Part-based visual tracking via structural support correlation filter

To better deal with the partial occlusion issue and improve their efficiency of part-based and support vector machines (SVM) based trackers, we propose a novel part-based structural support correlation filter tracking method, which absorbs the strong discriminative ability from SVM and the excellent property of part-based tracking methods which is less sensitive to partial occlusion. Then, our proposed model can learn the support correlation filter of each part jointly by a star structure model, which preserves the spatial layout structure among parts and tolerates outliers of parts. In addition, our model introduces inter-frame consistencies of local parts to mitigate the drift problem. Finally, our model can accurately estimate the scale changes of object by the relative distance change among reliable parts. The extensive empirical evaluations on three benchmark datasets: OTB2015, TempleColor128 and VOT2015 demonstrate that the proposed method achieves comparable performance against several state-of-the-art trackers and runs in real time.