Occlusion adaptive motion snake

In this paper, we propose a novel technique for tracking the visible boundary of an object in an image sequence in the presence of occlusion. The proposed technique is based on a piecewise prediction and tracking scheme in which local motion and color information on both sides of the boundary are employed. The piecewise nature of the prediction scheme allows for determining if and where the tracked boundary is occluded by another object. Novel snake energy terms are also introduced to facilitate accurate snapping of the predicted boundary to the actual one in a subsequent frame. Experimental results are provided to illustrate the performance of the proposed occlusion detection algorithm and the novel snake energy terms.