Advertisement

Robust Multi-body Motion Tracking Using Commute Time Clustering

  • Huaijun Qiu
  • Edwin R. Hancock
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3951)

Abstract

The presence of noise renders the classical factorization method almost impractical for real-world multi-body motion tracking problems. The main problem stems from the effect of noise on the shape interaction matrix, which looses its block-diagonal structure and as a result the assignment of elements to objects becomes difficult. The aim in this paper is to overcome this problem using graph-spectral embedding and the k-means algorithm. To this end we develop a representation based on the commute time between nodes on a graph. The commute time (i.e. the expected time taken for a random walk to travel between two nodes and return) can be computed from the Laplacian spectrum using the discrete Green’s function, and is an important property of the random walk on a graph. The commute time is a more robust measure of the proximity of data than the raw proximity matrix. Our embedding procedure preserves commute time, and is closely akin to kernel PCA, the Laplacian eigenmap and the diffusion map. We illustrate the results both on the synthetic image sequences and real world video sequences, and compare our results with several alternative methods.

Keywords

Heat Kernel Laplacian Matrix Locality Preserve Projection Motion Segmentation Commute Time 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Belkin, M., Niyogi, P.: Laplacian eigenmaps for dimensionality reduction and data representation. Neural Computation 15(6), 1373–1396 (2003)CrossRefMATHGoogle Scholar
  2. 2.
    Chung, F.R.K., Yau, S.-T.: Discrete green’s functions. J. Combin. Theory Ser, 191–214 (2000)Google Scholar
  3. 3.
    Coifman, R.R., Lafon, S., Lee, A.B., Maggioni, M., Nadler, B., Warner, F., Zucker, S.W.: Geometric diffusions as a tool for harmonic analysis and structure definition of data: Diffusion maps. National Academy of Sciences 102(21), 7426–7431 (2005)CrossRefGoogle Scholar
  4. 4.
    Costeira, J., Kanade, T.: A multibody factorization method for independently moving objects. IJCV 29(3), 159–179 (1997)CrossRefGoogle Scholar
  5. 5.
    Fan, Z., Zhou, J., Wu, Y.: Inference of multiple subspaces from high-dimensional data and application to multibody grouping. In: CVPR, pp. 661–666 (2004)Google Scholar
  6. 6.
    Fan, Z., Zhou, J., Wu, Y.: Multibody motion segmentation based on simulated annealing. In: CVPR, pp. 776–781 (2004)Google Scholar
  7. 7.
    Gear, C.W.: Multibody grouping from motion images. IJCV 29(2), 130–150 (1998)CrossRefGoogle Scholar
  8. 8.
    Gruber, A., Weiss, Y.: Multibody factorization with uncertainty and missing data using the em algorithm. In: CVPR, pp. 707–714 (2004)Google Scholar
  9. 9.
    Ichimura, N.: Motion segmentation based on factorization method and discriminant criterion. In: ICCV, pp. 600–605 (1999)Google Scholar
  10. 10.
    Kanatani, K.: Motion segmentation by subspace separation and model selection. In: ICCV, pp. 301–306 (2001)Google Scholar
  11. 11.
    MacQueen, J.B.: Some methods for classification and analysis of multivariate observations. In: Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, pp. 281–297 (1967)Google Scholar
  12. 12.
    Park, J.-H., Zha, H., Kasturi, R.: Spectral clustering for robust motion segmentation. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3024, pp. 390–401. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  13. 13.
    Pavan, M., Pelillo, M.: A new graph-theoretic approach to clustering and segmentation. In: CVPR 2003, pp. I:145–152 (2003)Google Scholar
  14. 14.
    Qiu, H., Hancock, E.R.: Image segmentation using commute times. In: BMVC, pp. 929–938 (2005)Google Scholar
  15. 15.
    Sch, B., Smola, A., Muller, K.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Computation 10, 1299–1319 (1998)CrossRefGoogle Scholar
  16. 16.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE PAMI 22(8), 888–905 (2000)CrossRefGoogle Scholar
  17. 17.
    Shi, J., Tomasi, C.: Good features to track. In: CVPR, pp. 593–600 (1994)Google Scholar
  18. 18.
    Sugaya, Y., Kanatani, K.: Outlier removal for motion tracking by subspace separation. IEICE Trans. INF and SYST E86-D(6), 1095–1102 (2003)Google Scholar
  19. 19.
    Sugaya, Y., Kanatani, K.: Multi-stage unsupervised learning for multi-body motion segmentation. IEICE Trans. INF and SYST E87-D(7), 1935–1942 (2004)Google Scholar
  20. 20.
    Weiss, Y.: Segmentatoin using eigenvectors: a unifying view. In: ICCV, pp. 975–982 (1999)Google Scholar
  21. 21.
    Wu, Y., Zhang, Z., Huang, T.S., Lin, J.Y.: Multibody grouping via orthogonal subspace decomposition. In: CVPR, pp. 252–257 (2001)Google Scholar
  22. 22.
    Zelnik-Manor, L., Irani, M.: Degeneracies, dependencies and their implications in multi-body and multi-sequence factorizations. In: CVPR, pp. 287–293 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Huaijun Qiu
    • 1
  • Edwin R. Hancock
    • 1
  1. 1.Department of Computer ScienceUniversity of YorkYorkUK

Personalised recommendations