study of the Human Early Visual System , 1981 .