Spatio-Temporal Robust Motion Estimation and Segmentation

In this paper, a general spatio-temporal framework for motion estimation is presented. It allows to estimate a fully parametric motion model over an image sequence. As parametric models describe one motion only, a robust estimator is introduced in order to cope with several moving objects. The motion segmentation algorithm combines luminance and the composition of all the motions detected over a set of successive frames for motion boundaries estimation.

[1]  P. Rousseeuw,et al.  Unmasking Multivariate Outliers and Leverage Points , 1990 .

[2]  G. Bluman,et al.  Symmetries and differential equations , 1989 .

[3]  W. B. Thompson,et al.  Combining motion and contrast for segmentation , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Benoît Duc,et al.  Motion estimation using invariance under group transformations , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[5]  P. Anandan,et al.  Hierarchical Model-Based Motion Estimation , 1992, ECCV.

[6]  Michael J. Black.  Combining Intensity and Motion for Incremental Segmentation and Tracking Over Long Image Sequences , 1992, ECCV.

[7]  Peter J. Rousseeuw,et al.  Robust regression and outlier detection , 1987 .

[8]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.