Advertisement

Journal of Real-Time Image Processing

, Volume 15, Issue 2, pp 309–327 | Cite as

Performance evaluation of a 3D multi-view-based particle filter for visual object tracking using GPUs and multicore CPUs

  • David Concha
  • Raúl Cabido
  • Juan José Pantrigo
  • Antonio S. Montemayor
Original Research Paper

Abstract

This paper presents a deep and extensive performance analysis of the particle filter (PF) algorithm for a very compute intensive 3D multi-view visual tracking problem. We compare different implementations and parameter settings of the PF algorithm in a CPU platform taking advantage of the multithreading capabilities of the modern processors and a graphics processing unit (GPU) platform using NVIDIA CUDA computing environment as developing framework. We extend our experimental study to each individual stage of the PF algorithm, and evaluate the quality versus performance trade-off among different ways to design these stages. We have observed that the GPU platform performs better than the multithreaded CPU platform when handling a large number of particles, but we also demonstrate that hybrid CPU/GPU implementations can run almost as fast as only GPU solutions.

Keywords

Particle filtering GPU computing Performance evaluation 3D visual tracking Multi-view 

Notes

Acknowledgments

This research has been partially supported by the Spanish Government Projects Refs. TIN2011-28151 and TIN2014-57633 and NVIDIA Professor Partnership Program.

