Advertisement

Dense Motion and Disparity Estimation Via Loopy Belief Propagation

  • Michael Isard
  • John MacCormick
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3852)

Abstract

We describe a method for computing a dense estimate of motion and disparity, given a stereo video sequence containing moving non-rigid objects. In contrast to previous approaches, motion and disparity are estimated simultaneously from a single coherent probabilistic model that correctly accounts for all occlusions, depth discontinuities, and motion discontinuities. The results demonstrate that simultaneous estimation of motion and disparity is superior to estimating either in isolation, and show the promise of the technique for accurate, probabilistically justified, scene analysis.

Keywords

Reference Image Object Boundary Foreground Object Motion Problem Disparity Estimation 
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.
    Waxman, A., Duncan, J.: Binocular image flows: Steps towards stereo-motion fusion. IEEE Trans. on PAMI 8, 715–729 (1986)Google Scholar
  2. 2.
    Williams, O., Isard, M., MacCormick, J.: Estimating disparity and occlusions in stereo video sequences. In: Proc. CVPR (2005)Google Scholar
  3. 3.
    Chang, Y., Aggarwal, J.: Line correspondences from cooperating spatial and temporal grouping processes for a sequence of images. Computer Vision and Image Understanding 67, 186–201 (1997)CrossRefGoogle Scholar
  4. 4.
    Ho, A., Pong, T.: Cooperative fusion of stereo and motion. Pattern Recognition 29, 121–130 (1996)CrossRefGoogle Scholar
  5. 5.
    Wang, W., Duncan, J.: Recovering the three dimensional motion and structure of multiple moving objects from binocular image flows. Computer Vision and Image Understanding 63, 430–446 (1996)CrossRefGoogle Scholar
  6. 6.
    Sun, J., Shum, H.Y., Zheng, N.N.: Stereo matching using belief propagation. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2351, pp. 510–524. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  7. 7.
    Kolmogorov, V., Zabih, R.: Computing visual correspondence with occlusions using graph cuts. In: Proc. Int. Conf. on Computer Vision (2001)Google Scholar
  8. 8.
    Criminisi, A., Shotton, J., Blake, A., Torr, P.: Gaze manipulation for one-to-one teleconferencing. In: Proc. Int. Conf. on Computer Vision (2003)Google Scholar
  9. 9.
    Leung, C., Appleton, B., Lovell, B.C., Sun, C.: An energy minimisation approach to stereo-temporal dense reconstruction. In: Proc. Int. Conf. on Pattern Recognition (2004)Google Scholar
  10. 10.
    Zhang, L., Curless, B., Seitz, S.M.: Spacetime stereo: Shape recovery for dynamic scenes. In: Proc. CVPR., vol. 2, pp. 367–374 (2003)Google Scholar
  11. 11.
    Shao, J.: Generation of temporally consistent multiple virtual camera views from stereoscopic image sequences. Int. J. Comput. Vision 47, 171–180 (2002)zbMATHCrossRefGoogle Scholar
  12. 12.
    Vedula, S., Baker, S., Rander, P., Collins, R., Kanade, T.: Three-dimensional scene flow. In: Proc. Int. Conf. on Computer Vision, vol. 2, pp. 722–729 (1999)Google Scholar
  13. 13.
    Belhumeur, P.: A Bayesian approach to binocular stereopsis. Int. J. Computer Vision 19, 237–260 (1996)CrossRefGoogle Scholar
  14. 14.
    Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Computer Vision (2002)Google Scholar
  15. 15.
    Baker, S., Matthews, I.: Lucas-Kanade 20 years on: A unifying framework. Int. J. Comput. Vision 56, 221–255 (2004)CrossRefGoogle Scholar
  16. 16.
    Isard, M., MacCormick, J.: Dense motion and disparity estimation via loopy belief propagation. Technical report, Microsoft Research (2005)Google Scholar
  17. 17.
    Blake, A., et al.: Bi-layer segmentation of binocular stereo video. In: Proc. CVPR (2005)Google Scholar
  18. 18.
    Yedidia, J., Freeman, W., Weiss, Y.: Understanding Belief Propagation and its Generalizations. In: Exploring Artificial Intelligence in the New Millennium, Elsevier Science, Amsterdam (2003)Google Scholar
  19. 19.
    Felzenszwalb, P., Huttenlocher, D.: Efficient belief propagation for early vision. In: Proc. CVPR (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Michael Isard
    • 1
  • John MacCormick
    • 1
  1. 1.Microsoft Research Silicon ValleyMountain ViewUSA

Personalised recommendations