Abstract

Visual tracking is a challenging problem, because the target frequently change its appearance, randomly move its location and get occluded by other ob- jects in unconstrained environments. The state changes of the target are tempo- rally and spatially continuous, in this paper therefore, a robust Spatio-Temporal structural context based Tracker (STT) is presented to complete the tracking task in unconstrained environments. The temporal context capture the historical ap- pearance information of the target to prevent the tracker from drifting to the back- ground in a long term tracking. The spatial context model integrates contributors, which are the key-points automatically discovered around the target, to build a supporting field. The supporting field provides much more information than ap- pearance of the target itself so that the location of the target will be predicted more precisely. Extensive experiments on various challenging databases demon- strate the superiority of our proposed tracker over other state-of-the-art trackers.