Patch-based scale calculation for visual tracking

Robust scale calculation is a challenging problem in visual object tracking. Most state-of-the-art trackers fail to handle large scale variations in complex image sequences. This paper propose a novel approach for robust scale calculation in a tracking-by-detection framework. The proposed approach divides the target into four patches and computes the scale factor by finding the maximum response position of each patch via kernelized correlation filter. Experiments are performed on 20 sequences with scale variations in the recent benchmark evaluation. And the results show that our method outperforms state-of-the-art tracking methods while operating in real-time.