Skip to main content
SpringerLink
Log in

Learning Must-Link Constraints for Video Segmentation Based on Spectral Clustering

  • Conference paper
  • First Online:
Pattern Recognition (GCPR 2014)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 8753))

Included in the following conference series:

Abstract

In recent years it has been shown that clustering and segmentation methods can greatly benefit from the integration of prior information in terms of must-link constraints. Very recently the use of such constraints has been integrated in a rigorous manner also in graph-based methods such as normalized cut. On the other hand spectral clustering as relaxation of the normalized cut has been shown to be among the best methods for video segmentation. In this paper we merge these two developments and propose to learn must-link constraints for video segmentation with spectral clustering. We show that the integration of learned must-link constraints not only improves the segmentation result but also significantly reduces the required runtime, making the use of costly spectral methods possible for today’s high quality video.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    correct refers to the desired ground truth segmentation, which ideally corresponds with the optimal segmentation \(S^*\).

  2. 2.

    certain groupings are the conservative grouping decisions which we propose to learn.

References

  1. Alpert, S., Galun, M., Brandt, A., Basri, R.: Image segmentation by probabilistic bottom-up aggregation and cue integration. TPAMI 34(2), 315–326 (2012)

    Article  Google Scholar 

  2. Andres, B., Kappes, J.H., Beier, T., Köthe, U., Hamprecht, F.A.: Probabilistic image segmentation with closedness constraints. In: ICCV (2011)

    Google Scholar 

  3. Arbeláez, P., Maire, M., Fowlkes, C.C., Malik, J.: Contour detection and hierarchical image segmentation. TPAMI 33(5), 898–916 (2011)

    Article  Google Scholar 

  4. Banica, D., Agape, A., Ion, A., Sminchisescu, C.: Video object segmentation by salient segment chain composition. In: ICCV, IPGM Workshop (2013)

    Google Scholar 

  5. Basu, S., Davidson, I., Wagstaff, K.: Constrained Clustering: Advances in Algorithms, Theory, and Applications. Chapman & Hall, Boca Raton (2008)

    Google Scholar 

  6. Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)

    Article  MATH  Google Scholar 

  7. Brendel, W., Todorovic, S.: Video object segmentation by tracking regions. In: ICCV (2009)

    Google Scholar 

  8. Brox, T., Malik, J.: Object segmentation by long term analysis of point trajectories. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 282–295. Springer, Heidelberg (2010)

    Chapter  Google Scholar 

  9. Bühler, T., Hein, M.: Spectral clustering based on the graph p-Laplacian. In: ICML (2009)

    Google Scholar 

  10. Chang, J., Wei, D., Fisher, J.W.: A video representation using temporal superpixels. In: CVPR (2013)

    Google Scholar 

  11. Cheng, H.T., Ahuja, N.: Exploiting nonlocal spatiotemporal structure for video segmentation. In: CVPR (2012)

    Google Scholar 

  12. Criminisi, A., Shotton, J., Konukoglu, E.: Decision forests: a unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning. In: Foundations and Trends in Computer Graphics and Vision (2012)

    Google Scholar 

  13. Eriksson, A.P., Olsson, C., Kahl, F.: Normalized cuts revisited: a reformulation for segmentation with linear grouping constraints. In: ICCV (2007)

    Google Scholar 

  14. Fowlkes, C., Malik, J.: How much does globalization help segmentation?. Technical report, EECS - UC Berkeley (2004)

    Google Scholar 

  15. Fragkiadaki, K., Shi, J.: Video segmentation by tracing discontinuities in a trajectory embedding. In: CVPR (2012)

    Google Scholar 

  16. Galasso, F., Keuper, M., Brox, T., Schiele, B.: Spectral graph reduction for efficient image and streaming video segmentation. In: CVPR (2014)

    Google Scholar 

  17. Galasso, F., Nagaraja, N.S., Cardenas, T.Z., Brox, T., Schiele, B.: A unified video segmentation benchmark: annotation, metrics and analysis. In: ICCV (2013)

    Google Scholar 

  18. Galasso, F., Cipolla, R., Schiele, B.: Video segmentation with superpixels. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012, Part I. LNCS, vol. 7724, pp. 760–774. Springer, Heidelberg (2013)

    Chapter  Google Scholar 

  19. Galasso, F., Iwasaki, M., Nobori, K., Cipolla, R.: Spatio-temporal clustering of probabilistic region trajectories. In: ICCV (2011)

    Google Scholar 

  20. Grundmann, M., Kwatra, V., Han, M., Essa, I.: Efficient hierarchical graph-based video segmentation. In: CVPR (2010)

    Google Scholar 

  21. Hein, M., Bühler, T.: An inverse power method for nonlinear eigenproblems with applications in 1spectral clustering and sparse pca. In: NIPS (2010)

    Google Scholar 

  22. Hein, M., Setzer, S.: Beyond spectral clustering - tight relaxations of balanced graph cuts. In: NIPS (2011)

    Google Scholar 

  23. Jain, V., Turaga, S.C., Briggman, K.L., Helmstaedter, M., Denk, W., Seung, H.S.: Learning to agglomerate superpixel hierarchies. In: NIPS (2011)

