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.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Costeira, J.P., Kanade, T.: A multibody factorization method for independently moving objects. Int. J. Comput. Vision 29(3), 159–179 (1998-1999)
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)
Gear, C.W.: Multibody grouping from motion images. Int. J. Comput. Vision 29(2), 133–150 (1998-8/9)
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)
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)
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)
Kanatani, K.: Geometric information criterion for model selection. Int. J. Comput. Vision 26(3), 171–189 (1998-2/3)
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)
Kanatani, K.: Motion segmentation by subspace separation: Model selection and reliability evaluation. Int. J. Image Graphics 2(2), 179–197 (2002-4)
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)
Kanatani, K.: Uncertainty modeling and model selection for geometric inference. IEEE Trans. Patt. Anal. Mach. Intell. 26(10) (to appear, 2004)
Kanatani, K., Sugaya, Y.: Factorization without factorization: Complete Recipe. Memoirs of the Faculty of Engineering, Okayama University 38(2), 61–72 (2004)
Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Sys. Man Cyber. 9(1), 62–66 (1979-1)
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)
Rousseeuw, P.J., Leroy, A.M.: Robust Regression and Outlier Detection. Wiley, New York (1987)
Schlesinger, M.I., Hlaváč, V.: Ten Lectures on Statistical and Structural Pattern Recognition. Kluwer, Dordrecht (2002)
Sugaya, Y., Kanatani, K.: Outlier removal for motion tracking by subspace separation. IEICE Trans. Inf. Syst. E86-(D-6), 1095–1102 (2003-6)
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)
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)
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/
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)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights 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