The Robust Estimation of Multiple Motions: Parmetric and Piecewise-Smooth Flow Fields

(with P. Anandan)

Most approaches for estimating optical flow assume that, within a finite image region, only a single motion is present. This single motion assumption is violated in common situations involving transparency, depth discontinuities, independently moving objects, shadows, and specular reflections. To robustly estimate optical flow, the single motion assumption must be relaxed. This work describes a framework based on robust estimation that addresses violations of the brightness constancy and spatial smoothness assumptions caused by multiple motions. We show how the robust estimation framework can be applied to standard formulations of the optical flow problem thus reducing their sensitivity to violations of their underlying assumptions. The approach has been applied to three standard techniques for recovering optical flow: area-based regression, correlation, and regularization with motion discontinuities. This work focuses on the recovery of multiple parametric motion models within a region as well as the recovery of piecewise-smooth flow fields and provides examples with natural and synthetic image sequences.

Software available on-line

o Area-based optical flow: robust affine regression.
o Dense optical flow: robust regularization.

Related Publications

Black, M. J. and Anandan, P., The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields, Computer Vision and Image Understanding, CVIU, 63(1), pp. 75-104, Jan. 1996. (pdf).

Black, M. J. and Anandan, P., A framework for the robust estimation of optical flow, Fourth International Conf. on Computer Vision, ICCV-93, Berlin, Germany, May, 1993, pp. 231-236. (postscript)

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. 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)