Robust patch-based tracking using valid patch selection and feature fusion update

This paper proposes a robust patch-based object tracking algorithm. Unlike many traditional algorithms, which divide the object into multiple patches and allocate the weight values for each patches, this paper uses SIFT feature matching to select valid patches and filter out invalid patches. The invalid patches usually corresponding to the occluded or partially transformed part of the object. Thus, guided by valid patch, patch-based color histogram provides a richer description of the object. The similarity of valid patch is used in particle filter to locate the object. Moreover, since feature similarity is easy to bring into object drift, this paper updates the object template fusing feature similarity and valid patches, which is both scale adaptive and robust to partial occlusion. The experimental results show that the proposed algorithm is more accurate and robust than state-of-the-art tracking algorithms in challenging scenarios.