Abstract

This paper defines a temporal continuity constraint that expresses assumptions about the evolution of 2D image velocity, or optical flow, over a sequence of images. Temporal continuity is exploited to develop an incremental minimization framework that extends the minimization of a non-convex objective function over time. Within this framework this paper describes an incremental continuation method for recursive non-linear estimation that robustly and adaptively recovers optical flow with motion discontinuities over an image sequence.

Citations

621	Visual reconstruction - Blake, Zisserman - 1987
459	Spatiotemporal energy models for the perception of motion - Adelson, B - 1985
185	Epipolar-plane image analysis: An approach to determining structure from motion - Bolles, Baker, et al. - 1987
128	Scene segmentation from visual motion using global optimization - Murray, Buxton - 1987
86	Robust dynamic motion estimation over time - Black, Anandan - 1991
68	Robust incremental optical flow - Black - 1992
48	Performance of optical ow techniques - Barron, Fleet, et al. - 1992
15	Robust Statistics: The Approach based on In uence Functions - Hampel, Ronchetti, et al. - 1986
15	Temporal surface reconstruction - Heel - 1991
11	A framework for robust estimation of optical #ow - Black, Anandan - 1993
6	Incremental estimation of image- ow using a kalman lter - Singh - 1991
1	Robust computation of optical ow inamulit-scale di erential framework - Weber, Malik - 1993