Academia.eduAcademia.edu

Outline

From Occlusion to Global Depth Order, a Monocular Approach

2017, Springer eBooks

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

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.

References (27)

  1. T. Basha, Y. Moses, and S. Avidan. Photo sequencing. In Computer Vision-ECCV 2012, pages 654-667. Springer, 2012.
  2. J. Burge, C.C. Fowlkes, and M.S. Banks. Natural-scene statistics predict how the figure-ground cue of convexity affects human depth perception. The Journal of Neuroscience, 30(21):7269-7280, 2010.
  3. F. Calderero and V. Caselles. Recovering Relative Depth from Low-Level Features Without Explicit T-junction Detection and Interpretation. International Journal of Computer Vision, 104:38-68, 2013.
  4. V. Caselles, B. Coll, and J.M. Morel. Topographic maps and local contrast changes in natural images. International Journal of Computer Vision, 33(1):5-27, 1999.
  5. M. Dimiccoli, J-M Morel, and P. Salembier. Monocular depth by nonlinear diffu- sion. In Computer Vision, Graphics & Image Processing, 2008. ICVGIP'08. Sixth Indian Conference on, pages 95-102. IEEE, 2008.
  6. M. Dimiccoli and P. Salembier. Exploiting t-junctions for depth segregation in single images. Acoustics, Speech and Signal . . . , pages 1229-1232, 2009.
  7. M. Dimiccoli and P. Salembier. Hierarchical region-based representation for seg- mentation and filtering with depth in single images. Image Processing (ICIP), 2009 16th, 1:3533-3536, 2009.
  8. C. Dwork, R. Kumar, M. Naor, and D. Sivakumar. Rank aggregation methods for the web. In Proceedings of the 10th international conference on World Wide Web, pages 613-622. ACM, 2001.
  9. S. Esedoglu and R. March. Segmentation with depth but without detecting junc- tions. Journal of Mathematical Imaging and Vision, 18(1):7-15, 2003.
  10. R. Gao, T. Wu, S. Zhu, and N. Sang. Bayesian inference for layer representation with mixed markov random field. Energy Minimization Methods in Computer Vision and Pattern Recognition, 4679:213-224, 2007.
  11. A Guzmán. Decomposition of a visual scene into three-dimensional bodies. Pro- ceeding AFIPS '68 (Fall, part I), 1968.
  12. Z. Jia, A. Gallagher, Y.J. Chang, and T. Chen. A learning-based framework for depth ordering. In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pages 294-301. IEEE, 2012.
  13. G. Kanizsa. Organization in vision: essays on Gestalt perception. NY, Praeger, 1979.
  14. J. Malik. Interpreting line drawings of curved objects. International Journal of Computer Vision, 73403, 1987.
  15. D. Marr. Vision: A computational approach. San Francisco: Free-man & Co, 1982.
  16. D. Martin, C. Fowlkes, D. Tal, and J. Malik. A database of human segmented natu- ral images and its application to evaluating segmentation algorithms and measuring ecological statistics. In Proc. 8th Int'l Conf. Computer Vision, volume 2, pages 416-423, July 2001.
  17. G. Matheron. Modèle séquentiel de partition aléatoire. Technical report, CMM, 1968.
  18. J. McDermott. Psychophysics with junctions in real images. Perception, 33(9):1101-1127, 2004.
  19. M. Nitzberg, D. Mumford, and T. Shiota. Filtering, segmentation, and depth, volume 662. Lecture notes in computer science, Springer, 1993.
  20. M. Nitzberg and D.B. Mumford. The 2.1-d sketch. In Computer Vision, 1990. Proceedings, Third International Conference on, pages 138-144. IEEE, 1990.
  21. G. Palou and P. Salembier. Occlusion-based depth ordering on monocular images with binary partition tree. In Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on, pages 1093-1096. IEEE, 2011.
  22. G. Palou and P. Salembier. Monocular depth ordering using t-junctions and con- vexity occlusion cues. IEEE Transactions on Image Processing, 22(5):1926-1939, 2013.
  23. H.K. Pao, D. Geiger, and N. Rubin. Measuring convexity for figure/ground sepa- ration. In Computer Vision, 1999. The Proceedings of the Seventh IEEE Interna- tional Conference on, volume 2, pages 948-955. IEEE, 1999.
  24. N. Rubin. Figure and ground in the brain. Nature Neuroscience, 4:857-858, 2001.
  25. Jakob Santner, Thomas Pock, and Horst Bischof. Interactive multi-label segmenta- tion. In Proceedings 10th Asian Conference on Computer Vision (ACCV), Queen- stown, New Zealand, November 2010.
  26. J. Serra. Introduction to mathematical morphology, volume 35(3). Elsevier, 1986.
  27. Qiong Zeng, Wenzheng Chen, Huan Wang, Changhe Tu, Daniel Cohen-Or, Dani Lischinski, and Baoquan Chen. Hallucinating stereoscopy from a single image. In Computer Graphics Forum, volume 34, pages 1-12. Wiley Online Library, 2015.