Fast visual object tracking via correlation filter and binary descriptors

摘要

Visual object tracking is one of the basic units in the construction of smart cities, which focuses on establishing a dynamic appearance model to represent and recognize the target in complex scenarios. In this paper, we consider visual object tracking as multiple local patches matching problem and design an online tracker based on correlation filter and binary descriptors. We integrate binary descriptors into our tracking model, which provide reliable and robust local feature information. Further, a self-adaptive decision scheme is proposed to fuse the global correlation information and the local feature descriptors. Experimental results on benchmark videos dedicate the effectiveness and robustness of our tracker.