    Google Scholar 

  24. Kamvar, S.D., Klein, D., Manning, C.D.: Spectral learning. In: IJCAI (2003)

    Google Scholar 

  25. Kannan, A., Jojic, N., Frey, B.J.: Generative model for layers of appearance and deformation. In: AISTATS (2005)

    Google Scholar 

  26. Kumar, M.P., Torr, P., Zisserman, A.: Learning layered motion segmentations of video. IJCV 76, 301–319 (2008)

    Article  Google Scholar 

  27. Lee, Y.J., Kim, J., Grauman, K.: Key-segments for video object segmentation. In: ICCV (2011)

    Google Scholar 

  28. Lezama, J., Alahari, K., Sivic, J., Laptev, I.: Track to the future: Spatio-temporal video segmentation with long-range motion cues. In: CVPR (2011)

    Google Scholar 

  29. Li, F., Kim, T., Humayun, A., Tsai, D., Rehg, J.M.: Video segmentation by tracking many figure-ground segments. In: ICCV (2013)

    Google Scholar 

  30. Li, Z., Liu, J., Tang, X.: Constrained clustering via spectral regularization. In: CVPR (2009)

    Google Scholar 

  31. von Luxburg, U.: A tutorial on spectral clustering. Stat. Comput. 17(4), 395–416 (2007)

    Article  MathSciNet  Google Scholar 

  32. Maire, M., Yu, S.X.: Progressive multigrid eigensolvers for multiscale spectral segmentation. In: ICCV (2013)

    Google Scholar 

  33. Maji, S., Vishnoi, N.K., Malik, J.: Biased normalized cuts. In: CVPR (2011)

    Google Scholar 

  34. Ng, A.Y., Jordan, M., Weiss, Y.: On spectral clustering: Analysis and an algorithm. In: NIPS (2001)

    Google Scholar 

  35. Ochs, P., Malik, J., Brox, T.: Segmentation of moving objects by long term video analysis. TPAMI 36, 1187–1200 (2013)

    Article  Google Scholar 

  36. Palou, G., Salembier, P.: Hierarchical video representation with trajectory binary partition tree. In: CVPR (2013)

    Google Scholar 

  37. Paris, S.: Edge-preserving smoothing and mean-shift segmentation of video streams. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 460–473. Springer, Heidelberg (2008)

    Chapter  Google Scholar 

  38. Rangapuram, S., Hein, M.: Constrained 1-spectral clustering. In: AISTATS (2012)

    Google Scholar 

  39. Shi, J., Malik, J.: Normalized cuts and image segmentation. TPAMI 22, 1–8 (2000)

    Article  MATH  Google Scholar 

  40. Sundaram, N., Keutzer, K.: Long term video segmentation through pixel level spectral clustering on gpus. In: ICCV Workshops (2011)

    Google Scholar 

  41. Sundberg, P., T.Brox, Maire, M., Arbelaez, P., Malik, J.: Occlusion boundary detection and figure/ground assignment from optical flow. In: CVPR (2011)

    Google Scholar 

  42. Taylor, C.: Towards fast and accurate segmentation. In: CVPR (2013)

    Google Scholar 

  43. Vazquez-Reina, A., Avidan, S., Pfister, H., Miller, E.: Multiple hypothesis video segmentation from superpixel flows. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 268–281. Springer, Heidelberg (2010)

    Chapter  Google Scholar 

  44. Wagstaff, K., Cardie, C., Rogers, S., Schrödl, S.: Constrained k-means clustering with background knowledge. In: ICML (2001)

    Google Scholar 

  45. Wang, X., Davidson, I.: Flexible constrained spectral clustering. In: KDD (2010)

    Google Scholar 

  46. Xu, C., Corso, J.J.: Evaluation of super-voxel methods for early video processing. In: CVPR (2012)

    Google Scholar 

  47. Xu, C., Xiong, C., Corso, J.J.: Streaming hierarchical video segmentation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part VI. LNCS, vol. 7577, pp. 626–639. Springer, Heidelberg (2012)

    Chapter  Google Scholar 

  48. Xu, L., Li, W., Schuurmans, D.: Fast normalized cut with linear constraints. In: CVPR (2009)

    Google Scholar 

  49. Yu, S.X., Shi, J.: Grouping with bias. In: NIPS (2001)

    Google Scholar 

Download references

Acknowledgments

The authors would like to thank Syama Sundar Rangapuram for his support on the use of the 1-spectral clustering code.

Author information

Authors and Affiliations

  1. Max Planck Institute for Informatics, Saarbrücken, Germany

    Anna Khoreva, Fabio Galasso & Bernt Schiele

  2. Saarland University, Saarbrücken, Germany

    Matthias Hein

Authors
  1. Anna Khoreva
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Fabio Galasso
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Matthias Hein
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Bernt Schiele
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Anna Khoreva .

Editor information

Editors and Affiliations

  1. Department of Mathematics and Computer Science, University of Münster, Münster, Germany

    Xiaoyi Jiang

  2. Computer Science Department 5, University of Erlangen-Nürnberg, Erlangen, Germany

    Joachim Hornegger

  3. Department of Computer Science, University of Kiel, Kiel, Germany

    Reinhard Koch

Rights and permissions

Reprints and permissions

Copyright information

© 2014 Springer International Publishing Switzerland

About this paper

Cite this paper

Khoreva, A., Galasso, F., Hein, M., Schiele, B. (2014). Learning Must-Link Constraints for Video Segmentation Based on Spectral Clustering. In: Jiang, X., Hornegger, J., Koch, R. (eds) Pattern Recognition. GCPR 2014. Lecture Notes in Computer Science(), vol 8753. Springer, Cham. https://doi.org/10.1007/978-3-319-11752-2_58

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-11752-2_58

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-11751-5

  • Online ISBN: 978-3-319-11752-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation