Regularized least-square object tracking based on ?2,1 minimization

In this paper, we propose a fast and long-term object tracking algorithm using the ℓ2,1 minimization to obtain a better tracking quality. Our method is based on Regularized Least-Squares Classification (RLSC), in which the target model is updated using an online learning process during object tracking. We construct an appearance model using saliency map, image intensity and position of the target and its surrounding regions. The Fourier analysis is adopted for fast learning and saliency map detection in this work. The proposed tracking algorithm runs at 165 frames-per-second(FPS) in MATLAB on an i5 machine. Extensive experimental results on challenging image sequences demonstrate the efficiency, accuracy and robustness of the proposed tracker in comparison with state-of-the-arts methods.