Spatial-temporal saliency feature extraction for robust mean-shift tracker

Robust object tracking in crowded and cluttered dynamic scenes is a very difficult task in robotic vision due to complex and changeable environment and similar features between the background and foreground. In this paper, a saliency feature extraction method is fused into mean-shift tracker to overcome above difficulties. First, a spatial-temporal saliency feature extraction method is proposed to suppress the interference of the complex background. Furthermore, we proposed a saliency evaluation method by fusing the top-down visual mechanism to enhance the tracking performance. Finally, the efficiency of the saliency features based mean-shift tracker is validated through experimental results and analysis.