A Model for the Detection of Motion over Time

(with P. Anandan)

We propose a model for the recovery of visual motion fields from image sequences. Our model exploits three constraints on the motion of a patch in the environment:

i) Data Conservation: the intensity structure corresponding to an environmental surface patch changes gradually over time;
ii) Spatial Coherence: since surfaces have spatial extent neighboring points have similar motions;
iii) Temporal Coherence: the direction and velocity of motion for a surface patch changes gradually.
The formulation of the constraints takes into account the possibility of multiple motions at a particular location. We also present a highly parallel computational model for realizing these constraints in which computation occurs locally, knowledge about the motion increases over time, and occlusion and disocclusion boundaries are estimated. An implementation of the model using a stochastic temporal updating scheme is described. Experiments with both synthetic and real imagery are presented.

Related Publications

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.

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) (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. (abstract)