Particle Swarm Optimization Based Object Tracking

This paper proposes a particle swarm optimization based algorithm for object tracking in image sequences. In each frame the particles are drawn from a Gaussian distribution in order to cover the promising object locations and afterwards the particle swarm optimization takes place in order to concentrate the particles near the true object state. The aim of the particle swarm optimization is to shift the particles toward more promising regions in the search area. A grayscale appearance model that is learned on-line is utilized in evaluation of the particles score. Experimental results that were obtained in a typical office environment show the feasibility of our approach, especially when the object undergoing tracking has a rapid motion or the appearance changes are considerable. The resulting algorithm runs in real-time on a standard computer.