Joint estimation-segmentation of optic flow
In this paper we address the intricate issue of jointly recovering the apparent velocity field between two consecutive frames and its underlying partition. We design a global cost functional including robust estimators. These estimators enable to deal with the large deviations occurring in the different energy terms and offer the possibility to introduce a simple coupling between a dense optical flow field and a segmentation. This coupling is also reinforced by a parametric likeness term. The resulting estimation-segmentation model thus involves a tight cooperation between a local estimation process and a global modelization. The minimization of the final cost function is conducted efficiently by a multigrid optimization algorithm.
KeywordsOptical Flow Motion Estimation Markov Random Field Motion Field Global Deformation
Unable to display preview. Download preview PDF.
- 1.E.H. Adelson and J.Y.A. Wang. Representing moving images with layers. IEEE Trans. Pattern Anal., Machine Intell., 5(3):625–638, 1994.Google Scholar
- 2.G. Adiv. Determining three-dimensional motion and structure from optical flow generated by several moving objects. IEEE Trans. Pattern Anal. Machine Intell., 7:384–401, Jul 1985.Google Scholar
- 3.S. Ayer and H.S. Sawhney. Layered representation of motion video using robust maximum-likelihood estimation of mixture models and Mdl encoding. In Proc. Int. Conf. Computer Vision, pages 777–784, June 1995.Google Scholar
- 15.E. Mémin and P. Pérez. Dense estimation and object-based segmentation of the optical flow with robust techniques. IEEE Trans. Image Processing, 5(1), 1998.Google Scholar
- 16.E. Mémin and P. Pérez. A multigrid approach for hierarchical motion estimation. In Proc. Int. Conf. Computer Vision, pages 933–938, 1998.Google Scholar