Perspective n-View Multibody Structure-and-Motion Through Model Selection

  • Konrad Schindler
  • James U
  • Hanzi Wang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3951)


Multi-body structure-and-motion (MSaM) is the problem to establish the multiple-view geometry of an image sequence of a 3D scene, where the scene consists of multiple rigid objects moving relative to each other. So far, solutions have been proposed for several restricted settings, such as only two views, affine projection, and perspective projection of linearly moving points. We give a solution for sequences of several images, full perspective projection, and general rigid motion. It can deal with the fact that the set of correspondences changes over time, and is robust to outliers. The proposed solution is based on Monte-Carlo sampling and clustering of two-view motions, linking them through the sequence, and model selection to yield the best explanation for the entire sequence.


Consecutive Frame Feature Track Dynamic Scene Temporal Consistency Motion Segmentation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2000)MATHGoogle Scholar
  2. 2.
    Faugeras, O., Luong, Q.T., Papadopoulo, T.: The geometry of multiple images. MIT Press, Cambridge (2001)Google Scholar
  3. 3.
    Wolf, L., Shashua, A.: Two-body segmentation from two perspective views. In: Proc. CVPR, pp. 263–270 (2001)Google Scholar
  4. 4.
    Vidal, R., Soatto, S., Ma, Y., Sastry, S.: Segmentation of dynamic scenes from the multibody fundamental matrix. In: Proc. ECCV Workshop on Visual Modeling of Dynamic Scenes (2002)Google Scholar
  5. 5.
    Costeira, J., Kanade, T.: A multi-body factorization method for motion analysis. In: Proc. 5th ICCV, pp. 1071–1077 (1995)Google Scholar
  6. 6.
    Vidal, R., Hartley, R.: Motion segmentation with missing data using PowerFactorization and GPCA. In: Proc. CVPR, pp. 310–316 (2004)Google Scholar
  7. 7.
    Han, M., Kanade, T.: Reconstruction of scenes with multiple linearly moving objects. In: Proc. CVPR, pp. 542–549 (2000)Google Scholar
  8. 8.
    Torr, P.H.S.: Geometric motion segmentation and model selection. Philosophical Transactions of the Royal Society of London A 356, 1321–1340 (1998)MathSciNetCrossRefMATHGoogle Scholar
  9. 9.
    Tong, W.S., Tang, C.K., Medioni, G.: Simultaneous two-view epipolar geometry estimation and motion segmentation by 4D tensor voting. IEEE TPAMI 26, 1167–1184 (2004)CrossRefGoogle Scholar
  10. 10.
    Schindler, K., Suter, D.: Two-view multibody structure-and-motion with outliers. In: Proc. CVPR, pp. 676–683 (2005)Google Scholar
  11. 11.
    Nistér, D.: An efficient solution to the five-point relative pose problem. IEEE TPAMI 26, 756–770 (2004)CrossRefGoogle Scholar
  12. 12.
    Wills, J., Agarwal, S., Belongie, S.: What went where. In: Proc. CVPR, pp. 37–44 (2003)Google Scholar
  13. 13.
    Torr, P.H.S.: Model selection for structure and motion recovery from multiple images. In: Bab-Hadiashar, A., Suter, D. (eds.) Data Segmentation and Model Selection for Computer Vision, Springer, Heidelberg (2000)Google Scholar
  14. 14.
    Leonardis, A., Gupta, A., Bajcsy, R.: Segmentation of range images as the search for geometric parametric models. IJCV 14, 253–277 (1995)CrossRefGoogle Scholar
  15. 15.
    Tomasi, C., Kanade, T.: Detection and tracking of point features. Technical Report CMU-CS-91-132, Carnegie Mellon University (1991)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Konrad Schindler
    • 1
  • James U
    • 1
  • Hanzi Wang
    • 1
  1. 1.Institute for Vision Systems EngineeringMonash UniversityClaytonAustralia

Personalised recommendations