Effective covariance tracker based on adaptive changing of tracking window

In this paper, we present an effective covariance tracking algorithm based on adaptive size changing of tracking window. Recent researches have advocated the use of a covariance matrix of object image features for tracking objects instead of the conventional histogram object representation models used in popular algorithms. The general covariance tracking algorithm has some problem of scale change of moving objects. Since the scale of the moving object often changes in time, the tracking(or object) window should be updated accordingly. In addition, the covariance matrix of moving objects should be adaptively changed considering the tracking window size. We propose a novel solution to this problem by segmenting the moving object from the background pixels in the tracking window. The proposed method will improve the tracking performance of the conventional covariance tracking. Our several simulations prove the effectiveness of the proposed one.