Joint feature points correspondences and color similarity for robust object tracking

A new visual object tracking algorithm is proposed by using joint feature points correspondences and color similarity of the moving object to solve the background disturbance. This tracking algorithm is based on particle filtering in which a new method of computing each sample weight is proposed. Each sample weight can be obtained through measuring the similarities of color histogram and feature points between the object model and each sample. Comparisons with the conventional particle filtering and a combination between the mean shift tracking and kalman filtering, the experimental results show that this approach is robust to the moving objects tracking.