Extraction des objets en mouvement : une approche mixte contours-régions

In this paper, we propose a new method to extract moving objects from a video stream without any motion estimation. The objective is to obtain a fast and efficient extraction method, robust to noise and large motions. Our approach consists in a frame differencing strategy combined with a hierarchical segmentation approach. First, we propose to extract moving edges with a new difference scheme, based on the spatial gradient of successive frames. In the second stage, the moving regions are extracted from previously detected moving edges by using the hierarchical segmentation. The obtained moving objects description is represented as a region adjacency graph. The method is validated on real sequences in the context of videosurveillance, assuming a static camera hypothesis.