FEATURE-BASED ANNEALING PARTICLE FILTER FOR ROBUST BODY POSE ESTIMATION

Adolfo López, Josep R. Casas

2009

Abstract

This paper presents a new annealing method for particle filtering in the context of body pose estimation. The feature-based annealing is inferred from the weighting functions obtained with common image features used for the likelihood approximation. We introduce a complementary weighting function based on the foreground extraction and we balance the different measures through the annealing layers in order to improve the posterior estimate. This technique is applied to estimate the upper body pose of a subject in a realistic multi-view environment. Comparative results between the proposed method and the common annealing strategy are presented to assess the robustness of the algorithm.

References

  1. Arulampalam, M., Maskell, S., Gordon, N., Clapp, T., Sci, D., Organ, T., and Adelaide, S. (2002). A tutorial on particle filters for online nonlinear/nonGaussianBayesian tracking. Signal Processing, IEEE Transactions on, 50(2):174-188.
  2. Bregler, C. and Malik, J. (1998). Tracking People with Twists and Exponential Maps. In Proc. CVPR (1998).
  3. Caillette, F., Galata, A., and Howard, T. (2005). Real-Time 3-D Human Body Tracking using Variable Length Markov Models. British Machine Vision Conference, 1:469-478.
  4. Canny, J. (1986). A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(6):679-698.
  5. Canton-Ferrer, C., Casas, J., and Pardas, M. (2008). Exploiting Structural Hierarchy in Articulated Objects Towards Robust Motion Capture. Lecture Notes in Computer Science, pages 82-91.
  6. Deutscher, J., Blake, A., and Reid, I. (2000). Articulated body motion capture by annealed particle filtering. Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on, 2:126-133 vol.2.
  7. Doucet, A., Godsill, S., and Andrieu, C. (2000). On Sequential Monte Carlo Sampling Methods for Bayesian Filtering. Statistics and Computing, 10(3):197-208.
  8. Gordon, N., Salmond, D., and Smith, A. (1993). Novel approach to nonlinear/non-gaussian bayesian state estimation. Radar and Signal Processing, IEE Proceedings F, 140(2):107-113.
  9. Isard, M. and Blake, A. (1998). CONDENSATIONConditional density propagation for visual tracking. Int. Journal of Computer Vision, 29(1):5-28.
  10. Laurentini, A. (1994). The visual hull concept for silhouette-based image understanding. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 16(2):150-162.
  11. Liu, J. and Chen, R. (1998). Sequential Monte Carlo methods for dynamical systems. Journal of the American Statistical Association, 93(5):1032-1044.
  12. MacCormick, J. and Isard, M. (2000). Partitioned Sampling, Articulated Objects, and Interface-Quality Hand Tracking. Lecture Notes in Computer Science, pages 3-19.
  13. Mikic, I. (2003). Human Body Model Acquisition and tracking using multi-camera voxel Data. PhD. Thesis, University of California, San Diego.
  14. Mitchelson, J. and Hilton, A. (2003). Simultaneous pose estimation of multiple people using multiple-view cues with hierarchical sampling. In Proc. of BMVC, September.
  15. Raskin, L., Rivlin, E., and Rudzsky, M. (2008). Using Gaussian Process Annealing Particle Filter for 3D Human Tracking-Volume 2008, Article ID 592081, 13 pages. EURASIP Journal on Advances in Signal Processing.
  16. Stauffer, C. and Grimson, W. (2000). Learning Patterns of Activity Using Real-Time Tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, pages 747-757.
  17. Xu, L., Landabaso, J., and Pardas, M. (2005). Shadow Removal with Blob-Based Morphological Reconstruction for Error Correction. Acoustics, Speech, and Signal Processing, 2005. Proceedings.(ICASSP'05). IEEE International Conference on, 2.
Download


Paper Citation


in Harvard Style

López A. and R. Casas J. (2009). FEATURE-BASED ANNEALING PARTICLE FILTER FOR ROBUST BODY POSE ESTIMATION . In Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009) ISBN 978-989-8111-69-2, pages 438-443. DOI: 10.5220/0001783404380443


in Bibtex Style

@conference{visapp09,
author={Adolfo López and Josep R. Casas},
title={FEATURE-BASED ANNEALING PARTICLE FILTER FOR ROBUST BODY POSE ESTIMATION},
booktitle={Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009)},
year={2009},
pages={438-443},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001783404380443},
isbn={978-989-8111-69-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2009)
TI - FEATURE-BASED ANNEALING PARTICLE FILTER FOR ROBUST BODY POSE ESTIMATION
SN - 978-989-8111-69-2
AU - López A.
AU - R. Casas J.
PY - 2009
SP - 438
EP - 443
DO - 10.5220/0001783404380443