Top > JACIII > Real Time Color Object Tracking on Cell Broadband Engine Using ...

single-jc.php

JACIII Vol.14 No.3 pp. 272-280
doi: 10.20965/jaciii.2010.p0272
(2010)

Paper:

Views over last 60 days: 609

Real Time Color Object Tracking on Cell Broadband Engine Using Particle Filters

Norikazu Ikoma* and Akihiro Asahara**

*Faculty of Engineering, Kyushu Institute of Technology, Kita-Kyushu, Fukuoka 804-8550, Japan

**Fixstars Corporation, 1-8-27-3F Kounan, Minato-ku, Tokyo 108-0075, Japan

Received:
December 7, 2009
Accepted:
January 6, 2010
Published:
April 20, 2010
Creative Commons License
Keywords:
particle filters, parallel implementation, many cores CPU
Abstract
Real time visual tracking by particle filter has been implemented on Cell Broadband Engine in parallel. Major problem for the implementation is small size of Local Store (LS) in SPEs (Synergistic PEs), which are computational cores, to deal with image of large size. As a first step for the implementation, we focus on color single object tracking, which is one of the most simple case of visual tracking. By elaborating to compress the color extracted image into bit-wise representation of binary image, all information of the color extracted image can be stored in LS for 640×480 size of original image. By applying our previous implementation of general particle filter algorithm on Cell/B.E. to this specific case, we have achieved real time performance of visual tracking on PlayStation®3 about 7 fps with a camera of maximum 15 fps.
Cite this article as:
N. Ikoma and A. Asahara, “Real Time Color Object Tracking on Cell Broadband Engine Using Particle Filters,” J. Adv. Comput. Intell. Intell. Inform., Vol.14 No.3, pp. 272-280, 2010.
Data files:
References
  1. [1] A. Doucet, N. Freitas, and N. J. Gordon, (eds), “Sequential Monte Carlo Methods in Practice”, New York, Springer, 2001.
  2. [2] J. U. Cho, S. H. Jin, X. D. Pham, J. W. Jeon, J. E. Byun, and H. Kang, “A Real-Time Object Tracking System Using a Particle Filter,” Proc. of 2006 Int. Conf. on Intelligent Robots and Sys., pp. 2822-2827, 2006.
  3. [3] M. Isard and A. Blake, “CONDENSATION – Conditional Density Propagation for Visual Tracking,” Int. J. of Computer Vision, Vol.29, No.1, pp. 5-28, 1998.
  4. [4] K. Okuma, A. Taleghani, N. Freitas, J. Little, and D. G. Lowe, “A Boosted Particle Filter: Multitarget Detection and Tracking,” Proc. of European Conf. on Computer Vision, pp. 28-39, 2004.
  5. [5] J. S. Liu, “Monte Carlo Strategies in Scientific Computing,” New York, Springer, 2001.
  6. [6] M. Gschwind, H. P. Hofstee, B. Flachs, M. Hopkins, Y. Watanabe, and T. Yamazaki, “Synergistic Processing in Cell’s Multicore Architecture,” IEEE Micro, Vol.26, No.2, pp. 10-24, 2006.
  7. [7] N. Ikoma, Y. Shin, and A. Asahara, “Parallel implementation of particle filter algorithm on Cell Broadband Engine,” Opening Workshop of 2008-2009 Program of Statistical and Applied Mathematical Sciences Institute (SAMSI) on Sequential Monte Carlo Methods, Research Triangle Park, NC, (Poster presentation), Sep. 7-10, 2008.
  8. [8] N. Ikoma, Y. Shin, A. Asahara, H. Kawano, and H. Maeda, “On an implementation of parallel algorithm of particle filter on Cell Broadband Engines,” 4th Int. Conf. on Soft Computing and Intelligent Systems and 9th Int. Sympo. on advanced Intelligent Systems, Nagoya, Japan, pp. 1645-1650, Sep. 17-21, 2008.
  9. [9] M. Bolić, P. M. Djurić, and S. Hong, “Resampling Algorithms and Architectures for Distributed Particle Filters,” IEEE Trans., Signal Processing, Vol.53, No.7, pp. 2442-2450, 2005.
  10. [10] M. Shabany and P. G. Gulak, “An Efficient Architecture for Distributed Resampling for High-Speed Particle Filtering,” Proc. of 2006 Int. Sympo. on Circuits and Systems, pp. 3422-3425, 2006.
  11. [11] S. Fukuda, N. Ikoma, H. Kawano, and H. Maeda, “On ring structure of particles’ transfer and pipelining improvement with nonnormalized weight for parallel computation hardware design of particle filter,” Proc. of Int. Workshop on Nonlinear Circuits and Signal Processing, 2008, Gold Coast, Australia, pp. 359-362, Mar. 6-8, 2008.
  12. [12] S. Hong, S. Chin, and S. Magesh, “A Flexible Resampling Mechanism for Parallel Particle Filters,” Proc. of 2003 Int. Sympo. on VLSI Technology, Systems, and Applications, pp. 288-291, 2003.
  13. [13] S. Hong and P. M. Djurić, “High-Throughput Scalable Parallel Resampling Mechanism for Effective Redistribution of Particles,” IEEE Trans., Signal Processing, Vol.54, No.3, pp. 1144-1155, 2006.
  14. [14] N. Ikoma, T. Higuchi, and H. Maeda “Tracking of maneuvering target by using switching structure and heavy-tailed distribution with particle filter method,” Proc. of 2002 IEEE Conf. on Control Applications, pp. 1283-1287, 2002.
  15. [15] H. Sugano and R. Miyamoto, “A Real-Time Object Recognition System on Cell Broadband Engine,” Lecture Notes in Computer Science, Advances in Image and Video Technology, Springer, Vol.4872, pp. 932-943, 2007.

Creative Commons License  This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Apr. 22, 2024