Near Real-Time Motion Segmentation Using Graph Cuts

  • Thomas Schoenemann
  • Daniel Cremers
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4174)


We present a new approach to integrated motion estimation and segmentation by combining methods from discrete and continuous optimization. The velocity of each of a set of regions is modeled as a Gaussian-distributed random variable and motion models and segmentation are obtained by alternated maximization of a Bayesian a-posteriori probability. We show that for fixed segmentation the model parameters are given by a closed-form solution. Given the velocities, the segmentation is in turn determined using graph cuts which allows a globally optimal solution in the case of two regions. Consequently, there is no contour evolution based on differential increments as for example in level set methods. Experimental results on synthetic and real data show that good segmentations are obtained at speeds close to real-time.


Computer Vision Motion Estimation Motion Segmentation Optimal Segmentation Segmentation Boundary 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Amiaz, T., Kiryati, N.: Dense discontinuous optical flow via contour-based segmentation. In: Int. Conf. on Image Processing, Genova, Italy, vol. 3, pp. 1264–1267 (September 2005)Google Scholar
  2. 2.
    Birchfield, S., Tomasi, C.: Multiway cut for stereo and motion with slanted surfaces. In: IEEE Int. Conf. on Computer Vision, pp. 489–495 (1999)Google Scholar
  3. 3.
    Black, M., Jepson, A.: Eigentracking: Robust matching and tracking of articulated objects using a view-based representation. In: Europ. Conf. on Computer Vision, Cambridge, England. LNCS, pp. 329–342. Springer, Heidelberg (1996)Google Scholar
  4. 4.
    Boykov, Y., Jolly, M.-P.: Interactive graph cuts for optimal boundary & region segmentation of objects in n-d images. In: IEEE Int. Conf. on Computer Vision, vol. 1, pp. 105–112 (2001)Google Scholar
  5. 5.
    Boykov, Y., Kolmogorov, V.: An Experimental Comparison of Min-cut/Max-flow Algorithms for Energy Minimization in Vision. In: Figueiredo, M., Zerubia, J., Jain, A.K. (eds.) EMMCVPR 2001. LNCS, vol. 2134, pp. 359–374. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  6. 6.
    Boykov, Y., Kolmogorov, V.: Computing geodesics and minimal surfaces via graph cuts. In: IEEE Int. Conf. on Computer Vision (2003)Google Scholar
  7. 7.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. on Patt. Anal. and Mach. Intell. 23(11), 1222–1239 (2001)CrossRefGoogle Scholar
  8. 8.
    Brox, T., Bruhn, A., Weickert, J.: Variational motion segmentation with level sets. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 471–483. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  9. 9.
    Cremers, D., Soatto, S.: Motion Competition: A Variational Framework for Piecewise Parametric Motion Segmentation. Int. J. of Computer Vision 62(3), 249–265 (2005)CrossRefGoogle Scholar
  10. 10.
    Cremers, D., Yuille, A.L.: A Generative Model Based Approach to Motion Segmentation. In: Michaelis, B., Krell, G. (eds.) DAGM 2003. LNCS, vol. 2781, pp. 313–320. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  11. 11.
    Ford, L., Fulkerson, D.: Flows in Networks. Princeton University Press, Princeton (1962)MATHGoogle Scholar
  12. 12.
    Greig, D.M., Porteous, B.T., Seheult, A.H.: Exact maximum a posteriori estimation for binary images. J. Roy. Statist. Soc. Ser. B. 51(2), 271–279 (1989)Google Scholar
  13. 13.
    Horn, B., Schunck, B.: Determining optical flow. A.I. 17, 185–203 (1981)Google Scholar
  14. 14.
    Jähne, B., Haußecker, H., Scharr, H., Spies, H., Schmundt, D., Schurr, U.: Study of Dynamical Processes with Tensor-Based Spatiotemporal Image Processing Techniques. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407, pp. 322–336. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  15. 15.
    Juan, O.: On Some Extensions of Level Sets and Graph Cuts & Their Applications to Image and Video Segmentation. PhD thesis, École Nationale des Ponts et Chaussées (May 2006)Google Scholar
  16. 16.
    Kolmogorov, V., Zabih, R.: What energy functions can be minimized via graph cuts? IEEE Trans. on Patt. Anal. and Mach. Intell. 24(5), 657–673 (2004)Google Scholar
  17. 17.
    Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Proc. 7th International Joint Conference on Artificial Intelligence, Vancouver, pp. 674–679 (1981)Google Scholar
  18. 18.
    Schnörr, C.: Determining optical flow for irregular domains by minimizing quadratic functionals of a certain class. Int. J. of Computer Vision 6(1), 25–38 (1991)CrossRefGoogle Scholar
  19. 19.
    Wang, J., Adelson, E.: Representating moving images with layers. IEEE Trans. on Image Processing 3(5), 625–638 (1994)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Thomas Schoenemann
    • 1
  • Daniel Cremers
    • 1
  1. 1.CVPR GroupUniversity of BonnBonnGermany

Personalised recommendations