Moving object tracking using an active fusion model with robustness against partial occlusions

This paper proposes an active fusion model for tracking partially occluded moving objects. The active fusion model is unified the advantages of contour-based and region-based snake that are both representative approaches used in tracking of moving objects. Although these approaches have been proposed in the literature, most of them have a common problem that tracking accuracy is remarkably decreased in the presence of occlusion. Our active fusion model adjusts the confidence of each model based on calculating amounts and locations of occlusion so that it can improve the tracking accuracy. Experimental results show that the proposed model is very effective and robust to partial occlusions, as compared to the previous methods.