Wu Jing-Jing
School of Mechanical Engineering Jiangnan University, Wuxi, Jiangsu, 214122, China
You Li-Hua
School of Mechanical Engineering Jiangnan University, Wuxi, Jiangsu, 214122, China
Cao Yi
School of Mechanical Engineering Jiangnan University, Wuxi, Jiangsu, 214122, China
ABSTRACT
Particle probability hypothesis density (particle PHD) filter based visual trackers has attractive features of avoiding data association and the capability of solving nonlinear non-Gaussian models. But one main drawback of this approach is the unreliability of clustering technique for extracting state estimates, especially when target intersection and clutter make the distribution of particles complex multimodality. For improving the robustness and accuracy of state estimates, kernel based state extraction method is proposed for the tracker. Experimental results show the proposed method can efficiently track a variable number of objects in cluttered scene even when interactions of targets occur.
PDF References Citation
How to cite this article
Wu Jing-Jing, You Li-Hua and Cao Yi, 2013. Particle Probability-hypothesis-density Filter with Kernel Based State Extraction for Efficient Multi-target Visual Tracking. Information Technology Journal, 12: 4176-4179.
DOI: 10.3923/itj.2013.4176.4179
URL: https://scialert.net/abstract/?doi=itj.2013.4176.4179
DOI: 10.3923/itj.2013.4176.4179
URL: https://scialert.net/abstract/?doi=itj.2013.4176.4179
REFERENCES
- Comaniciu, D., V. Ramesh and P. Meer, 2003. Kernel-based object tracking. IEEE Trans. Pattern Anal. Machine Intell., 25: 564-577.
CrossRefDirect Link - Han, B. and L. Davis, 2005. On-Line density-based appearance modeling for object tracking. Proceedings of the IEEE International Conference on Computer Vision, Volume 2, October 17-21, 2005, Beijing, China, pp: 1492-1499.
CrossRef - Mahler, R.P.S., 2003. Multitarget Bayes filtering via first-order multitarget moments. IEEE Trans. Aerospace Electron. Syst., 39: 1152-1178.
CrossRefDirect Link - Vo, B.N., S. Singh and A. Doucet, 2003. Sequential Monte Carlo implementation of the PHD filter for multi-target tracking. Proceedings of the 6th International Conference on Information Fusion, July 8-11, 2003, Queensland, Australia, pp: 792-799.
CrossRef - Vo, B.N. and W.K. Ma, 2006. The Gaussian mixture probability hypothesis density filter. IEEE Trans. Signal Process., 54: 4091-4094.
CrossRef - Wang, Y.D., J.K. Wu, A.A. Kassim and W. Huang, 2008. Data-driven probability hypothesis density filter for visual tracking. IEEE Trans. Circuits Syst. Video Technol., 18: 1085-1095.
CrossRef