Journal of Systems Integration

, Volume 4, Issue 2, pp 107–125 | Cite as

The design and implementation of a distributed image understanding system

  • Shu-Yuen Hwang
  • Tsan-Pin Wang


Computer vision is concerned with extracting information about a scene by analyzing images of that scene. Performing any computer vision task requires an enormous amount of computation. Exploiting parallelism appears to be a promising way to improve the performance of computer vision systems. Past work in this area has focused on applying parallel processing techniques to image-operator level parallelism. In this article, we discuss the parallelism of computer vision in the control level and present a distributed image understanding system (DIUS).

In DIUS, control-level parallelism is exploited by a dynamic scheduler. Furthermore, two levels of rules are used in the control mechanism. Meta-rules are concerned mainly with which strategy should be driven and the execution sequence of the system; control rules determine which task needs to be done next. A prototype system has been implemented within a parallel programming environment, Strand, which provides various virtual architectures mapping to either a shared-memory machine, Sequent, or to the Sun network.

Key Words

Computer vision image understanding systems distributed systems 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    D.H. Ballard and C.M. Brown,Compuer Vision. Prentice Hall Press: Englewood Cliffs, NJ, 1982.Google Scholar
  2. 2.
    H.G. Barrow and J.M. Tenenbaum, “Computational vision,”Proceedings of the IEEE, vol. 69, no. 5, pp. 572–595, May 1981.Google Scholar
  3. 3.
    P.J. Besl and R.C. Jain, “Three-dimensional object recognition,”ACM Computing Survey, vol. 17, no. 1, pp. 75–145, March 1985.Google Scholar
  4. 4.
    T.O. Binford, “Survey of model-based image analysis systems,”International Journal of Robotics Research, vol. 1, no. 1, pp. 587–633, Spring 1982.Google Scholar
  5. 5.
    R.A. Brooks, “Symbolic reasoning among 3-D models and 2-D images,” inComputer Vision, M. Brady, (ed.), North-Holland: Amsterdam, The Netherlands, 1981.Google Scholar
  6. 6.
    J.F. Canny, “A computational approach to edge detection,”IEEE Transactions on PAMI, vol. PAMI-8, no. 6, pp. 679–698, 1986.Google Scholar
  7. 7.
    V. Chaudhary and J.K. Aggarwal, “Parallelism in computer vision: A review,” inParallel Algorithms for Machine Intelligence and Vision, V. Kumar et al., (eds.), Springer-Verlag: New York, NY, 1990.Google Scholar
  8. 8.
    R.T. Chin and C.R. Dyer, “Model-based recognition in robot vision,”ACM Computing Survey, vol. 18, no. 1, pp. 67–108, March 1986.Google Scholar
  9. 9.
    A. Choudhary and S. Ranka, “Parallel processing for computer vision and image understanding,”IEEE Computer, vol. 25, no. 2, pp. 7–9, February 1992.Google Scholar
  10. 10.
    R. Engelmore and T. Morgan,Blackboord Systems. Addison-Wesley Publishing Company: Wokingham, England, 1988.Google Scholar
  11. 11.
    J.A. Feldman, “Connectionist models and parallelism in high level vision,”Computer vision, Graphics, and Image Processing, vol. 31, no. 2, pp. 178–200, 1985.Google Scholar
  12. 12.
    I. Foster and S. Taylor,Strand; New Concepts in Parallel Programming, Prentice Hall: Englewood Cliffs, NJ, 1990.Google Scholar
  13. 13.
    G.R. Grape,Model Based (Intermediate-Level) Computer Vision. Technical Report STAN-CS-73-366, Department of Computer Science, Stanford, University, 1973.Google Scholar
  14. 14.
    A.R. Hanson and E.M. Riseman,Computer Vision Systems. Academic Press: New York, NY, 1978.Google Scholar
  15. 15.
