Abstract
Particle filter has been proven very robust in handling non-linear and non-Gaussian problems and has been widely used in the area of object tracking. One of the main problems in particle filter-based object tracking is, however, its high computational cost induced by the most time-consuming stage of measurement model computation. This paper makes progress in resolving the problem by proposing an efficient particle filter-based tracking algorithm using color information. First, a compact color cooccurrence histogram is presented, which considers both spatial and color information and can effectively represent color distribution with a very small number of histogram bins. The paper also introduces integral images by which the cooccurrence histogram can be obtained with simple array reference operations. However, the construction of the integral images on the CPU may be computationally expensive. Hence, this paper develops parallel algorithms on a desktop Graphics Processing Unit (GPU), which accomplishes the integral images construction and cooccurrence histogram computation after bin index determination. The resulting algorithm is quite efficient and has better performance than the traditional histogram-based tracking algorithm. The tracking time of the proposed algorithm increases insignificantly with the growth of particle number, and it remains consistent among varying image sequences and stable throughout all frames in the same image sequence due to its irrelevance to object size. Experiments in diverse image sequences validate our conclusions.
Similar content being viewed by others
References
Hogg, D. C. (1984). Interpreting images of a known moving object. Dphil thesis, School of Cognitive and Computing Sciences, University of Sussex, Brighton.
Kass, M., Witkin, A., & Terzopoulos, D. (1988). Snakes: Active contour models. International Journal of Computer Vision, 1(4), 321–331.
Isard, M., & Blake, A. (1998). Condensation—conditional density propagation for visual tracking. International Journal of Computer Vision, 29(1), 5–28.
Arulampalam, S., Maskell, S., Gordon, N., & Clapp, T. (2002). A tutorial on particle filters for on-line nonlinear/non-Gaussian bayesian tracking. IEEE Transactions on Signal Processing, 50(2), 174–188.
Hol, J., Schön, T., & Gustafsson, F. (2006). On resampling algorithms for particle filters. In Nonlinear statistical signal processing workshop (pp. 79–82).
Douc, R., & Cappe, O. (2005). Comparison of resampling schemes for particle filtering. In Proc. 4th int. symp. image and signal process. and analysis (pp. 64–69).
Comaniciu, D., Ramesh, V., & Meer, P. (2000). Real-time tracking of non-rigid objects using mean shift. In Proc. IEEE conf. comp. vis. patt. recog. (pp. 142–149).
Gordon, N., Salmond, D., & Smith, A. F. M. (1993). Novel approach to nonlinear/non-Gaussian Bayesian state estimation. IEE Proceedings F–Radar and Signal Processing, 140(2), 107–113.
Doucet, A., Godsill, S., & Andrieu, C. (2000). On sequential Monte Carlo sampling methods for Bayesian filtering. Statistics and Computing, 10(3), 197–208.
Yilmaz, A., Javed, O., & Shah, M. (2006). Object tracking: A survey. ACM Computing Surveys, 38(4), 13.
Blake, A., Curwen, R., & Zisserman, A. (1993). A framework for spatio-temporal control in the tracking of visual contour. International Journal of Computer Vision, 11(2), 127–145.
Terzopoulos, D., & Szeliski, R. (1993). Tracking with Kalman snakes. In A. Blake & A. Yuille (Eds.), Active vision (pp. 3–20). Cambridge: MIT Press.
Peterfreund, N. (1999). Robust tracking of position and velocity with Kalman snakes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(6), 564–569.
Maskell, S., & Gordon, N. (2001). A tutorial on particle filters for on-line nonlinear/non-Gaussian Bayesian tracking. IEEE Transactions on Signal Processing, 50, 174–188.
Li, P., Zhang, T., & Pece, A. (2003). Visual contour tracking based on particle filters. Image and Vision Computing, 21(1), 111–123.
Nummiaro, K., Koller-Meier, E. B., & Gool, L. (2003). A color based particle filter. Image and Vision Computing, 21(1), 99–110.
Pérez, P., Hue, C., Vermaak, J., & Gangnet, M. (2002). Color-based probabilistic tracking. In Eur. conf. on computer vision (pp. 661–675). Copenhaguen, Denmark.
Jacquot, A., Sturm, P., & Ruch, O. (2005). Adaptive tracking of non-rigid objects based on color histograms and automatic parameter selection. In Proc. IEEE workshop on motion and video computing (pp. 103–109).
Maggio, E., & Cavallaro, A. (2005). Multi-part target representation for colour tracking. In Proc. IEEE int. conf. on image processing (pp. 729–732).
Xu, X., & Li, B. (2007). Adaptive rao-blackwellized particle filter and its evaluation for tracking in surveillance. IEEE Transactions on Image Processing, 16(3), 838–849.
Wang, J., & Yagi, Y. (2009). Adaptive mean-shift tracking with auxiliary particles. IEEE Transactions on Systems, Man, and Cybernetics, 39(6), 1578–1589.
Viola, P., & Jones, M. (2004). Robust real-time face detection. International Journal of Computer Vision, 57(2), 137–154.
Yang, C., Duraiswami, R., & Davis, L. (2005). Fast multiple object tracking via a hierarchical particle filter. In Proc. of the tenth IEEE int. conf. on computer vision (pp. 212–219). Washington, DC, USA.
Han, B., Yang, C., Duraiswami, R., & Davis, L. (2005). Bayesian filtering and integral image for visual tracking. In Worshop on image analysis for multimedia interactive services (WIAMIS). Montreux, Switzerland.
