Sequential particle swarm optimization for visual tracking

Visual tracking usually involves an optimization process for estimating the motion of an object from measured images in a video sequence. In this paper, a new evolutionary approach, PSO (particle swarm optimization), is adopted for visual tracking. Since the tracking process is a dynamic optimization problem which is simultaneously influenced by the object state and the time, we propose a sequential particle swarm optimization framework by incorporating the temporal continuity information into the traditional PSO algorithm. In addition, the parameters in PSO are changed adaptively according to the fitness values of particles and the predicted motion of the tracked object, leading to a favourable performance in tracking applications. Furthermore, we show theoretically that, in a Bayesian inference view, the sequential PSO framework is in essence a multilayer importance sampling based particle filter. Experimental results demonstrate that, compared with the state-of-theart particle filt...

• Type: Conference
• Year: 2008
• Where: CVPR
• Authors: Xiaoqin Zhang, Weiming Hu, Stephen J. Maybank, Xi Li, Mingliang Zhu
• Keywords: Computer Vision, CVPR 2008, Particle Swarm Optimization, Sequential Pso Framework, State-of-theart Particle Filter, Traditional Pso Algorithm, Unscented Particle Filter