Evaluation and Selection of Models for Motion Segmentation

  • Kenichi Kanatani
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2352)


We first present an improvement of the subspace separation for motion segmentation by newly introducing the affine space constraint. We point out that this improvement does not always fare well due to the effective noise it introduces. In order to judge which solution to adopt if different segmentations are obtained, we test two measures using real images: the standard F test, and the geometric model selection criteria.


Greedy Algorithm Real Image Space Constraint Space Separation World Coordinate System 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    B. Efron and R. J. Tibshirani, An Introduction to Bootstrap, Chapman-Hall, New York, 1993.zbMATHGoogle Scholar
  2. 2.
    J. P. Costeira and T. Kanade, A multibody factorization method for independently moving objects, Int. J. Comput. Vision, 29-;3 (1998), 159–179.CrossRefGoogle Scholar
  3. 3.
    C. W. Gear, Multibody grouping from motion images, Int. J. Comput. Vision, 29-2 (1998), 133–150.CrossRefGoogle Scholar
  4. 4.
    N. Ichimura, Motion segmentation based on factorization method and discriminant criterion, Proc. 7th Int. Conf. Comput. Vision, September 1999, Kerkyra, Greece, pp. 600–605.Google Scholar
  5. 5.
    N. Ichimura, Motion segmentation using feature selection and subspace method based on shape space, Proc. 15th Int. Conf. Pattern. Recog., September 2000, Barcelona, Spain, Vol. 3, pp. 858–864Google Scholar
  6. 6.
    K. Inoue and K. Urahama, Separation of multiple objects in motion images by clustering, Proc. 8th Int. Conf. Comput. Vision, July 2001, Vancouver, Canada, Vol. 1, pp. 219–224.Google Scholar
  7. 7.
    K. Kanatani, Statistical Optimization for Geometric Computation: Theory and Practice, Elsevier Science, Amsterdam, The Netherlands, 1996.zbMATHCrossRefGoogle Scholar
  8. 8.
    K. Kanatani, Motion segmentation by subspace separation and model selection, Proc. 8th Int. Conf. Comput. Vision, July 2001, Vancouver, Canada, Vol. 2, pp. 301–306.Google Scholar
  9. 9.
    K. Kanatani, Model selection for geometric inference, plenary talk, Proc. the 5th Asian Conf. Comput. Vision, January 2002, Melbourne, Australia, Vol. 1, pp. xxi–xxxii.Google Scholar
  10. 10.
    K. Kanatani, Motion segmentation by subspace separation: Model selection and reliability evaluation, Int. J. Image Gr., Vol. 2, (2002), to appear.Google Scholar
  11. 11.
    K. Kanatani and C. Matsunaga, Estimating the number of independent motions for multibody segmentation, Proc. the 5th Asian Conf. Comput. Vision, January 2002, Melbourne, Australia, Vol. 1, pp. 7–12.Google Scholar
  12. 12.
    A. Maki and C. Wiles, Geotensity constraint for 3D surface reconstruction under multiple light sources, Proc. 6th Euro. Conf. Comput. Vision, June–July 2000, Dublin, Ireland, Vol. 1, pp. 725–741.Google Scholar
  13. 13.
    A. Maki and H. Hattori, Illumination subspace for multibody motion segmentation, Proc. IEEE Conf. Comput. Vision Pattern Recog., December 2001, Kauai, Hawaii, Vol. 2, pp. 11–17.Google Scholar
  14. 14.
    N. Otsu, A threshold selection method from gray-level histograms, IEEE Trans. Sys. Man Cyber., 9-1 (1979), 62–66.Google Scholar
  15. 15.
    C. J. Poelman and T. Kanade, A paraperspective factorization method for shape and motion recovery, IEEE Trans. Pat. Anal. Mach. Intell., 19-3 (1997), 206–218.CrossRefGoogle Scholar
  16. 16.
    P. J. Rousseeuw and A. M. Leroy, Robust Regression and Outlier Detection, Wiley, New York, 1987.zbMATHCrossRefGoogle Scholar
  17. 17.
    C. Tomasi and T. Kanade, Shape and motion from image streams under orthography—A factorization method, Int. J. Comput. Vision, 9-2 (1992), 137–154.CrossRefGoogle Scholar
  18. 18.
    P. H. S. Torr, A. Zisserman and S. J. Maybank, Robust detection of degenerate configurations while estimating the fundamental matrix, Comput. Vision Image Understand., 71-3 (1998), 312–333.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Kenichi Kanatani
    • 1
  1. 1.Department of Information TechnologyOkayama UniversityOkayamaJapan

Personalised recommendations