Combined motion and edge analysis for a layer-based representation of image sequences

We propose a method for the motion-congruent segmentation of image sequences based on both motion field and luminance information. In order to do so, the affine motion models are determined by analyzing the motion field through a clustering procedure, while their regions of validity are determined by an MRF-based region estimator. This last block performs a pixel-wise re-assignment of a limited number of affine models (those determined via clustering