Incremental robust local dictionary learning for visual tracking

Visual tracking is a fundamental task in computer vision. In this paper, we propose an incremental robust local dictionary learning framework to address this problem. We first initialize a dictionary using local low-rank features to represent the appearance subspace for the object. In this way, each candidate can be modeled by the sparse linear representation of the learnt dictionary. Then by incrementally updating the local dictionary and learning sparse representation for the candidate, we build a robust online object tracking system. Compared with conventional methods, which directly use corrupted observations to form the dictionary, our local low-rank features based dictionary successfully remove occlusions and exactly represent the intrinsic structure of the object. Furthermore, in contrast to the traditional holistic dictionary, the local low-rank features based dictionary contain abundant partial information and spatial information. Experimental results on challenging image sequences show that our method consistently outperforms several state-of-the-art methods.