Parallelization of Particle Filter Algorithms

  • Matthew A. Goodrum
  • Michael J. Trotter
  • Alla Aksel
  • Scott T. Acton
  • Kevin Skadron
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6161)


This paper presents the parallelization of the particle filter algorithm in a single target video tracking application. In this document we demonstrate the process by which we parallelized the particle filter algorithm, beginning with a MATLAB implementation. The final CUDA program provided approximately 71x speedup over the initial MATLAB implementation.


Video Sequence Graphic Processing Unit Particle Filter Average Error Rate Global Synchronization 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Aksel, A., Scott, T.A.: Target Tracking Using Snake Particle Filter. In: 2010 Southwest Symposium on Image Analysis and Interpretation. IEEE Computer Society, Austin (2010)Google Scholar
  2. 2.
    Arulampalam, M.S., Maskell, S., Gordon, N., Clapp, T.: A Tutorial on Particle Filters for Online Nonlinear/Non-Gaussian Bayesian Tracking. IEEE Transactions on Signal Processing 50(2), 174–188 (2002)CrossRefGoogle Scholar
  3. 3.
    Box, G.E.P., Muller, M.E.: A Note on the Generation of Random Normal Deviates. The Annals of Mathematical Statistics 29(2), 610–611 (1958)CrossRefzbMATHGoogle Scholar
  4. 4.
    Boyer, M., Tarjan, D., Acton, S., Skadron, K.: Accelerating Leukocyte Tracking using CUDA: A Case Study in Leveraging Manycore Coprecessors. In: 23rd IEEE International Parallel and Distributed Processing Symposium. IEEE, Rome (2009)Google Scholar
  5. 5.
    Ferreira, Filipe, J., Lobo, J., Dias, J.: Bayesian real-time perception algorithms on GPU. Journal of Real-Time Image Processing, Special Issue (2010)Google Scholar
  6. 6.
    Gilliam, A.D., Epstein, F.H., Acton, S.T.: Cardiac Motion Recovery via Active Trajectory Field Models. IEEE Transactions in Biomedicine 13(2) (2009)Google Scholar
  7. 7.
    Lenz, C., Panin, G., Knoll, A.: A GPU-Accelerated Particle Filter with Pixel-Level Likelihood. In: International Workshop on Vision Modeling and Virtualization, Konstanz, Germany (2008) Google Scholar
  8. 8.
    Lozano, O.M., Otsuka, K.: Real-time visual tracker by stream processing. Journal of Signal Processing Systems 57(2), 285–295 (2009)CrossRefGoogle Scholar
  9. 9.
    Nummiaro, K., Koller-Meier, E., Van Gool, L.: An Adaptive Color-based Particle Filter. Image and Vision Computing 21(1), 99–110 (2003)CrossRefzbMATHGoogle Scholar
  10. 10.
    nVidia.: CUDA Reference Manual 2.3. CUDA ZONE (July 1, 2009). (accessed, October 24, 2009).
  11. 11.
    Quinn, M.J.: Parallel Programming in C with MBI and OpenMP. McGraw-Hill, New York (2004)Google Scholar
  12. 12.
    Szafaryn, L.G., Skadron, K., Saucerman, J.J.: Experiences Accelerating MATLAB Systems Biology Applications. In: Proceedings of the Workshop on Biomedicine in Computing: Systems, Architectures, and Circuits, BiC (2009)Google Scholar
  13. 13.
    Thrust.: Thrust: C++ Template Library for CUDA. (accessed April 23, 2010).
  14. 14.
    Ulman, G..: Bayesian Particle Filter Tracking with CUDA. (April 2010), (accessed May 14, 2010).
  15. 15.
    Eide, V.S.W., Eliassen, F., Granmo, O.-C., Lysne, O.: Scalable Independent Multi-level Distribution in Multimedia Content Analysis. In: Boavida, F., Monteiro, E., Orvalho, J. (eds.) IDMS 2002 and PROMS 2002. LNCS, vol. 2515, pp. 37–48. Springer, Heidelberg (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Matthew A. Goodrum
    • 1
  • Michael J. Trotter
    • 1
  • Alla Aksel
    • 2
  • Scott T. Acton
    • 2
  • Kevin Skadron
    • 1
  1. 1.Department of Computer ScienceUniversity of VirginiaCharlottesvilleUSA
  2. 2.Department of Electrical and Computer EngineeringUniversity of VirginiaCharlottesvilleUSA

Personalised recommendations