    A. Hanson and E. Riseman, “The VISIONS image-understanding system,” inAdvances in Computer Vision, vol. 1, C. brown, (ed.), Lawrence Erlbaum Associates Publishing: Hillsdale, NJ, 1988.Google Scholar
  16. 16.
    M.H. Hassan,An AI Approach for Object Recognition. Ph. D. Dissertation, Department of Computer Science, Wayne State University, 1988.Google Scholar
  17. 17.
    W. Harvey, D. Kalp, M. Tambe and D. Mckeown, “The effectiveness of task-level parallelism for production systems,”Journal of Parallel and Distributed Computing, vol. 13, no. 4, pp. 395–411, 1911.Google Scholar
  18. 18.
    S.Y. Hwang, “State-space search for high-level control of machine vision,”Optical Engineering, vol. 31, no. 6, pp. 1264–1276, June, 1992.Google Scholar
  19. 19.
    S.Y. Hwang and S.L. Tanimoto, “Parallel coordination of image operators: model, algorithm, and performance,”Image and Vision Computing, vol. 11, no. 3, pp. 129–138, April 1993.Google Scholar
  20. 20.
    L.H. Jamieson et al., “A software environment for parallel computer vision,”IEEE Computer, vol. 25, no. 2, pp. 73–77, February 1992.Google Scholar
  21. 21.
    R. Krishnapuram, “A belief maintenance scheme for hierarchical knowledge-based image analysis systems,”International Journal of Intelligent Systems, vol. 6, pp. 699–715, 1991.Google Scholar
  22. 22.
    M. Minsky, “A framework for representing knowledge,” inPsychology of Computer Vision, P. H. Winsont, (ed.), MIT Press: Cambridge, MA, 1975.Google Scholar
  23. 23.
    D.M. MeKeown, W.A. Harvey, and L.E. Wilson, “Automating knowledge acquisition for aerial image interpretation,”Computer Vision, Graphics, and Image Processing, vol. 46, no. 1, pp. 37–81, 1989.Google Scholar
  24. 24.
    D. McKeown, W.A. Harvey, and J. McDermott, “Rule-based interpretation of aerial imagery,”IEEE Transactions on PAMI, vol. PAMI-7, no. 5, pp. 570–585, 1985.Google Scholar
  25. 25.
    A.M. Nazif and M.D. Levine, “Low level image segmentation: an expert system,”IEEE Transactions on PAMI, vol. PAMI-6, no. 5, pp. 555–577, September 1984.Google Scholar
  26. 26.
    A. Osterhaug,Guide to Parallel Programming: on Sequent Computer Systems. Prentice Hall: Englewood Cliffs, NJ, 1989.Google Scholar
  27. 27.
    A. Resenfeld, “Computer vision: basic principles,”Proceedings of IEEE, vol. 77, no. 8, pp. 863–868, August 1988.Google Scholar
  28. 28.
    P.L. Rosin and T. Ellis, “Frame-based system for image interpretation,”Image and Vision Computing, vol. 9, no. 6, pp. 353–361, December 1991.Google Scholar
  29. 29.
    S. Rubin, “The ARGOS Image Understanding System.” Ph. D. Dissertation, Department of Computer Science, Carnegie-Mellon University, 1978.Google Scholar
  30. 30.
    Y. Shirai,Three Dimensional Computer Vision. Springer-Verlag: Berlin, 1987.Google Scholar
  31. 31.
    M.O. Shneier, R. Lumia, and E.W. Kent, “Model-based strategies for high-level robot vision,”Computer Vision, Graphics, and Image Processing, vol. 33, no. 3, pp. 293–306, 1986.Google Scholar
  32. 32.
    C.C. Weems, E.M. Riseman and A.R. Hanson, “Image understanding architecture: exploiting potential parallelism in machine vision,”IEEE Computer, vol. 25, no. 2, pp. 65–68, February 1992.Google Scholar
  33. 33.
    T.E. Weymouth and A.A. Amini, “visual perception using a blackboard architecture,” inImage Analysis Applications. R. Kasturi and M.M. Trivedi, (eds.), Marcel Dekker Inc.: New York, NY, 1990.Google Scholar

Copyright information

© Kluwer Academic Publishers 1994

Authors and Affiliations

  • Shu-Yuen Hwang
    • 1
  • Tsan-Pin Wang
    • 1
  1. 1.Department of Computer Science and Information EngineeringNational Chiao Tung UniversityHsinchuTaiwan ROC

Personalised recommendations