On the Relationship Between Image and Motion Segmentation

  • Adrian Barbu
  • Song Chun Zhu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3667)


In this paper we present a generative model for image sequences, which can be applied to motion segmentation and tracking, and to image sequence compression. The model consists of regions of relatively constant color that have a motion model explaining their motion in time. At each frame, the model can allow accretion and deletion of pixels. We also present an algorithm for maximizing the posterior probability of the image sequence model, based on the recently introduced Swendsen-Wang Cuts algorithm. We show how one can use multiple cues and model switching in a reversible manner to make better bottom-up proposals. The algorithm works on the 3d spatiotemporal pixel volume to reassign entire trajectories of constant color in very few steps, while maintaining detailed balance.


Image Segmentation Motion Model Image Model Detailed Balance Region Trajectory 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Barbu, A., Zhu, S.C.: Graph Partition by Swendsen-Wang Cuts. In: IEEE International Conference in Computer Vision (2003)Google Scholar
  2. 2.
    Black, M.J., Jepson, A.D.: Estimating optical flow in segmented images using variable order parametric models with local deformations. IEEE Trans PAMI 18(10), 972–986 (1996)Google Scholar
  3. 3.
    Cremers, D., Soatto, S.: Variational Space-Time Motion Segmentation. In: ICCV (2003)Google Scholar
  4. 4.
    Horn, B.K.P.: Robot Vision. MIT Press, Cambridge (1986)Google Scholar
  5. 5.
    Gaucher, L., Medioni, G.: Accurate Motion Flow with Discontinuities. In: ICCV, pp. 695–702 (1999)Google Scholar
  6. 6.
    Torr, P.H.S.: Geometric motion segmentation and model selection. Philosophical Trans of the Royal Society A, 1321–1340 (1998)Google Scholar
  7. 7.
    Weiss, Y.: Smoothness in Layers: Motion segmentation using nonparametric mixture estimation. In: Proc. of IEEE CVPR, pp. 520–527 (1997)Google Scholar
  8. 8.
    Wolff, U.: Collective Monte Carlo updating for spin systems. Phys. Rev. Lett. 62(4), 361–364 (1989)CrossRefGoogle Scholar
  9. 9.
    Yuille, A.L., Grzywacz, N.M.: A mathematical analysis of the motion coherence theory. Int. J. Computer Vision 3, 155–175 (1989)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Adrian Barbu
    • 1
  • Song Chun Zhu
    • 2
  1. 1.UCLA, Computer Science DepartmentLos AngelesUSA
  2. 2.UCLA, Statistics DepartmentLos angelesUSA

Personalised recommendations