Robust Dynamic Motion Estimation Over Time

(with P. Anandan)

Outstanding Paper Award winner at CVPR'91.

This paper presents a novel approach to incrementally estimating visual motion over a sequence of images. We start by formulating constraints on image motion to account for the possibility of multiple motions. This is achieved by exploiting the notions of weak continuity and robust statistics in the formulation of the minimization problem. The resulting objective function is non-convex. Traditional stochastic relaxation techniques for minimizing such functions prove inappropriate for the task. We present a highly parallel incremental stochastic minimization algorithm which has a number of advantages over previous approaches. The incremental nature of the scheme makes it truly dynamic and permits the detection of occlusion and disocclusion boundaries.

Related Publications

Black, M. J. and Anandan, P., Robust dynamic motion estimation over time, Proc. Computer Vision and Pattern Recognition, CVPR-91, Maui, Hawaii, June 1991, pp. 296-302. (postscript)

Black, M. J. and Anandan, P., A model for the detection of motion over time, Proc. Int. Conf. on Computer Vision, ICCV-90, Osaka, Japan, Dec. 1990, pp. 33-37; also Yale Research Report YALEU/DCS/RR-822, September 1990. (pdf), (abstract)

Black, M., Recursive non-linear estimation of discontinuous flow fields, Proc. Third European Conf. on Computer Vision, ECCV'94, J. Eklundh (Ed.), Springer Verlag, LNCS 800, Stockholm, Sweden, May 1994, pp. 138-145. (postscript, 0.8MB), (abstract)