A novel visual object tracking algorithm using multiple spatial context models and Bayesian Kalman filter

Abstract

Appearance modelling and tracking strategy are two fundamental problems in visual object tracking. In this paper, the appearance of the object is modeled by a spatial context based bag of multiple models (BMM). The BMM keeps multiple hypotheses and utilizes spatial information to perform tracking. Furthermore, a novel Bayesian Kalman filter is used as the tracking strategy to handle fast movement and acceleration of the tracked object. Experimental results show that our method can successfully handle complex scenarios with complicated background, long-term occlusion and fast movement.