Abstract
In this paper, we analyze algorithmic and architectural characteristics of a class of particle filters known as Gaussian Particle Filters (GPFs). GPFs approximate the posterior density of the unknowns with a Gaussian distribution which limits the scope of their applications in comparison with the universally applied sample-importance resampling filters (SIRFs) but allows for their implementation without the classical resampling procedure. Since there is no need for resampling, we propose a modified GPF algorithm that is suitable for parallel hardware realization. Based on the new algorithm, we propose an efficient parallel and pipelined architecture for GPF that is superior to similar architectures for SIRF in the sense that it requires no memories for storing particles and it has very low amount of data exchange through the communication network. We analyze the GPF on the bearings-only tracking problem and the results are compared with results obtained by SIRF in terms of computational complexity, potential throughput, and hardware energy. We consider implementation on FPGAs and we perform detailed comparison of the GPF and SIRF algorithms implemented in different ways on this platform. GPFs that are implemented in parallel pipelined fashion on FPGAs can support higher sampling rates than SIRFs and as such they might be a more suitable candidate for real-time applications.
Similar content being viewed by others
Notes
The notation \({\mathbf x}^{(m)}_{0:n}\) represents the set \(\big\{{\mathbf x}_0^{(m)}, {\mathbf x}_1^{(m)}, \cdots, {\mathbf x}_n^{(m)}\big\}.\)
References
Bar-Shalom, Y., Rong Li, X., & Kirubarajan, T. (2001). Estimation with applications to tracking and navigation: Theory, algorithms and software. New York: Wiley.
Bolić, M., Djurić, P. M., & Hong, S. (2004). Resampling algorithms for particle filters: A computational complexity perspective. EURASIP Journal of Applied Signal Processing, 15, 2267–2278.
Bolić, M., Djurić, P. M., & Hong, S. (2005). Resampling algorithms and architectures for distributed particle filters. IEEE Transactions on Signal Processing, 53(7), 2442–2450.
Bolić, M., Athalye, A., Djurić, P. M., & Hong, S. (2004). Algorithmic modification of particle filters for hardware implementation. In Proceedings of the European signal processing conference (pp. 1641–1646), Vienna, Austria.
Clark, D., Vo, B.-T., & Vo, B.-N. (2007). Gaussian particle implementations of probability hypothesis density filters. In The proceedings of the IEEE aerospace conference.
Daum, F., & Huang, J. (2002). Curse of dimensionality and particle filters. In Fifth ONR/GTRI workshop on target tracking and sensor fusion. Newport, RI, June 2002.
Digital Core Design Inc. (2009). Pipelined floating point libraries. www.dcd.pl.
Doucet, A., de Freitas, N., & Gordon, N. (Eds.) (2001). Sequential Monte Carlo methods in practice. New York: Springer.
Doucet, A., Godsill, S. J., & Andrieu, C. (2000). On sequential Monte Carlo sampling methods for Bayesian filtering. Statistics and Computing, 10, 197–208.
Danger, J. L., Ghazel, A., Boutillon, E., & Laamari, H. (2000). Efficient FPGA implementation of Gaussian noise generator for communication channel emulation. In Proceedings of IEEE ICECS conference (pp. 366–369). Laslik, Lebanon.
Ghirmai, T. (2007). Gaussian particle filtering for tracking maneuvering targets. In The proceedings of the IEEE SoutheastCon (pp. 439–443).
Gordon, N. J., Salmond, D. J., & Smith, A. F. M. (1993). A novel approach to nonlinear and non-Gaussian Bayesian state estimation. IEE Proceedings F, 140, 107–113.
Hao, Y., Xiong, Z., & Hu, Z. (2006). Particle filter for INS in-motion alignment. In The proceedings of the 1ST IEEE conference on industrial electronics and applications.
Hennessy, J. L., & Patterson, D. A. (2006). Computer architecture: A quantitative approach (3rd ed.). San Mateo: Morgan Kauffmann Publishers.
Hong, S., Chin, S.-S., Djurić, P. M., & Bolić, M. (2006). Design and implementation of flexible resampling mechanism for high-speed parallel particle filters. The Journal of VLSI Signal Processing, 44, 47–62.
Hong, S., Djurić, P. M., & Bolić, M. (2005). Simplifying physical realization of Gaussian particle filters with block level pipeline control. EURASIP Journal of Applied Signal Processing, 4, 575–587.
Howland, P. E. (1999). Target tracking using television-based bistatic radar. IEE Procedings, Radar, Sonar and Navigation, 146(3), 166–174.
Julier, S. J., & Durrant-Whyte, H. F. (1995) Navigation and parameter estimation of high speed road vehicles. In Robotics and automation conference, Japan (pp. 101–105).
Kotecha, J. H., & Djurić, P. M. (2003). Gaussian particle filtering. IEEE Transactions on Signal Processing, 51(10), 2592–2601.
Kotecha, J. H., & Djurić, P. M. (2003). Gaussian sum particle filtering. IEEE Transactions on Signal Processing, 51(10), 2602–2612.
Kumar, M.. (1988) Measuring parallelism in computation-intensive scientific/engineering applications. IEEE Transactions on Computers, 37(9), 1088–1098.
van Lawick van Pabst, J., & Krekel, P. F. (1993). Multisensor data fusion of points, line segments and surface segments in 3d space. In P. S. Schenker (Ed.), Sensor Fusion VI, SPIE Proceedings (Vol. 2059). Pasadena: Jet Propulsion.
Ristić, B., Arulampalam, S., & Gordon, N. (2004). Beyond the Kalman filter: Particle filters for tracking applications. Cormano: Artech House.
Shiva, S. G. (1996). Pipelined and parallel computer architectures. London: Harper Collins College.
Uhlmann, J. K. (1994). Simultaneous map building and localization for real-time applications. Technical report, University of Oxford.
Vemula, M., Bugallo, M. F., & Djurić, P. M. (2007). Performance comparison of Gaussian-based filters using information measures. IEEE Signal Processing Letters, 14(12), 1020–1023.
Volder, J. (1959). The CORDIC trigonometric computing technique. IRE Trans. Electronic Computing, EC-8, 330–334.
Wu, Y., Hu, X., Hu, D., & Wu, M. (2005). Comments on Gaussian particle filtering. Transacations on Signal Processing, 53(8), 3350–3351.
Xilinx Inc. (2003). Virtex-II Pro Patforms FPGA: Functional description. www.xilinx.com.
Zhang, Y., & Dai, H. (2007). Dynamic self-calibration in collaborative wireless networks using belief propagation with Gaussian particle Filtering. In Proceedings of the 41st annual conference on information sciences and systems, CISS (pp. 771–776).
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was supported by the NSF under Awards CCR-9903120 and CCR-0220011.
Rights and permissions
About this article
Cite this article
Bolić, M., Athalye, A., Hong, S. et al. Study of Algorithmic and Architectural Characteristics of Gaussian Particle Filters. J Sign Process Syst 61, 205–218 (2010). https://doi.org/10.1007/s11265-009-0434-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11265-009-0434-4