Object tracking via dense SIFT features and low-rank representation.

In this paper, we present a low-rank sparse tracking method which builds upon the particle filtering framework. The proposed method learns the local dense scale-invariant feature transform features corresponding to candidate samples jointly by exploiting the underlying sparse and low-rank constraints. Furthermore, the alternating direction method of multipliers method guarantees the optimization equation can be solved accurately and robustly. We evaluate our proposed tracking method against 9 state-of-the-art trackers on a set of 64 challenging sequences. Experimental results show that the proposed method performs favorably against state-of-the-art trackers in terms of accuracy. [ABSTRACT FROM AUTHOR]