Research on Cue Fusion Based on the Particle Filter

Conference paper

Abstract

A single source has the instability for tracking target because of the impact of the environment. To solve this problem, cue fusion based on the particle filter is proposed. The algorithm uses the stratified sampling strategy through weighted color histogram and motion histogram, slows down the degradation of particles, and enhances the stability and accuracy of target tracking. The results show that cue fusion based on the particle filter is better than a single source even if the number of particles in cue fusion is the half of it in a single source.

Keywords

Particle filter Cue fusion Histogram Object tracking 

Notes

Acknowledgment

This work is supported by the Natural Science Foundation of China (Grant No. 41074090), Henan Province Open Laboratory for Control Engineering Key Disciplines (Grant No. KG2009-18), Henan Science and Technology key project (Grant No. 092102210360), and the Doctorate Program of Henan Polytechnic University (Grant No. B2009-27).

References

  1. 1.
    Pan, P., Schonfeld, D.: Visual tracking using high-order particle filtering. IEEE Signal Processing Letters. 18, 51–54 (2011)CrossRefGoogle Scholar
  2. 2.
    Wei-ya, W., Xue-mei, D., Xiang-dong, H.: A new method for small target detection and tracking. Journal of Optoelectronics ·Laser. 18, 121–124 (2007)Google Scholar
  3. 3.
    Bouaynaya, Schonfeld, N., Dept, D.: On the Optimality of Motion-Based Particle Filtering. IEEE Transactions on Circuits and Systems for Video Technology. 19, 1068–1072 (2009)Google Scholar
  4. 4.
    Perez, P., Vermaak, J., Blake, A.: Data fusion for visual tracking with particles. Proceeding of the IEEE. 92, 495–513 (2004)Google Scholar
  5. 5.
    Guo-Ying, Z., Pietikainen, M., Koller, D.: Dynamic texture recognition using local binary patterns with an application to facial expressions. IEEE Transactions on Pattern Analysis and Machine Intelligence. 29, 915–928 (2007)CrossRefGoogle Scholar
  6. 6.
    Jia, Y., Ming-yuan, W., Shu-Zhen, C., Qing-lin, Z.: Anti-occlusion tracking algorithm based on Mean Shift and fragment. 18, 1413–1419 (2010)Google Scholar
  7. 7.
    Zhao-Hua, H., Yao-liang, S., De-Qaun, L., Xin, F.: A particle filter based tracking algorithm with cue fusion under complex background. Journal of Optoelectronics ·Laser. 19, 678–680 (2008)Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  1. 1.School of Electrical Engineering and AutomationHenan Polytechnic UniversityJiaozuoChina

Personalised recommendations