Multi-features guided robust visual tracking

This paper focuses on dealing with the tracking challenges such as target occlusion and deformation. It proposes a new tracking method via extracting and evaluating multi-features for both target region and its adjacent surroundings. The multi-features separately describe the key factors to detect target including the color feature, the shape and contour feature, and the distributions of structure and intensity described by the Pearson Correlation Coefficient. These multi-features are proposed as the basic representation of target template and candidates and used to define a matching algorithm between them. The best matched candidate is taken as the final tracking result. To improve the efficiency of target template and candidates, the region of importance (ROI) for target is proposed by evaluating the distribution of salient values on many extended regions. The ROIs produce more accurate regions to form target template and candidates. Finally, a new template update method is defined based on the precision of tracked result to adapt to target state and achieve the follow target tracking. Using 25 videos in visual tracking benchmark, we achieve the quantitative and qualitatively evaluations of 12 different trackers. Many experiments demonstrate that our tracker produces much better results than the present trackers in dealing with target occlusion, deformation, rotation, background clutters.