Hierarchical depth mapping from multiple cameras

  • Jong-Il Park
  • Seiki Inoue
Session 7: Motion & Stereo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1310)


We present a method to estimate a dense and sharp depth map using multiple cameras. A key issue in obtaining sharp depth map is how to overcome the harmful influence of occlusion. Thus, we first propose an occlusion-overcoming strategy which selectively use the depth information from multiple cameras. With a simple sort and discard technique, we resolve the occlusion problem considerably at a slight sacrifice of noise tolerance. Another key issue in area-based stereo matching is the size of matching window. We propose a hierarchical scheme that attempts to acquire a sharp depth map such that edges of the depth map coincide with object boundaries on the one hand, reduce noisy estimates due to insufficient size of matching window on the other hand. We show the hierarchical method can produce a sharp and correct depth map.


Depth Information Stereo Match Correct Match Multiple Camera Hierarchical Scheme 
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. 1.
    S.D.Cochran and G.Medioni, “3-D surface description from binocular stereo,” IEEE Trans. PAMI, vo1.14, no.10, pp.981–994, Oct. 1992.Google Scholar
  2. 2.
    U.Dhond and J.Aggarwal, “Structure from stereo: A review,” IEEE Trans. System, Man, and Cybernetics, vol.19, no.6, pp.1489–1510, Nov./Dec. 1989.Google Scholar
  3. 3.
    W.E.L.Grimson, “A computer implementation of a theory of human stereo vision,” Phil. Trans. Royal Soc. London, vol.B292, pp.217–253, 1981.Google Scholar
  4. 4.
    M.J.Hannah, “Bootstrap stereo,” Proc. ARPA Image Understanding Workshop, pp.201–208, College Park, MD, Apr. 1980.Google Scholar
  5. 5.
    S.Inoue, “Mental image expression by media integration — COMICS,” Proc. of 1st International Workshop on New Video Media Technology, pp.47–52, Seoul, Korea, March 1996.Google Scholar
  6. 6.
    T.Kanade and M.Okutomi, “A stereo matching algorithm with an adaptive window: Theory and experiment,” IEEE Trans. PAMI, vol.16, no.9, pp.920–932, Sept. 1994.Google Scholar
  7. 7.
    T.Kanade et al., “Virtualized Reality: Concepts and early results,” Proc. IEEE Workshop on Representation of Visual Scenes, pp.69–76, June 1995.Google Scholar
  8. 8.
    T.Kanade et al., “A stereo machine for video-rate dense depth mapping and its new applications,” Proc. IEEE CVPR'96, pp.196–202, San Francisco, June 1996.Google Scholar
  9. 9.
    Y.Nakamura et al., “Occlusion detectable stereo — Occlusion patterns in camera matrix,” Proc. IEEE CVPR'96, pp.371–378, San Francisco, June 1996.Google Scholar
  10. 10.
    V.S.Nalwa, A Guided Tour of Computer Vision, Addison-Wesley, 1993.Google Scholar
  11. 11.
    Y.Ohta, “Computer vision as media technology,” Proc. Image Sensing Symposium, pp.265–270, 1996 (in Japanese).Google Scholar
  12. 12.
    M.Okutomi and T.Kanade, “A multiple-baseline stereo,” IEEE Trans. PAMI, vol.15, no.4, pp.353–363, April 1993.Google Scholar
  13. 13.
    J.Park et al., “Extraction of depth information for scene description and its application,” ITE'96, pp.112–113, Nagoya, Japan, July 1996 (in Japanese).Google Scholar
  14. 14.
    J.Park and S.Inoue, “Image expression based on disparity estimation from multiple cameras,” Proc. 3rd Joint Workshop on Multimedia Communications, 7-1, Taegu, Korea, Oct. 1996.Google Scholar
  15. 15.
    J.Park and S.Inoue, “Toward occlusion-free depth estimation for video production,” Proc. International Workshop on New Video Media Technology '97, 6-2, pp.131–136, Tokyo, Japan, Jan. 1996.Google Scholar
  16. 16.
    J.Park and S.Inoue, “New view generation from multi-view image sequence,” Technical Report of IEICE, Sapporo, Japan, Feb. 1997 (in Japanese).Google Scholar
  17. 17.
    M.Shibata et al., “Scene describing method for video production,” ITEJ Tech. Report, vol.16, no.10, pp.19–24, Jan. 1992 (in Japanese).Google Scholar
  18. 18.
    R.Tsai, “Multiframe image point matching and 3-D surface reconstruction,” IEEE Trans. PAMI, vol.5, no.2, pp.159–174, March 1983.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Jong-Il Park
    • 1
  • Seiki Inoue
    • 1
  1. 1.ATR Media Integration & Communications Research Labs.Soraku-gun, KyotoJapan

Personalised recommendations