This work 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 work develops an incremental continuation method for recursive non-linear estimation that robustly and adaptively recovers optical flow with motion discontinuities over an image sequence.
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)
Black, M. J., Combining intensity and motion for incremental segmentation and tracking over long image sequences, in Proc. Second European Conf. on Computer Vision, ECCV-92, G. Sandini (Ed.), Springer Verlag, LNCS 588, May 1992, pp. 485-493. (postscript 0.14MB), (abstract)
Black, M. J. and Anandan, P., Dynamic motion estimation and feature extraction over long image sequences, Proc. IJCAI Workshop on Dynamic Scene Understanding, Sydney, Australia, August 1991.