A noise robust method for segmentation of moving objects in video sequences

Abstract

An algorithm for automatic, noise robust segmentation of moving objects in image sequences is presented. Such algorithms are required for object-based coding techniques like the upcoming ISO/MPEG-4 standard. In a first step, a mask of changed image areas is estimated by a local thresholding relaxation technique. Then, areas of uncovered background are removed from this mask, taking into account an estimated displacement vector field. The resulting object mask is finally improved by applying a grey-level edge adaptation and an object mask memory. The algorithm is compared to a global thresholding technique which is known from the literature. Experimental results show the improvement of the estimated object masks.