Fast moving and deformational target tracking approach based on heterogeneous features fusion

Abstract

Aiming at the unstable performance on fast-moving and deformational target tracking in current kernel correlation filter (KCF), an innovative approach based on heterogeneous features fusion is proposed in this paper. Firstly, a histogram of oriented gradient is utilized to cater for motion state change in complex surveillance background. Combined with a colour-free template as a novel heterogeneous feature, the proposed approach improves the tracking performance on the fast-moving target in KCF. Subsequently, the optimized spatial regularization and quadruple block method are implemented in order to solve the difficulties of scale change and boundary effect in the cyclic matrix. The simulation results indicate that the proposed approach has better precision and success rate than other popular tracking algorithms when dealing with both fast motion and deformation on the platform of the object tracking benchmark and actual traffic datasets.