References

  1. 1.
    Azad, P., Münch, D., Asfour, T., Dillmann R.: 6-DoF model-based tracking of arbitrarily shaped 3D objects. In: Proceedings of the IEEE International Conference on Robotics and Automation (2011)Google Scholar
  2. 2.
    Black , M.J., Sigal, L.: Synchronized Video and Motion Capture Dataset for Evaluation of Articulated Human Motion (HumanEva). CS Department, Brown University. http://vision.cs.brown.edu/humaneva/ (2007). Accessed June 2014
  3. 3.
    Brown, J.A., Capson, D.W.: A framework for 3D model-based visual tracking using a GPU-accelerated particle filter. IEEE Trans. Vis. Comput. Graph. 18, 68–80 (2012)CrossRefGoogle Scholar
  4. 4.
    Cabido, R., Montemayor, A.S., Pantrigo, J.J., Payne, B.R.: Multiscale and local search methods for real time region tracking with particle filters: local search driven by adaptive scale estimation on GPUs. Mach. Vis. Appl. 21(1), 43–58 (2009)CrossRefGoogle Scholar
  5. 5.
    Cabido, R., Concha, D., Pantrigo, J.J., Montemayor, A.S.: High speed articulated object tracking using GPUs: a particle filter approach. In: Proceedings of the 10th International Symposium on Pervasive Systems, Algorithms, and Networks (ISPAN). GPU Technology and Applications (GPUTA) Track (2009)Google Scholar
  6. 6.
    Carpenter, J., Clifford, P., Fearnhead, P.: Building robust simulation based filters for evolving data sets. Tech. Rep. Dept. Statist., Univ. Oxford, Oxford, UK (1999)Google Scholar
  7. 7.
    Chitchian, M., Simonetto, A., van Amesfoort, A.S., Keviczky, T.: Distributed computation particle filters on GPU-architectures for real-time control applications. IEEE Trans. Control Syst. Technol. 21(6), 2224–2238 (2013)CrossRefGoogle Scholar
  8. 8.
    Choi, C., Christensen, H.I.: RGB-D object tracking: a particle filter approach on GPU. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2013)Google Scholar
  9. 9.
    Gordon, N.J., Salmond, D.J., Smith, A.F.M.: Novel approach to nonlinear/non-Gaussian Bayesian state estimation. IEE Proc. F Radar Signal Process. 140(2), 107–113 (1993)CrossRefGoogle Scholar
  10. 10.
    Harris, M.: Optimizing Parallel Reduction in CUDA. NVIDIA Developer Technology (2007)Google Scholar
  11. 11.
    Isard, M., Blake, A.: Condensation—conditional density propagation for visual tracking. Int. J. Comput. Vis. 29, 5–28 (1998)CrossRefGoogle Scholar
  12. 12.
    Jepson, A.D., Fleet, D.J., El-Maraghi, T.F.: Robust online appearance models for visual tracking. In: Proceedings of the IEEE Conf. on CVPR, Kauai, vol. I, pp. 415–422 (2001)Google Scholar
  13. 13.
    Khronos OpenCL Working Group: The OpenCL Specification 2.0 (2013)Google Scholar
  14. 14.
    Kaewtrakulpong, P., Bowden, R.: An improved adaptive background mixture model for realtime tracking with shadow detection. In: Proceedings of 2nd European Workshop on Advanced Video Based Surveillance Systems (AVBS), Video Based Surveillance Systems: Computer Vision and Distributed Processing (2001)Google Scholar
  15. 15.
    Klein, G., Murray, D.: Full-3D edge tracking with a particle filter. In: Proceedings of the British Machine Vision Conference (2006)Google Scholar
  16. 16.
    Lepetit, V., Fua, P.: Monocular model-based 3D tracking of rigid objects: a survey. Found. Trends Comput. Graph. Vis. 1(1), 1–89 (2005)CrossRefGoogle Scholar
  17. 17.
    Li, P.: An efficient particle filter based tracking method using graphics processing unit (GPU). J. Signal Process. Syst. 68(3), 317–332 (2012)CrossRefGoogle Scholar
  18. 18.
    Li, T., Sun, S., Sattar, T.P., Corchado, J.M.: Fight sample degeneracy and impoverishment in particle filters: a review of intelligent approaches. Expert Syst. Appl. 4(8), 3944–3954 (2014)CrossRefGoogle Scholar
  19. 19.
    Lopez-Mendez, A., Alcoverro, M., Pardas, M., Casas, J.R.: Real-time upper body tracking with online initialization using a range sensor. In: IEEE International Conference on Computer Vision Workshops (ICCV Workshops) (2011)Google Scholar
  20. 20.
    Michely, P., Chestnutty, J., Kagamiz, S., Nishiwakiz, K., Kuffneryz, J., Kanade, T.: GPU-accelerated real-time 3D tracking for humanoid autonomy. In: Proceedings of the JSME Robotics and Mechatronics Conference (ROBOMEC’08) (2008)Google Scholar
  21. 21.
    Migniot, C., Ababsa, F.: Hybrid 3D–2D human tracking in a top view. J. Real-Time Image Process. (2014). doi: 10.1007/s11554-014-0429-7
  22. 22.
    Mohedano, R., García, N., Salgado, L., Jaureguizar, F.: 3D tracking using multi-view based particle filters. Lect. Notes Comput. Sci. 5259, 785–795 (2008)CrossRefGoogle Scholar
  23. 23.
    Montemayor, A.S., Pantrigo, J.J., Sánchez, A., Fernández, F.: Particle filter on GPUs for real-time tracking. In: Proceedings of the ACM SIGGRAPH (Research Poster), Los Angeles, pp. 94 (2004)Google Scholar
  24. 24.
    Montemayor, A.S., Pantrigo, J.J., Cabido, R., Payne, B.R., Sánchez, A., Fernández, F.: Improving GPU particle filter with shader model 3.0 for visual tracking. In: Proceedings of the ACM SIGGRAPH (Research Poster), Boston (2006)Google Scholar
  25. 25.
    NVIDIA Corp.: CUDA C Programming Guide v. 5.5 (2013)Google Scholar
  26. 26.
    Pantrigo, J.J., Hernández, J., Sánchez, A.: Multiple and variable target visual tracking for video surveillance applications. Pattern Recognit. Lett. 31(12), 1577–1590 (2010)CrossRefGoogle Scholar
  27. 27.
    Prisacariu, V.A., Reid, I.D.: PWP3D: real-time segmentation and tracking of 3D objects. Int. J. Comput. Vis. 98(3), 335–354 (2012)MathSciNetCrossRefGoogle Scholar
  28. 28.
    Petit, A., Marchand, E., Kanani, K.: A robust model-based tracker combining geometrical and color edge information. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS’13) (2013)Google Scholar
  29. 29.
    Rymut, B., Kwolek, B.: Real-time multiview human body tracking using GPU-accelerated PSO. In: Proceedings of International Conference on Parallel Processing and Applied Mathematics (PPAM’13). Lecture Notes in Computer Science (2014)Google Scholar
  30. 30.
    Rymut, B., Kwolek, B.: Real-time multiview human pose tracking using graphics processing unit-accelerated particle swarm optimization, CCPE. Wiley, New York (2014)Google Scholar
  31. 31.
    Tang, X., Su, J., Zhao, F., Zhou, J., Wei, P.: Particle filter track-before-detect implementation on GPU. EURASIP J. Wirel. Commun. Netw. 2013, 38 (2013)CrossRefGoogle Scholar
  32. 32.
    Tyagi, A., Keck, M., Davis, J.W., Potamianos, G.: Kernel-based 3D tracking. In: Proceedings of the IEEE International Workshop on Visual Surveillance (2007)Google Scholar
  33. 33.
    Xie, C., Tana, J., Chenc, P., Zhangb, J., Hea, L.: Collaborative object tracking model with local sparse representation. J. Vis. Commun. Image Represent. 25(2), 423–434 (2014)CrossRefGoogle Scholar
  34. 34.
    Zotkin, D., Duraiswami, R., Davis, L.: Joint audio-visual tracking using particle filters. EURASIP J. Appl. Signal Process. 11, 1154–1164 (2002)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • David Concha
    • 1
  • Raúl Cabido
    • 1
  • Juan José Pantrigo
    • 1
  • Antonio S. Montemayor
    • 1
  1. 1.Department of Computer ScienceUniversidad Rey Juan CarlosMóstolesSpain

Personalised recommendations