Particle-Filter Tracking of Motion Vector to Locate Objects and Pattern Matching over Particles Based on Mpeg2

Abstract:

During process of objects tracking, problem of tracking box about marked objects is a major problem. Moreover, tracking of multi-objects are also difficult problems of objects tracking. This paper can tag object automatically through using motion vector of Mpeg2 to mark activities object of static video. Then, we extract multi-dimensional characteristics from initial goal of motion vector determined and made model. And accurately identify particles of larger weight to achieve purpose of accurately tracking objects through process of original value of particle filter matching observed value. As adopted methods of pattern classifying, so made feature matching between new particle and original particle are more accurate. The experiments show that the algorithm had good tracking performance and strong robustness.

• Periodical: Advanced Materials Research (Volumes 225-226)
• Pages: 350-355
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.225-226.350
• Online since: April 2011
• Authors: Liu Bai Li, Yan Ma, Yuan Yuan Liang
• Keywords: Block, Kalman Filter (KF), Object Tracking, Particle Degradation, Particle Filter (PF), Velocity

References

[1] M. Arulampalam, S. Maskell, N. Gordon. A Tutorial on Particle Filters for Online Non2linear/Non2Gaussian Bayesian Tracking[J]. IEEE Transactions on Signal Processing, 2002, 50 (2) : 174 - 188.

DOI: 10.1109/78.978374

[2] STRAKA O, SIMANDL M. Particle filter adaptation based on efficient sample size[C] / /Proc of the 14th IFAC Symposium on System Identification. Newcastle: IFAC Publisher, 2006: 9912996.

DOI: 10.3182/20060329-3-au-2901.00158

[3] KWOK C, FOX D, MEILA M. Real-time particle filter [J]. Proceedings of the IEEE, 2004, 92 (3): 4692484.

[4] HU XL, SCHON TB, LJUNG L. A basic convergence results for Particle Filtering[J]. IEEE Transactions Signal Processing, 2008, 56 (4): 133721348.

DOI: 10.1109/tsp.2007.911295

[5] GAO Shi-wei , GUO Lei , YANG Ning , CHEN Liang , DU Ya-qin. A New Particle Filter Object Tracking Algorithm. JOURNAL OF SHAN GHAI J IAOTONG UNIVERSITY. 2009(3).

[6] PAPAVASILIOU A. A uniformly convergent adaptive particle filter[J]. Journal of Applied Probability, 2005, 42 (4) : 105321068.

DOI: 10.1239/jap/1134587816

[7] Jones M J , Rehg J M. Statistical color models with application to skin detection[J]. International Journal of Computer Vision, 2002, 46(1): 81-96.

[8] Bar - Shalom Y, Forrmann T E. Tracking and Association Data[M]. Academic Press, 1988. 2．David A, Jean P. Computer Vision - A Modern Approach [M ]. Beijing: Electronic Industry Press, (2004).

[9] ZHANG zhong-kai, KANG-jian, RUI guo-sheng. Research on Target Tracking by Velocity Constrained Particle Filtering. Journal of Projectiles, Rockets, Missiles and Guidance, 2010, 1.

[10] ZHOU Fei, HE Wei-jun, FAN Xin-yue. Tracking application about singer model based on marginalized particle filter. The Journal of China Universities of Posts and Telecommunications. August 2010, 17(4): 47–51.

DOI: 10.1016/s1005-8885(09)60486-6