2D Structural Descriptions for Video Handling

  • H. Morikawa
  • H. Harashima
Conference paper
Part of the CG International Series book series (CGIS)


We describe an approach to obtain 2D structural descriptions — 2D shape, motion, spatial relation, and relative depth of each region — from image sequences, and demonstrate some of the unique manipulations possible upon real scenes using the derived 2D structural descriptions. To obtain such 2D structural descriptions, we present an analysis-by-synthesis-based incremental segmentation scheme which includes dynamic occlusion analysis to determine relative depth of several objects. We then present computer-graphics-style manipulations upon real scenes using the derived 2D structural descriptions, including video composition, focus simulation, and lightning variation, and suggest that the use of the 2D structural descriptions would open up many new creative and communicative possibilities.


Motion Estimation Segmentation Result Object Boundary Relative Depth Image Code 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Aizawa K, Harashima H, Saito T (1989) Model-based analysis synthesis image coding system for a person’s faee. Signal Processing: Image Communication, 1(2):139–152.CrossRefGoogle Scholar
  2. Born M, Wolf E (1970) Principles of Optics. Pergamon Press, Oxford, England.Google Scholar
  3. Brice CR, Fennema CL (1970) Scene analysis using regions. Artificial Intelligence, 1:205–226.CrossRefGoogle Scholar
  4. Diehl N (1991) Object-oriented motion estimation and segmentation in image sequences. Signal Processing: Image Communication, 3(1):23–56.MathSciNetCrossRefGoogle Scholar
  5. Duff T (1985) Compositing 3-D rendered images. Computer Graphics, 19(3):41–44.MathSciNetCrossRefGoogle Scholar
  6. Foley JD, van Dam A (1984) Fundamentals of Interactive Computer Graphics. Addison-Wesley, Reading, MA.Google Scholar
  7. Fu KS, Mu JK (1981) A survey on image segmentation. Pattern Recognition, 13(1):3–16.MathSciNetCrossRefGoogle Scholar
  8. Haralick RM, Shapiro LG (1985) Image segmentation techniques. Computer Vision, Graphics and Image Processing, 29:100–132.CrossRefGoogle Scholar
  9. Horn BKP (1986) Robot Vision. MIT Press, Cambridge, MAGoogle Scholar
  10. Hötter M, Thoma R (1988) Image segmentation based on object oriented mapping parameter estimation. Signal Processing, 15(3):315--334.CrossRefGoogle Scholar
  11. Kunt M, Konomopoulous A, Kocher M (1985) Second-generation image coding. Proc. of the IEEE, 73(4):549–574.CrossRefGoogle Scholar
  12. Lippman A (1991) Feature sets for interactive images. Comm. of the ACM, 34(4):92–102.CrossRefGoogle Scholar
  13. Morikawa H, Harashima H (1991a) 3D structure extraction coding of image sequences. Journal of Visual Communication and Image Representation, 2(4):332–344.CrossRefGoogle Scholar
  14. Morikawa H, Kondo E, Hararashima H (1991b) Structural description of moving pictures for coding. In Proc. Picture Coding Sympmium (PCs’91). 127, pp.369372, Tokyo, Japan.Google Scholar
  15. Morikawa H, Harashima H (1991c) Incremental segmentation of moving pictures with dynamic occlusion analysis. In Proc. Fhrst Korea Japan Joint Conference on Computer Vision, pp.374–381, Seoul, Korea.Google Scholar
  16. Musmann HG, Hötter M, Ostermann J (1989) Object-oriented analysis-synthesis coding of moving images. Signal Processing: Image Communication, 1(2):117–138.CrossRefGoogle Scholar
  17. Nakamae E, Harada K, Ishizaki T, Nishita T (1986) A montage method: The overlaying of the computer generated images onto a background photograph. Computer Graphics, 20(4):207–214.CrossRefGoogle Scholar
  18. Peleg S, Rom H (1990) Motion based segmentation. In Proc. Intemational Conf. on Pattem Recognition, pp.109–113, Atlantic City, N J.Google Scholar
  19. Porter T, Duff T (1984) Compositing digital images. Computer Graphics, 18(3):253–259.CrossRefGoogle Scholar
  20. Potmesil M, Charkravarty I (1981) A lens and aperture camera model for synthctic image generation. Computer Graphics. 15(3):297–305.CrossRefGoogle Scholar
  21. Potter JL (1977) Scene segmentation using motion information. Computer Graphics and Image Processing, 6:558–581.CrossRefGoogle Scholar
  22. Schachter BJ (1983) Computer Image Genemtion. John Wiley & Sons, New York.Google Scholar
  23. Shalkoff RJ, McVey ES (1982) A model and tracking algorithm for a class of video targets. IEEE Trans. Pattern Analysis and Machine Intelligence, 4(1):2–10.CrossRefGoogle Scholar
  24. Sommerfeld A (1964) Mechanics of Deformable Bodies. Academic Press, New York.Google Scholar
  25. Thompson WB (1980) Combining motion and contrast for segmentation. IEEE Trans. Pattem Analysis and Machine Intelligence, 2(6) :543–549.Google Scholar
  26. Thompson WB, Mutch KM, Berzins VA (1985) Dynamic occlusion analysis in optical flow fields. IEEE Trans. Pattern Analysis and Machine Intelligence, 7(4):374–383.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Tokyo 1992

Authors and Affiliations

  • H. Morikawa
    • 1
  • H. Harashima
    • 1
  1. 1.Department of Electrical EngineeringThe University of TokyoBunkyo-ku, Tokyo, 113Japan

Personalised recommendations