DISPARITY-BASED SEGMENTATION OF STEREOSCOPIC FOREGROUND BACKGROUND IMAGE SEQUENCES

In this contribution, we describe a method for displacement estimation in stereoscopic images, which is closely coupled with a segmentation of the pictures into homogeneously displaced regions. The technique is driven by a statistical optimization criterion which assesses the qua lity of the disparity estimate and of the segmentation, thus improving both of these simultaneously. In addition, the optimization criterion explicitly takes occluded areas into consideration. With the addition al help of two constraints, this enables the algorithm to locate regio ns corresponding to occlusions accurately.