Advertisement

Where to look next using a Bayes net: Incorporating geometric relations

  • Raymond D. Rimey
  • Christopher M. Brown
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 588)

Abstract

A task-oriented system is one that performs the minimum effort necessary to solve a specified task. Depending on the task, the system decides which information to gather, which operators to use at which resolution, and where to apply them. We have been developing the basic framework of a task-oriented computer vision system, called TEA, that uses Bayes nets and a maximum expected utility decision rule. In this paper we present a method for incorporating geometric relations into a Bayes net, and then show how relational knowledge and evidence enables a task-oriented system to restrict visual processing to particular areas of a scene by making camera movements and by only processing a portion of the data in an image.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    J. M. Agosta. The structure of Bayes networks for visual recognition. In Uncertainty in AI, pages 397–405. North-Holland, 1990.Google Scholar
  2. 2.
    E. Charniak. Bayesian networks without tears. AI Magazine, 12(4):50–63, Winter 1991.Google Scholar
  3. 3.
    T. Dean, T. Camus, and J. Kirman. Sequential decision making for active perception. In Proceedings: DARPA Image Understanding Workshop, pages 889–894, 1990.Google Scholar
  4. 4.
    T. L. Dean and M. P. Wellman. Planning and Control. Morgan Kaufmann, 1991.Google Scholar
  5. 5.
    M. Henrion, J. S. Breese, and E. J. Horvitz. Decision analysis and expert systems. AI Magazine, 12(4):64–91, Winter 1991.Google Scholar
  6. 6.
    T. Levitt, T. Binford, G. Ettinger, and P. Gelband. Probability-based control for computer vision. In Proceedings: DARPA Image Understanding Workshop, pages 355–369, 1989.Google Scholar
  7. 7.
    J. Pearl. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufman, 1988.Google Scholar
  8. 8.
    R. D. Rimey. Where to look next using a Bayes net: An overview. In Proceedings: DARPA Image Understanding Workshop, 1992.Google Scholar
  9. 9.
    R. D. Rimey and C. M. Brown. Task-oriented vision with multiple Bayes nets. Technical Report 398, Department of Computer Science, University of Rochester, November 1991.Google Scholar
  10. 10.
    R. D. Rimey and C. M. Brown. Task-oriented vision with multiple Bayes nets. In A. Blake and A. Yuille, editors, Active Vision. MIT Press, 1992. Forthcoming.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • Raymond D. Rimey
    • 1
  • Christopher M. Brown
    • 1
  1. 1.Computer Science DepartmentThe University of RochesterRochesterUSA

Personalised recommendations