Li, P., & Wang, H. (2007). Object tracking with particle filter using color information. In MIRAGE 2007 (pp. 534–541).
Martinez-del-Rincon, J., Orrite-Urunuela, C., & Herrero-Jaraba, J. E. (2005). An efficient particle filter for color-based tracking in complex scenes. In IEEE conf. on advanced video and signal based surveillance (pp. 176–181).
Sugano, H., & Miyamoto, R. (2009). Hardware implementation of a cascade particle filter. In IEEE int. conf. on image processing (pp. 3257–3260).
Wang, H., Suter, S. D., Schindler, K., & Shen, C. (2007). Adaptive object tracking based on an effective appearance filter. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(9), 1661–1667.
Lenz, C., Panin, G., & Knoll, A. (2008). A GPU-accelerated particle filter with pixel-level likelihood. In Int. workshop on vision, modeling and visualization (VMV). Konstanz, Germany.
Medeiros, H., Gao, X., Kleihorst, R., Park, J., & Kak, A. C. (2008). A parallel implementation of the color-based particle filter for object tracking. In ACM SenSys workshop on applications, systems, and algorithms for image sensing.
Cabido, R., Montemayor, A. S., Pantrigo, J. J., & Payne, B. R. (2009). Multiscale and local search methods for real time region tracking with particle filters: Local search driven by adaptive scale estimation on GPUs. Machine Vision and Applications, 21(1), 43–58.
Míguez, J. (2007). Analysis of parallelizable resampling algorithms for particle filtering. Signal Processing, 87(12), 3155–3174.
Bolic, M., Djuric, P., & Hong, S. (2005) Resampling algorithms and architectures for distributed particle filters. IEEE Transactions on Signal Processing, 87(12), 2442–2450.
Hendeby, G., Hol, J., Karlsson, R., & Gustafsson, F. (2007). A graphics processing unit implementation of the particle filter. In Proc. of the 15th Eur. statistical signal processing (pp. 1639–1643). Pozna’n, Poland.
Haralick, R. M., Shanmugan, K., & Dinstein, I. (1973). Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, 3(6), 610–621.
Palm, C. (2004). Color texture classification by integrative co-occurrence matrices. Pattern Recognition, 37(5), 965–976.
Chang, P., & Krumm, J. (1999). Object recognition with color co-occurrence histograms. In Proc. IEEE conf. comp. vis. patt. recog. (pp. 498–504).
Vadivel, A., Sural, S., & Majumdar, A. K. (2007). An integrated color and intensity co-occurrence matrix. Pattern Recognition Letters, 28(8), 974–983.
NVIDIA Products (2010). http://www.nvidia.com/page/products.html. Accessed January 2010.
The resource for CUDA developers (2010). http://www.nvidia.com/object/cuda_home.html. Accessed January 2010.
Blelloch, G. (1993). Prefix sums and their applications. In Reif, J. (Ed.), Synthesis of parallel algorithms (pp. 35–62). San Fransisco: Morgan Kaufmann.
Blake, A., & Isard, M. (1998). Active contours: The application of techniques from graphics, vision, control theory and statistics to visual tracking of shapes in motion. New York: Springer-Verlag.
Isard, M., & Blake, A. (1996). Contour tracking by stochastic propagation of conditional density. In European conf. on computer vision (pp. 343–356). Cambridge, UK.
Jain, A. (2010). Data clustering: 50 years beyond k-means. Pattern Recognition Letters, 31(8), 651–666.
CAVIAR test case scenarios (2003). http://groups.inf.ed.ac.uk/vision/CAVIAR/CAVIARDATA1/. Accessed March 2009.
PETS2001 Datasets (2001). The University of Reading, UK. http://peipa.essex.ac.uk/ipa/pix/pets/PETS2001/. Accessed March 2009.
NVIDIA CUDA C Programming Guide, Version 4.0 (2011). http://developer.download.nvidia.com/compute/cuda/4_0_rc2/toolkit/docs/CUDA_C_Programming_Guide.pdf. Accessed May 2011.
Ahn, J. H., Erez, M., & Dally, W. J. (2005). Scatter-add in data parallel architectures. In Proceedings of the 11th Int. symposium on high-performance computer architecture (pp. 132–142). San Francisco, California, USA.
Podlozhnyuk, V. (2008). Histogram calculation in CUDA. http://www.nvidia.cn/object/cuda_sample_data-parallel.html. Accessed May 2011.
Shams, R., & Kennedy, R. A. (2007). Efficient histogram algorithms for NVIDIA CUDA compatible devices. In Proc. int. conf. on signal processing and communications systems (pp. 418–422). Gold Coast, Australia.
Acknowledgements
We highly appreciate the insightful comments of the reviewers which improve both the quality and presentation of the manuscript. The research was supported by the National Natural Science Foundation of China (60973080, 61170149 and 60673110), Program for New Century Excellent Talents in University from Chinese Ministry of Education (NCET-10-0151), Key Project by Chinese Ministry of Education (No. 210063). It was also supported in part by the Program for New Century Excellent Talents of Heilongjiang Province (1153-NCET-002) and High-level professionals (innovative teams) of Heilongjiang University (Hdtd2010-07).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Li, P. An Efficient Particle Filter–based Tracking Method Using Graphics Processing Unit (GPU). J Sign Process Syst 68, 317–332 (2012). https://doi.org/10.1007/s11265-011-0620-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11265-011-0620-z