Tracking Based on SURF and Superpixel

In this paper we present a novel algorithm for object tracking in video sequence based on SURF key-point and super pixel. SURF key-point is very effective for object matching between two images and we can use it to locate object by and large. But only in this way it can´t guarantee the success of object tracking because many available key-points are un-matched and can´t be used to locate the object. In order to solve this problem we take the advantage of super pixel to obtain more available key-points based on its property that all points in the same super pixel region belong to the same object. At last we construct a weight map for each frame to refine the location of target object. The experiments demonstrate that our work is robust for tracking, especially dealing with occlusions and object transformations.