A new contour based tracking algorithm using improved greedy snake

In this paper, we introduce a new contour based tracking method using active contour. Original greedy snake as a parametric active contour has weak performance in tracking target with high velocity and large displacement between two successive frames. This is due to concave parts of target boundary, shrinkage of contour if it is far from target boundary and the lack of target motion information. To cope with these problems we proposed a greedy snake with adaptive curvature energy and additional field energy term as an external energy. Third problem is handled by Kalman filter which is used in the proposed tracking algorithm for estimation of location of initial contour in the current frame. Several experiments on real video sequences show that our method can track target contour in successive frames perfectly and is robust against camera movements including zooming and vibrations.