Skip to main content

On binocularly viewed occlusion junctions

Part of the Lecture Notes in Computer Science book series (LNCS,volume 1064)


Under binocular viewing of a scene, there are inevitably regions seen only in one eye or camera. Normally, this is a source of trouble for stereopsis algorithms which must deal with these regions on non-correspondence. This paper points out that in fact half-occlusion can be a source of valuable information. This is done by deriving a formula relating the displacement of an occlusion junction in the two eyes' images and the depth difference between the scene edges that comprise the occlusion junction. This paper represents the first quantitative result on the cue of half-occlusion in stereopsis.


  • Illusory Contour
  • Subjective Contour
  • Epipolar Line
  • Binocular Viewing
  • Frontoparallel Plane

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.


  1. B.L. Anderson. The role of partial occlusion in stereopsis. Nature, 367:365–368, 1994.

    Google Scholar 

  2. B.L. Anderson and B. Julesz. A Theoretical Analysis of Illusory Contour Formation in Stereopsis. Psych Review, 1995 (in press).

    Google Scholar 

  3. B.L. Anderson and K. Nakayama. Toward a general theory of stereopsis: Binocular matching, occluding contours, and fusion. Psych Review, 101, pp. 414–445, 1994

    Google Scholar 

  4. P.N. Belhumeur and D. Mumford. A Bayesian treatment of the stereo correspondence problem using half-occluded regions. Proc. of IEEE CVPR, Urbana,IL, June 1992.

    Google Scholar 

  5. R. Cipolla and A. Blake. Surface shape from the deformation of apparent contours. Int. Journ. of Computer Vision, 9(2): 83–112, 1992.

    Google Scholar 

  6. M.B. Clowes, “On seeing things,” Artificial Intelligence 2, pp. 79–116, 1971.

    Google Scholar 

  7. A. Guzman, “Computer Recognition of three-dimensional objects in a scene,” MIT Tech. Rept. MAC-TR-59, 1968.

    Google Scholar 

  8. D.A. Huffman, “Impossible objects as nonsense sentences,” Machine Intelligence 6, pp. 295–323, 1971.

    Google Scholar 

  9. D.G. Jones and J. Malik. Computational framework for determining stereo correspondence from a set of linear spatial filters. Image and Vision Computing, 10: 699–708, 1992.

    Google Scholar 

  10. R.B. Lawson and W.L. Gulick. Stereopsis and Anomalous Contour. Vision Research, 7: 271–297.

    Google Scholar 

  11. J. Malik. Interpreting Line Drawings of Curved Objects. Int. Journ. of Computer Vision, 1(1): 73–103, 1987.

    Google Scholar 

  12. G. Mitchison. Planarity and segmentation in stereoscopic matching. Perception, 17:753–782, 1988.

    Google Scholar 

  13. K. Nakayama and S. Shimojo. DaVinci Stereopsis: Depth and subjective occluding contours from unpaired image points. Vision Research, 30(11): 1811–1825, 1990.

    Google Scholar 

Download references

Author information

Authors and Affiliations


Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 1996 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Malik, J. (1996). On binocularly viewed occlusion junctions. In: Buxton, B., Cipolla, R. (eds) Computer Vision — ECCV '96. ECCV 1996. Lecture Notes in Computer Science, vol 1064. Springer, Berlin, Heidelberg.

Download citation

  • DOI:

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-61122-6

  • Online ISBN: 978-3-540-49949-7

  • eBook Packages: Springer Book Archive