Abstract
This paper presents a novel approach for motion segmentation from feature trajectories with missing data. It consists of two stages. In the first stage, missing data are filled in by applying a factorization technique to the matrix of trajectories. Since the number of objects in the scene is not given and the rank of this matrix can not be directly computed, a simple technique for matrix rank estimation, based on a frequency spectra representation, is proposed. In the second stage, motion segmentation is obtained by using a clustering approach based on the normalized cuts criterion. Finally, the shape S and motion M of each of the obtained clusters (i.e., single objects) are recovered by applying classical SFM techniques. Experiments with synthetic and real data are provided in order to demonstrate the viability of the proposed approach.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Boult, T., Brown, L.: Factorization-based segmentation of motions. In: IEEE Workshop on Motion Understanding, pp. 179–186 (1991)
Costeira, J., Kanade, T.: A multibody factorization method for independently moving objects. International Journal of Computer Vision, 159–179 (1998)
Han, M., Kanade, T.: Reconstruction of a scene with multiple linearly moving objects. International Journal of Computer Vision 53, 285–300 (2000)
Kanatani, K.: Motion segmentation by subspace separation and model selection. In: CVPR, vol. 2, pp. 586–591 (2001)
Zelnik-Manor, L., Irani, M.: Degeneracies, dependencies and their implications in multi-body and multi-sequence factorization. In: CVPR, pp. 287–293 (2003)
Yan, J., Pollefeys, M.: A general framework for motion segmentation: Independent, articulated, rigid, non-rigid, degenerate and non-degenerate. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3954, pp. 94–106. Springer, Heidelberg (2006)
Vidal, R., Hartley, R.: Motion segmentation with missing data using powerfactorization and GPCA. In: CVPR (2004)
Tomasi, C., Kanade, T.: Shape and motion from image streams: a factorization method. Full report on the orthographic case (1992)
Buchanan, A., Fitzgibbon, A.: Damped newton algorithms for matrix factorization with missing data. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 316–322 (2005)
Golub, G., Van Loan, C. (eds.): Matrix Computations. The Johns Hopkins Univ. Press, Baltimore (1989)
Chen, P., Suter, D.: Recovering the missing components in a large noisy low-rank matrix: Application to SFM. IEEE Transactions on PAMI 26 (2004)
Weiss, Y.: Segmentation using eigenvectors: a unifying view. In: International Conference on Computer Vision (1999)
Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Transactions on PAMI (2000)
Kanatani, K.: Statistical optimization and geometric inference in computer vision. Philosophical transactions: Mathematical, physical and engineering sciences 356, 1303–1320 (1998)
Ma, Y., Soatto, J., Kosecká, J., Sastry, S.: An invitation to 3D vision: From images to geometric models. Springer, Heidelberg (2004)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Julià, C., Sappa, A., Lumbreras, F., Serrat, J., López, A. (2007). Motion Segmentation from Feature Trajectories with Missing Data. In: Martí, J., Benedí, J.M., Mendonça, A.M., Serrat, J. (eds) Pattern Recognition and Image Analysis. IbPRIA 2007. Lecture Notes in Computer Science, vol 4477. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-72847-4_62
Download citation
DOI: https://doi.org/10.1007/978-3-540-72847-4_62
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-72846-7
Online ISBN: 978-3-540-72847-4
eBook Packages: Computer ScienceComputer Science (R0)