Skip to main content
SpringerLink
Log in
Book cover

International Workshop on Statistical Methods in Video Processing

SMVP 2004: Statistical Methods in Video Processing pp 13–25Cite as

Geometric Structure of Degeneracy for Multi-body Motion Segmentation

  • Conference paper

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 3247))

Abstract

Many techniques have been proposed for segmenting feature point trajectories tracked through a video sequence into independent motions. It has been found, however, that methods that perform very well in simulations perform very poorly for real video sequences. This paper resolves this mystery by analyzing the geometric structure of the degeneracy of the motion model. This leads to a new segmentation algorithm: a multi-stage unsupervised learning scheme first using the degenerate motion model and then using the general 3-D motion model. We demonstrate by simulated and real video experiments that our method is superior to all existing methods in practical situations.

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

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Costeira, J.P., Kanade, T.: A multibody factorization method for independently moving objects. Int. J. Comput. Vision 29(3), 159–179 (1998-1999)

    Google Scholar 

  2. Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM Algorithm. J. Roy. Statist. Soc. B39, 1–38 (1977)

    MathSciNet  MATH  Google Scholar 

  3. Gear, C.W.: Multibody grouping from motion images. Int. J. Comput. Vision 29(2), 133–150 (1998-8/9)

    Google Scholar 

  4. Ichimura, N.: Motion segmentation based on factorization method and discriminant criterion. In: Proc. 7th Int. Conf. Comput. Vision, Kerkyra, Greece, September 1999, vol. 1, pp. 600–605 (1999)

    Google Scholar 

  5. Ichimura, N.: Motion segmentation using feature selection and subspace method based on shape space. In: Proc. 15th Int. Conf. Pattern Recog., Barcelona, Spain, September 2000, vol. 3, pp. 858–864 (2000)

    Google Scholar 

  6. Inoue, K., Urahama, K.: Separation of multiple objects in motion images by clustering. In: Proc. 8th Int. Conf. Comput. Vision, Vancouver, Canada, July 2001, vol. 1, pp. 219–224 (2001)

    Google Scholar 

  7. Kanatani, K.: Geometric information criterion for model selection. Int. J. Comput. Vision 26(3), 171–189 (1998-2/3)

    Google Scholar 

  8. Kanatani, K.: Motion segmentation by subspace separation and model selection. In: Proc. 8th Int. Conf. Comput. Vision, Vancouver, Canada, July 2001, vol. 2, pp. 301–306 (2001)

    Google Scholar 

  9. Kanatani, K.: Motion segmentation by subspace separation: Model selection and reliability evaluation. Int. J. Image Graphics 2(2), 179–197 (2002-4)

    Google Scholar 

  10. Kanatani, K.: Evaluation and selection of models for motion segmentation. In: Proc. 7th Euro. Conf. Comput. Vision, Copenhagen, Denmark, June 2002, vol. 3, pp. 335–349 (2002)

    Google Scholar 

  11. Kanatani, K.: Uncertainty modeling and model selection for geometric inference. IEEE Trans. Patt. Anal. Mach. Intell. 26(10) (to appear, 2004)

    Google Scholar 

  12. Kanatani, K., Sugaya, Y.: Factorization without factorization: Complete Recipe. Memoirs of the Faculty of Engineering, Okayama University 38(2), 61–72 (2004)

    Google Scholar 

  13. Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Sys. Man Cyber. 9(1), 62–66 (1979-1)

    Google Scholar 

  14. Poelman, C.J., Kanade, T.: A paraperspective factorization method for shape and motion recovery. IEEE Trans. Pat. Anal. Mach. Intell. 19(3), 206–218 (1997-3)

    Google Scholar 

  15. Rousseeuw, P.J., Leroy, A.M.: Robust Regression and Outlier Detection. Wiley, New York (1987)

    Book  MATH  Google Scholar 

  16. Schlesinger, M.I., Hlaváč, V.: Ten Lectures on Statistical and Structural Pattern Recognition. Kluwer, Dordrecht (2002)

    Book  MATH  Google Scholar 

  17. Sugaya, Y., Kanatani, K.: Outlier removal for motion tracking by subspace separation. IEICE Trans. Inf. Syst. E86-(D-6), 1095–1102 (2003-6)

    Google Scholar 

  18. Sugaya, Y., Kanatani, K.: Automatic camera model selection for multibody motion segmentation. In: Proc. Workshop on Science of Computer Vision, Okayama, Japan, Sepember 2002, pp. 31–39 (2002)

    Google Scholar 

  19. Sugaya, Y., Kanatani, K.: Automatic camera model selection for multibody motion segmentation. In: Proc. IAPR Workshop on Machine Vision Applications, Nara, Japan, December 2002, pp. 412–415 (2002)

    Google Scholar 

  20. Tomasi, C., Kanade, T.: Detection and Tracking of Point Features, CMU Tech. Rep. CMU-CS-91-132 (April 1991), http://vision.stanford.edu/~birch/klt/

  21. Wu, Y., Zhang, Z., Huang, T.S., Lin, J.Y.: Multibody grouping via orthogonal subspace decomposition, sequences under affine projection. In: Proc. IEEE Conf. Computer Vision Pattern Recog., Kauai, Hawaii, U.S.A., December 2001, vol. 2, pp. 695–701 (2001)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Depertment of Information Technology, Okayama University, Okayama, 700-8530, Japan

    Yasuyuki Sugaya & Kenichi Kanatani

Authors
  1. Yasuyuki Sugaya
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kenichi Kanatani
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Integrated Data Systems Dept., Siemens Corporate Research, Princeton, NJ, USA

    Dorin Comaniciu

  2. Visual Sensorics and Information Processing Lab, J.W. Goethe University, Frankfurt, Germany

    Rudolf Mester

  3. Department of Computer Science, Okayama University, 700-8530, Okayama, Japan

    Kenichi Kanatani

  4. Institute for Vision Systems Engineering, Department of Electrical and Computer Systems Engineering, Monash University, Clayton Vic. 3800, Australia

    David Suter

Rights and permissions

Reprints and permissions

Copyright information

© 2004 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Sugaya, Y., Kanatani, K. (2004). Geometric Structure of Degeneracy for Multi-body Motion Segmentation. In: Comaniciu, D., Mester, R., Kanatani, K., Suter, D. (eds) Statistical Methods in Video Processing. SMVP 2004. Lecture Notes in Computer Science, vol 3247. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30212-4_2

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-30212-4_2

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-23989-5

  • Online ISBN: 978-3-540-30212-4

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation