Heuristic search approach to shape matching in image sequences

The problem of detecting correspondences between object contours belonging to successive image frames of a dynamic scene is addressed. The object contours are represented using concave, convex, and straight line segments which are extracted after smoothing the contour with a Gaussian kernel. The matching problem is tackled using heuristic search with a state space formulation. An admissible heuristic function is designed for guiding the search. Experimental results are presented to demonstrate the capabilities of the method.