Advertisement

Highly Consistent Sequential Segmentation

  • Michael Donoser
  • Martin Urschler
  • Hayko Riemenschneider
  • Horst Bischof
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6688)

Abstract

This paper deals with segmentation of image sequences in an unsupervised manner with the goal of getting highly consistent segmentation results from frame-to-frame. We first introduce a segmentation method that uses results of the previous frame as initialization and significantly improves consistency in comparison to a single frame based approach. We also find correspondences between the segmented regions from one frame to the next to further increase consistency. This matching step is based on a modified version of an efficient partial shape matching method which allows identification of similar parts of regions despite topology changes like merges and splits. We use the identified matched parts to define a partial matching cost which is then used as input to pairwise graph matching. Experiments demonstrate that we can achieve highly consistent segmentations for diverse image sequences, even allowing to track manually initialized moving and static objects.

Keywords

Segmentation Method Interest Point Salient Region Partial Match Graph Match 
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.

References

  1. 1.
    Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: From contours to regions: An empirical evaluation. In: Proc. of Conf. on Comp. Vision and Pattern Recognition, CVPR (2009)Google Scholar
  2. 2.
    Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. Trans. on Pattern Analysis and Machine Intelligence (PAMI) 24(4), 509–522 (2002)CrossRefGoogle Scholar
  3. 3.
    Brendel, W., Todorovic, S.: Video object segmentation by tracking regions. In: Proc. of International Conf. on Comp. Vision, ICCV (2009)Google Scholar
  4. 4.
    Bresson, X., Esedoglu, S., Vandergheynst, P., Thiran, J.P., Osher, S.J.: Fast global minimization of the active contour/snake model. Journal of Mathematical Imaging and Vision 28(2), 151–167 (2007)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. Trans. on Pattern Analysis and Machine Intelligence (PAMI) 24(5), 603–619 (2002)CrossRefGoogle Scholar
  6. 6.
    DeMenthon, D., Megret, R.: Spatio-temporal segmentation of videos by hierachical mean shift analysis. In: Proc. of Conf. on Comp. Vision and Pattern Recognition, CVPR (2002)Google Scholar
  7. 7.
    Donoser, M., Riemenschneider, H., Bischof, H.: Efficient partial shape matching of outer contours. In: Zha, H., Taniguchi, R.-i., Maybank, S. (eds.) ACCV 2009. LNCS, vol. 5994, pp. 281–292. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  8. 8.
    Donoser, M., Urschler, M., Hirzer, M., Bischof, H.: Saliency driven total variation segmentation. In: Proc. of International Conf. on Comp. Vision, ICCV (2009)Google Scholar
  9. 9.
    Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. International Journal of Comp. Vision (IJCV) 59 (2004)Google Scholar
  10. 10.
    Felzenszwalb, P., Schwartz, J.D.: Hierarchical matching of deformable shapes. In: Proc. of Conf. on Comp. Vision and Pattern Recognition, CVPR (2007)Google Scholar
  11. 11.
    Goldman, D.B., Gonterman, C., Curless, B., Salesin, D., Seitz., S.M.: Video object annotation, navigation, and composition. In: Proceedings of ACM Symposium on User Interface Software and Technology, UIST (2008)Google Scholar
  12. 12.
    Hedau, V., Arora, H., Ahuja, N.: Matching images under unstable segmentations. In: Proc. of Conf. on Comp. Vision and Pattern Recognition, CVPR (2008)Google Scholar
  13. 13.
    Huang, Y., Liu, Q., Metaxas, D.: Video object segmentation by hypergraph cut. In: Proc. of Conf. on Comp. Vision and Pattern Recognition, CVPR (2009)Google Scholar
  14. 14.
    Leordeanu, M., Hebert, M.: A spectral technique for correspondence problems using pairwise constraints. In: Proc. of International Conf. on Comp. Vision, ICCV (2005)Google Scholar
  15. 15.
    Ling, H., Jacobs, D.W.: Using the inner-distance for classification of articulated shapes. In: Proc. of Conf. on Comp. Vision and Pattern Recognition (CVPR), vol. 2, pp. 719–726 (2005)Google Scholar
  16. 16.
    Pock, T., Unger, M., Cremers, D., Bischof, H.: Fast and exact solution of total variation models on the gpu. In: CVPR Workshop on Visual Computer Vision on GPUs, pp. 1–8 (2008)Google Scholar
  17. 17.
    Shi, J., Malik, J.: Motion segmentation and tracking using normalized cuts. In: Proc. of International Conf. on Comp. Vision, ICCV (1998)Google Scholar
  18. 18.
    Wills, J., Agarwal, S., Belongie, S.: What went where. In: Proc. of Conf. on Comp. Vision and Pattern Recognition, CVPR (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Michael Donoser
    • 1
  • Martin Urschler
    • 2
    • 1
  • Hayko Riemenschneider
    • 1
  • Horst Bischof
    • 1
  1. 1.Institute for Computer Graphics and VisionGraz University of TechnologyAustria
  2. 2.Ludwig Boltzmann Institute for Clinical Forensic ImagingGrazAustria

Personalised recommendations