An Adaptive Kernel Bandwidth Mean-Shift Target Tracking Algorithm

Abstract

As the traditional Mean-Shift tracking algorithm fix the bandwidth of kernel function", "it can not effectively track the target when the scale of tracking target has a distinct change. In response to this shortage, a target tracking algorithm which combines target detection and contour tracking with Mean- Shift tracking algorithm is proposed. It uses the contour information of the real-time for the tracking target and updates adaptability the kernel bandwidth of Mean-Shift tracking algorithm. Experimental results show that the improved algorithm has a good adaptability when the scale of the target change.