Advertisement

Space-Time Multi-Resolution Banded Graph-Cut for Fast Segmentation

  • Tobi Vaudrey
  • Daniel Gruber
  • Andreas Wedel
  • Jens Klappstein
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5096)

Abstract

Applying real-time segmentation is a major issue when processing every frame of image sequences. In this paper, we propose a modification of the well known graph-cut algorithm to improve speed for discrete segmentation. Our algorithm yields real-time segmentation, using graph-cut, by performing a single cut on an image with regions of different resolutions, combining space-time pyramids and narrow bands. This is especially suitable for image sequences, as segment borders in one image are refined in the next image. The fast computation time allows one to use information contained in every image frame of an input image stream at 20 Hz, on a standard PC. The algorithm is applied to traffic scenes, using a monocular camera installed in a moving vehicle. Our results show the segmentation of moving objects with similar results to standard graph-cut, but with improved speed.

Keywords

Augmented Reality Temporal Prediction Motion Segmentation Motion Constraint Segmentation Boundary 
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.
    Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. In: Energy Minimization Methods in Computer Vision and Pattern Recognition, pp. 359–374 (2001)Google Scholar
  2. 2.
    Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. In: IEEE Trans. on Pattern Analysis and Machine Intelligence, pp. 1222–1239 (2001)Google Scholar
  3. 3.
    Cremers, D., Rousson, M., Deriche, R.: A review of statistical approaches to level set segmentation: integrating color, texture, motion and shape. International Journal of Computer Vision 72(2), 195–215 (2007)CrossRefGoogle Scholar
  4. 4.
    Cremers, D., Soatto, S.: Motion competition: A variational framework for piecewise parametric motion segmentation. International Journal of Computer Vision 62(3), 249–265 (2005)CrossRefGoogle Scholar
  5. 5.
    Greig, D.M., Porteous, B.T., Seheult, A.H.: Exact maximum a posteriori estimation for binary images. Journal of the Royal Statistical Society 51, 271–279 (1989)Google Scholar
  6. 6.
    Klappstein, J., Stein, F., Franke, U.: Monocular motion detection using spatial constraints in a unified manner. In: IEEE Intelligent Vehicles Symposium, pp. 261–267 (2006)Google Scholar
  7. 7.
    Kohli, P., Torr, P.H.S.: Effciently solving dynamic markov random fields using graph cuts. In: ICCV, pp. 922–929 (2005)Google Scholar
  8. 8.
    Kolmogorov, V., Zabih, R.: What energy functions can be minimized via graph cuts? In: IEEE Trans. Pattern Analysis and Machine Intelligence, pp. 147–159 (2004)Google Scholar
  9. 9.
    Lombaert, H., Sun, Y., Grady, L., Xu, C.: A multilevel banded graph cuts method for fast image segmentation. In: ICCV, pp. 259–265 (2005)Google Scholar
  10. 10.
    Malcolm, J., Rathi, Y., Tannenbaum, A.: Multi-object tracking through clutter using graph cuts. In: ICCV, pp. 1–5 (2007)Google Scholar
  11. 11.
    Mooser, J., You, S., Neumann, U.: Real-time object tracking for augmented reality combining graph cuts and optical flow. In: ISMAR: Int. Symposium on Mixed and Augmented Reality, pp. 145–152 (2007)Google Scholar
  12. 12.
    Osher, S., Paragios, N.: Geometric Level Set Methods in Imaging,Vision,and Graphics. Springer, New York (2003)CrossRefzbMATHGoogle Scholar
  13. 13.
    Pham, D.L., Xu, C., Prince, J.L.: Current methods in medical image segmentation. In: Annual Review of Biomedical Engineering, vol. 2, pp. 315–337 (2000)Google Scholar
  14. 14.
    Rother, C., Kolmogorov, V., Blake, A.: “GrabCut”: interactive foreground extraction using iterated graph cuts.  23(3), 309–314 (August 2004)Google Scholar
  15. 15.
    Shapiro, L.G., Stockman, G.C.: Computer Vision, New Jersey, pp. 279–325. Prentice-Hall, Englewood Cliffs (2001)Google Scholar
  16. 16.
    Sinop, A.K., Grady, L.: Accurate banded graph cut segmentation of thin structures using laplacian pyramids. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006. LNCS, vol. 4191, pp. 896–903. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  17. 17.
    Stein, F.: Efficient computation of optical flow using the census transform. In: Rasmussen, C.E., Bülthoff, H.H., Schölkopf, B., Giese, M.A. (eds.) DAGM 2004. LNCS, vol. 3175, pp. 79–86. Springer, Heidelberg (2004)Google Scholar
  18. 18.
    Tomasi, C., Kanade, T.: Detection and tracking of point features. Technical report, Carnegie Mellon University Technical Report CMU-CS-91-132 (1991)Google Scholar
  19. 19.
    Wang, J., Bhat, P., Colburn, R.A., Agrawala, M., Cohen, M.F.: Interactive video cutout. SIGGRAPH 24, 585–594 (2005)CrossRefGoogle Scholar
  20. 20.
    Wedel, A., Schoenemann, T., Brox, T., Cremers, D.: Warpcut - fast obstacle segmentation in monocular video. In: Hamprecht, F.A., Schnörr, C., Jähne, B. (eds.) DAGM 2007. LNCS, vol. 4713, pp. 264–273. Springer, Heidelberg (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Tobi Vaudrey
    • 1
  • Daniel Gruber
    • 2
  • Andreas Wedel
    • 3
    • 4
  • Jens Klappstein
    • 3
  1. 1.The University of AucklandNew Zealand
  2. 2.Universität KonstanzGermany
  3. 3.Daimler Group Research, SindelfingenGermany
  4. 4.Universität BonnGermany

Personalised recommendations