Algorithm for Tracking of Fast Motion Objects with Adaptive Mean Shift

The classic kernel-based object tracking algorithm uses fixed kernel-bandwidth, which limits the performance when the object scale exceeds the size of the tracking window and the object fast motion. Therefor, a real-time object tracking algorithm is proposed, This algorithm gets the target´s scale using automatic selection of kernel-bandwidth based on feature matching. Based on the analysis of similarity of object kernel-histogram by object center distance-weighting, gets the target´s location by mean-shift algorithm. Experimental results show that the proposed algorithm can track successfully fast moving objects of changing in size.