Visual object tracking via kernelized correlation filter and grey prediction

Due to the effects of deformation, scale changes and background interference, visual tracking has always been one of the challenging problems. In recent years, kernelized correlation filter (KCF) has attracted much attention. However, the tracking accuracy of KCF tracker is poor when the object fast motion, heavy occlusion and scale variation appear. Herein, this reason is analyzed that the KCF tracker generates candidate patches of object according to its location in the last frame. By establishing grey prediction model of object motion, we produce the candidate patches around the predicted location. Moreover, we apply an adaptive strategy to update model and employ a simple mechanism for scale estimation. We conduct our tracker on some tracking benchmarks, including OTB2013, VOT2016 and UAV123. Experimental results demonstrate the proposed tracking method has good and stable results.