Journal of Applied Sciences1812-56541812-5662Asian Network for Scientific Information10.3923/jas.2014.121.128ZhouZhiyuXiaolong PengDichong WuZefei ZhuChuanyu WuJianwei Wu22014142Particle filter simulates posterior probability distribution
of tracking target through a collection of random particles. Whereas the interferences
of analogues occur frequently in a normal condition, random particles might
not be able to proximate target state that easily. This study presents an innovative
particle tracking method, with a combination of color and motion information
provided by improved Camshift. First, the centroid position of tracking target
is denoted by joint probability distribution of color histogram and motion information,
such that the stability of Camshift has been improved. Then, an improved Camshift
is introduced to optimize particles evolution. With analogue interferences,
grey prediction model initialized by Camshift is imposed to harvest proposal
distribution of optimized particle filter. Finally, in the sampling process,
particles are sampled hierarchically to denote exact target position on the
basis of the weights. Experimental tasks have demonstrated that the method performs
well under the condition of targets maneuvering, incomplete or complete occlusions.
Furthermore, it outperformed the previous with more robustness and computation
accuracy.]]>Bradski, G.R.,1998Li, H.T., P.L. Wu and L.F. Kong,2010Liu, S., Y. Dang and Z. Fang,2004Luo, T., J.Z. Wang and P.Y. Lu,2011Niu, C.F., D.F. Chen and Y.S. Liu,2010Shi, H., T. Liu, M. Li and M.J. Shen,2012Sun, H.G., J. Zhang, Y.T. Liu, Q. Bu and Y.N. Xie,2010Wang, Z., X. Yang, Y. Xu and S. Yu,2009Xia, Y., X.J. Wu and H.Y. Wang,2012Yun, X. and G. Xiao,2011