Advertisement

Heterogeneous Reconfigurable System for Adaptive Particle Filters in Real-Time Applications

  • Thomas C. P. Chau
  • Xinyu Niu
  • Alison Eele
  • Wayne Luk
  • Peter Y. K. Cheung
  • Jan Maciejowski
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7806)

Abstract

This paper presents a heterogeneous reconfigurable system for real-time applications applying particle filters. The system consists of an FPGA and a multi-threaded CPU. We propose a method to adapt the number of particles dynamically and utilise the run-time reconfigurability of the FPGA for reduced power and energy consumption. An application is developed which involves simultaneous mobile robot localisation and people tracking. It shows that the proposed adaptive particle filter can reduce up to 99% of computation time. Using run-time reconfiguration, we achieve 34% reduction in idle power and save 26-34% of system energy. Our proposed system is up to 7.39 times faster and 3.65 times more energy efficient than the Intel Xeon X5650 CPU with 12 threads, and 1.3 times faster and 2.13 times more energy efficient than an NVIDIA Tesla C2070 GPU.

Keywords

Sequential Monte Carlo Idle Power Adaptive Particle FPGA Board Kullback Leibler Distance 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Happe, M., et al.: A self-adaptive heterogeneous multi-core architecture for embedded real-time video object tracking. Journal Real-Time Image Processing, 1–16 (2011)Google Scholar
  2. 2.
    Montemerlo, M., et al.: Conditional particle filters for simultaneous mobile robot localization and people-tracking. In: Proc. IEEE Int. Conf. Robotics and Automation, pp. 695–701 (2002)Google Scholar
  3. 3.
    Vermaak, J., et al.: Particle methods for bayesian modeling and enhancement of speech signals. IEEE Trans. Speech and Audio Processing 10(3), 173–185 (2002)CrossRefGoogle Scholar
  4. 4.
    Eele, A., Maciejowski, J.: Comparison of stochastic optimisation methods for control in air traffic management. In: Proc. IFAC World Congress (2011)Google Scholar
  5. 5.
    Doucet, A., et al.: Sequential Monte Carlo methods in practice. Springer (2001)Google Scholar
  6. 6.
    Bolic, M., et al.: Resampling algorithms and architectures for distributed particle filters. IEEE Trans. Signal Processing 53(7), 2442–2450 (2005)CrossRefMathSciNetGoogle Scholar
  7. 7.
    Koller, D., et al.: Using learning for approximation in stochastic processes. In: Proc. Int. Conf. Machine Learning, pp. 287–295 (1998)Google Scholar
  8. 8.
    Fox, D.: Adapting the sample size in particle filters through kld-sampling. Int. Trans. Robotics 22(12), 985–1003 (2003)CrossRefGoogle Scholar
  9. 9.
    Park, S.-H., et al.: Novel adaptive particle filter using adjusted variance and its application. Int. Journal Control, Automation, and Systems 8(4), 801–807 (2010)CrossRefGoogle Scholar
  10. 10.
    Bolic, M., et al.: Performance and complexity analysis of adaptive particle filtering for tracking applications. In: Proc. Asilomar Conf. Signals, Systems and Computers, vol. 1, pp. 853–857 (2002)Google Scholar
  11. 11.
    Chau, T.C., et al.: Adaptive sequential monte carlo approach for real-time applications. In: Proc. Int. Conf. Field Programmable Logic and Applications, pp. 527–530 (2012)Google Scholar
  12. 12.
    Liu, Z., et al.: Mobile robots global localization using adaptive dynamic clustered particle filters. In: IEEE/RSJ Int. Conf. Intelligent Robots and Systems, pp. 1059–1064 (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Thomas C. P. Chau
    • 1
  • Xinyu Niu
    • 1
  • Alison Eele
    • 3
  • Wayne Luk
    • 1
  • Peter Y. K. Cheung
    • 2
  • Jan Maciejowski
    • 3
  1. 1.Department of ComputingImperial College LondonUK
  2. 2.Department of Electrical and Electronic EngineeringImperial College LondonUK
  3. 3.Department of EngineeringUniversity of CambridgeUK

Personalised recommendations