Extraction of layers of similar motion through combinatorial techniques

Abstract : In this paper we present a new technique to extract layers in a video sequence. To this end, we assume that the observed scene is composed of several transparent layers, that their motion in the 2D plane can be approximated with an affine model. The objective of our approach is the estimation of these motion models as well as the estimation of their support in the image domain. Our technique is based on an iterative process that integrates robust motion estimation, MRF-based formulation, combinatorial optimization and the use of visual as well as motion features to recover the parameters of the motion models as well as their support layers. Special handling of occlusions as well as adaptive techniques to detect new objects in the scene are also considered. Promising results demonstrate the potentials of our approach.