An iterative motion estimation-segmentation method using watershed segments

This paper addresses the problem of segmentation of image sequences into moving objects. The segmentation (label) field is modeled by applying a Markov random field on regions provided by a watershed algorithm. The algorithm iterates between a motion estimation and a segmentation step. Temporal consistency is introduced by tracking the segmentation in time.

[1]  Christoph Stiller,et al.  Object-based estimation of dense motion fields , 1997, IEEE Trans. Image Process..

[2]  Danny De Vleeschauwer,et al.  Motion-Based Segmentation Using a Thresholded Merging Strategy on Watershed Segments , 1997, ICIP.

[3]  Nick G. Kingsbury,et al.  The recovery of a near optimal layer representation for an entire image sequence , 1997, Proceedings of International Conference on Image Processing.

[4]  A. Murat Tekalp,et al.  Digital Video Processing , 1995 .

[5]  Donald Geman,et al.  Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images , 1984 .

[6]  Edward H. Adelson,et al.  Representing moving images with layers , 1994, IEEE Trans. Image Process..

[7]  P. Holland,et al.  Robust regression using iteratively reweighted least-squares , 1977 .

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

[9]  Luc Vincent,et al.  Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Jean-Marc Odobez,et al.  Robust Multiresolution Estimation of Parametric Motion Models , 1995, J. Vis. Commun. Image Represent..

[11]  A. Murat Tekalp,et al.  An algorithm for simultaneous motion estimation and scene segmentation , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[12]  J. Besag.  On the Statistical Analysis of Dirty Pictures , 1986 .