Region covariance based object tracking using Monte Carlo method

Covariance features enabled efficient fusion of different type of image features have low dimensions and covariance-based object tracking has been proved robust, versatile for a modest computational cost. In this paper, a method combined Monte Carlo method and covariance features is proposed. Monte Carlo method is used to determine the scope of the search target at the region level. Covariance features are used to model the objects appearance at the object level. An improved object matching and occlusion handling strategies are given, which are followed by an appearance model update method. Experiments show our approach is robust and effective for tracking the object with irregular movement and partial occlusions.