Authors: Yuhua Zheng, Yan Meng
Addresses: Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ 07030, USA. ' Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ 07030, USA
Abstract: This article presents a new face tracking algorithm that employs a swarm-intelligence based method particle swarm optimisation (PSO). Firstly, all potential solutions are projected into a high-dimensional space where particles are initialised. Then, particles are driven by PSO rules to search for the solutions. The face is tracked when the particles reach convergence. Furthermore, a multi-feature model is also proposed for face description to enhance the tracking accuracy and efficiency. The proposed model and algorithm are object-independent and can be used for any free-selected object tracking. Experimental results on face tracking demonstrate that the proposed algorithm is efficient and robust in visual object tracking under dynamic environments with real-time performance.
Keywords: face tracking; multiple feature modelling; particle swarm optimisation; PSO; swarm intelligence; face description; tracking accuracy; object tracking.
International Journal of Intelligent Systems Technologies and Applications, 2009 Vol.7 No.3, pp.266 - 281
Available online: 15 Jul 2009 *Full-text access for editors Access for subscribers Purchase this article Comment on this article