Visual tracking using logistic regression and sparse representation

A novel tracking method is developed based on logistic regression classifier and sparse representation in this paper. Firstly, the logistic regression classifier with online update is utilized to determine the searched image patches belonging to the potential targets or the false targets. Through the classification, a huge number of false targets can be removed from the searched patches. Then, the sparse representation is applied to distinguish the tracked target in the current frame from the potential targets. Sparse representation improves the discrimination between potential targets which makes a contribution to the robustness of our method. The proposed method is test on challenging sequences and outperforms state-of-the-art tracking algorithms in most experimental cases.