Improved Object Tracking with Particle Filter and Mean Shift

Abstract

In this paper, we present a new object tracking algorithm based on particle filtering technique and the mean shift algorithm. The particle filtering technique is a powerful technique for tracking objects in image sequences with complex background. It has been proved to be a robust method of tracking in non-linear and non-Gaussian case. But two common problems of the particle filter technique are the degeneracy phenomenon and the huge computational cost. To solve these problems, our new tracking algorithm uses the mean shift algorithm inside the particle filter. With the help of the mean shift algorithm, we can sample more particles of higher weights, and discard those particles whose contribution to the tracking is almost zero. The experiment results show that the new algorithm reduces the degeneracy problem and the computational cost of the particle filter.