Skip to main content
Springer Nature Link
Log in

A Rao-Blackwellized Parts-Constellation Tracker

  • Conference paper
Dynamical Vision (WDV 2006, WDV 2005)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 4358))

  • 770 Accesses

Abstract

We present a method for efficiently tracking objects represented as constellations of parts by integrating out the shape of the model. Parts-based models have been successfully applied to object recognition and tracking. However, the high dimensionality of such models present an obstacle to traditional particle filtering approaches. We can efficiently use parts-based models in a particle filter by applying Rao-Blackwellization to integrate out continuous parameters such as shape. This allows us to maintain multiple hypotheses for the pose of an object without the need to sample in the high-dimensional spaces in which parts-based models live. We present experimental results for a challenging biological tracking task.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Baker, S., Dellaert, F., Matthews, I.: Aligning images incrementally backwards. Technical Report CMU-RI-TR-01-03, CMU Robotics Institute, Pittsburgh, PA, Feb (2001)

    Google Scholar 

  2. Burl, M.C., Weber, M., Perona, P.: A probabilistic approach to object recognition using local photometry and global geometry. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407, p. 628. Springer, Heidelberg (1998)

    Chapter  Google Scholar 

  3. Carpenter, J., Clifford, P., Fernhead, P.: An improved particle filter for non-linear problems. Technical report, Department of Statistics, University of Oxford (1997)

    Google Scholar 

  4. Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, Series B 39(1), 1–38 (1977)

    MATH  MathSciNet  Google Scholar 

  5. Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June (2003)

    Google Scholar 

  6. Freitas, N.: Rao-Blackwellised particle filtering for fault diagnosis. IEEE Trans. Aerosp (2002)

    Google Scholar 

  7. Gordon, N.J., Salmond, D.J., Smith, A.F.M.: Novel approach to nonlinear/non-Gaussian Bayesian state estimation. IEE Procedings F 140(2), 107–113 (1993)

    Google Scholar 

  8. Isard, M., Blake, A.: Contour tracking by stochastic propagation of conditional density. In: Eur. Conf. on Computer Vision (ECCV), pp. 343–356 (1996)

    Google Scholar 

  9. Khan, Z., Balch, T., Dellaert, F.: A Rao-Blackwellized particle filter for EigenTracking. In: IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE, Los Alamitos (2004)

    Google Scholar 

  10. Lucas, B.D., Kanade, T.: An iterative image registration technique with an application in stereo vision. In: Seventh International Joint Conference on Artificial Intelligence (IJCAI-81), pp. 674–679 (1981)

    Google Scholar 

  11. McLachlan, G.J., Krishnan, T.: The EM algorithm and extensions. Wiley series in probability and statistics. John Wiley & Sons, Chichester (1997)

    MATH  Google Scholar 

  12. Montemerlo, M., Thrun, S., Koller, D., Wegbreit, B.: FastSLAM: A factored solution to the simultaneous localization and mapping problem. In: AAAI Nat. Conf. on Artificial Intelligence, AAAI, Menlo Park (2002)

    Google Scholar 

  13. Murphy, K., Russell, S.: Rao-Blackwellised particle filtering for dynamic Bayesian networks. In: Doucet, A., de Freitas, N., Gordon, N. (eds.) Sequential Monte Carlo Methods in Practice, Springer, New York (January 2001)

    Google Scholar 

  14. Schulz, D., Fox, D., Hightower, J.: People tracking with anonymous and ID-sensors using Rao-Blackwellised particle filters. In: Proceedings of IJCAJ (2003)

    Google Scholar 

  15. Sigal, L., Bhatia, S., Roth, S., Black, M.J., Isard, M.: Tracking loose-limbed people. In: IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 421–428. IEEE, Los Alamitos (2004)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. College of Computing, Georgia Institute of Technology, Atlanta, GA 30332,  

    Grant Schindler & Frank Dellaert

Authors
  1. Grant Schindler
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Frank Dellaert
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

René Vidal Anders Heyden Yi Ma

Rights and permissions

Reprints and permissions

Copyright information

© 2007 Springer Berlin Heidelberg

About this paper

Cite this paper

Schindler, G., Dellaert, F. (2007). A Rao-Blackwellized Parts-Constellation Tracker. In: Vidal, R., Heyden, A., Ma, Y. (eds) Dynamical Vision. WDV WDV 2006 2005. Lecture Notes in Computer Science, vol 4358. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-70932-9_14

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-70932-9_14

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-70931-2

  • Online ISBN: 978-3-540-70932-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics