Skip to main content
Book cover

International Joint Conference on Computer Vision, Imaging and Computer Graphics

VISIGRAPP 2016: Computer Vision, Imaging and Computer Graphics Theory and Applications pp 575–592Cite as

From Occlusion to Global Depth Order, a Monocular Approach

Part of the Communications in Computer and Information Science book series (CCIS,volume 693)

Abstract

Estimating 3D structure of the scene from a single image remains a challenging problem in computer vision. This paper proposes a novel approach to obtain a global depth order of objects by incorporating monocular perceptual cues such as T-junctions and object boundary convexity, which are local indicators of occlusions, together with physical cues, namely ground contact points. The proposed combination of these local cues complement each other and creates a more thorough partial depth order relationship. The different partial orders are then robustly aggregated using a Markov random chain approximation to obtain the most plausible global depth order. Experiments show that the proposed method excels in comparison to state of the art methods.

Keywords

  • Monocular depth
  • Ordinal depth
  • Depth layering
  • Occlusion reasoning
  • Convexity
  • T-junctions
  • Boundary ownership
  • 2.1D

This is a preview of subscription content, access via your institution.

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-319-64870-5_28
  • Chapter length: 18 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   89.00
Price excludes VAT (USA)
  • ISBN: 978-3-319-64870-5
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   119.99
Price excludes VAT (USA)
Learn about institutional subscriptions
Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.
Fig. 5.
Fig. 6.
Fig. 7.
Fig. 8.
Fig. 9.
Fig. 10.
Fig. 11.

References

  1. Matheron, G.: Modèle séquentiel de partition aléatoire. Technical report, CMM (1968)

    Google Scholar 

  2. Dwork, C., Kumar, R., Naor, M., Sivakumar, D.: Rank aggregation methods for the web. In: Proceedings of the 10th International Conference on World Wide Web, pp. 613–622. ACM (2001)

    Google Scholar 

  3. Basha, T., Moses, Y., Avidan, S.: Photo sequencing. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 654–667. Springer, Heidelberg (2012). doi:10.1007/978-3-642-33783-3_47

    CrossRef  Google Scholar 

  4. Guzmán, A.: Decomposition of a visual scene into three-dimensional bodies. In: Proceeding AFIPS 1968 (Fall, part I) (1968)

    Google Scholar 

  5. Malik, J.: Interpreting line drawings of curved objects. Int. J. Comput. Vis. 1(1), 73–103 (1987)

    CrossRef  Google Scholar 

  6. Rubin, N.: Figure and ground in the brain. Nat. Neurosci. 4, 857–858 (2001)

    CrossRef  Google Scholar 

  7. Kanizsa, G.: Organization in Vision: Essays on Gestalt Perception. Praeger, New York (1979)

    Google Scholar 

  8. Marr, D.: Vision: A Computational Approach. Freeman & Co., San Francisco (1982)

    Google Scholar 

  9. Nitzberg, M., Mumford, D.: The 2.1-D sketch. In: Proceedings of Third International Conference on Computer Vision, pp. 138–144. IEEE (1990)

    Google Scholar 

  10. Nitzberg, M., Mumford, D., Shiota, T.: Filtering, Segmentation and Depth. LNCS, vol. 662. Springer, Heidelberg (1993)

    CrossRef  MATH  Google Scholar 

  11. Gao, R.-X., Wu, T.-F., Zhu, S.-C., Sang, N.: Bayesian inference for layer representation with mixed markov random field. In: Yuille, A.L., Zhu, S.-C., Cremers, D., Wang, Y. (eds.) EMMCVPR 2007. LNCS, vol. 4679, pp. 213–224. Springer, Heidelberg (2007). doi:10.1007/978-3-540-74198-5_17

    CrossRef  Google Scholar 

  12. Palou, G., Salembier, P.: Occlusion-based depth ordering on monocular images with binary partition tree. In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1093–1096. IEEE (2011)

    Google Scholar 

  13. Esedoglu, S., March, R.: Segmentation with depth but without detecting junctions. J. Math. Imaging Vis. 18, 7–15 (2003)

    CrossRef  MathSciNet  MATH  Google Scholar 

  14. Pao, H., Geiger, D., Rubin, N.: Measuring convexity for figure/ground separation. In: 1999 The Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 2, pp. 948–955. IEEE (1999)

    Google Scholar 

  15. Dimiccoli, M., Morel, J.M., Salembier, P.: Monocular depth by nonlinear diffusion. In: Sixth Indian Conference on Computer Vision, Graphics & Image Processing, ICVGIP 2008, pp. 95–102. IEEE (2008)

    Google Scholar 

  16. Calderero, F., Caselles, V.: Recovering relative depth from low-level features without explicit t-junction detection and interpretation. Int. J. Comput. Vis. 104, 38–68 (2013)

    CrossRef  MathSciNet  MATH  Google Scholar 

  17. Palou, G., Salembier, P.: Monocular depth ordering using t-junctions and convexity occlusion cues. IEEE Trans. Image Process. 22, 1926–1939 (2013)

    CrossRef  MathSciNet  Google Scholar 

  18. Burge, J., Fowlkes, C., Banks, M.: Natural-scene statistics predict how the figure-ground cue of convexity affects human depth perception. J. Neurosci. 30, 7269–7280 (2010)

    CrossRef  Google Scholar 

  19. Dimiccoli, M., Salembier, P.: Hierarchical region-based representation for segmentation and filtering with depth in single images. In: 2009 16th IEEE International Conference on Image Processing (ICIP), pp. 3533–3536 (2009)

    Google Scholar 

  20. Zeng, Q., Chen, W., Wang, H., Tu, C., Cohen-Or, D., Lischinski, D., Chen, B.: Hallucinating stereoscopy from a single image. In: Computer Graphics Forum, vol. 34, pp. 1–12. Wiley Online Library (2015)

    Google Scholar 

  21. Jia, Z., Gallagher, A., Chang, Y., Chen, T.: A learning-based framework for depth ordering. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 294–301. IEEE (2012)

    Google Scholar 

  22. McDermott, J.: Psychophysics with junctions in real images. Perception 33, 1101–1127 (2004)

    CrossRef  Google Scholar 

  23. Caselles, V., Coll, B., Morel, J.: Topographic maps and local contrast changes in natural images. Int. J. Comput. Vis. 33, 5–27 (1999)

    CrossRef  Google Scholar 

  24. Serra, J.: Introduction to mathematical morphology. Comput. Vis. Graph. Image Process. 35(3), 283–305 (1986)

    CrossRef  MATH  Google Scholar 

  25. Dimiccoli, M., Salembier, P.: Exploiting t-junctions for depth segregation in single images. In: Acoustics, Speech and Signal Processing, pp. 1229–1232 (2009)

    Google Scholar 

  26. Santner, J., Pock, T., Bischof, H.: Interactive multi-label segmentation. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010. LNCS, vol. 6492, pp. 397–410. Springer, Heidelberg (2011). doi:10.1007/978-3-642-19315-6_31

    CrossRef  Google Scholar 

  27. Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proceedings of 8th International Conference on Computer Vision, vol. 2, pp. 416–423 (2001)

    Google Scholar 

Download references

Acknowledgements

The authors acknowledge partial support by the MINECO/FEDER project with reference TIN2015-70410-C2-1-R, the MICINN project with reference MTM2012-30772, and by GRC reference 2014 SGR 1301, Generalitat de Catalunya.

Author information

Authors and Affiliations

  1. Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain

    Babak Rezaeirowshan, Coloma Ballester & Gloria Haro

Authors
  1. Babak Rezaeirowshan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Coloma Ballester
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Gloria Haro
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Gloria Haro .

Editor information

Editors and Affiliations

  1. Escola Superior de Tecnologia do IPS, Setúbal, Portugal

    José Braz

  2. MiraLab, University of Geneva, Carouge, Switzerland

    Nadia Magnenat-Thalmann

  3. LISA - ISTIA, University of Angers, Angers, France

    Paul Richard

  4. Department of Computer Science and Electrical Engineering, Jacobs University, Bremen, Germany

    Lars Linsen

  5. University of Groningen, Groningen, The Netherlands

    Alexandru Telea

  6. Università di Catania, Catania, Italy

    Sebastiano Battiato

  7. Research Innovation Center, Canon U.S.A. Inc., San Jose, California, USA

    Francisco Imai

Rights and permissions

Reprints and Permissions

Copyright information

© 2017 Springer International Publishing AG

About this paper

Cite this paper

Rezaeirowshan, B., Ballester, C., Haro, G. (2017). From Occlusion to Global Depth Order, a Monocular Approach. In: , et al. Computer Vision, Imaging and Computer Graphics Theory and Applications. VISIGRAPP 2016. Communications in Computer and Information Science, vol 693. Springer, Cham. https://doi.org/10.1007/978-3-319-64870-5_28

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-64870-5_28

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-64869-9

  • Online ISBN: 978-3-319-64870-5

  • eBook Packages: Computer ScienceComputer Science (R0)