Abstract—This paper presents a control structure for a general-purpose image understanding system. It addresses the high level of uncertainty in local hypotheses and the computational complexity of image interpretation. The control of vision algorithms is done by an independent subsystem that uses Bayesian networks and utility theory to compute marginal value of information and selects the algorithm with the highest value of information. It is shown that the knowledge base can be acquired using learning techniques and the value-driven approach to the selection of vision algorithms leads to performance gains.
1. A.R. Hanson, and E.M. Riseman, "Visions: A Computer System for Interpreting Scenes," Computer Vision Systems, A.R. Hanson and E.M. Riseman, eds. Academic Press, 1978.
2. B.A. Draper, R. Collins, J. Broglio, A. Hanson, and E. Riseman, "The Schema System," Int'l J. Computer Vision, vol. 2, pp. 209-250, 1989.
3. R.A. Brooks, "Symbolic Reasoning among 3-D Models and 2-D Images," Artificial Intelligence, vol. 17, pp. 285-348, 1981.
4. D.M. McKeown, Jr.A.H. Wilson, and J. McDermott, "Rule-Based Interpretation of Aerial Imagery," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 7, pp. 570-585, 1985.
5. M. Herman, and T. Kanade, "Incremental Reconstruction of 3-D Scenes from Multiple Complex Images," Artificial Intelligence, vol. 30, pp. 289-341, 1986.
6. R. Rimey, and C. Brown, "Task-Oriented Vision with Multiple Bayes Nets," Active Vision, A. Blake and A. Yuille, eds. The MIT Press, 1992.
7. C.M. Brown, M. Marengoni, and G. Kardaras, "Bayes Nets for Selective Perception and Data Fusion," Proc. SPIE Image and Information Systems: Applications and Opportunities, 1994.
8. W.B. Mann, and T.O. Binford, "An Example of 3D Interpretation of Images Using Bayesian Networks," Proc. DARPA Image Understanding Workshop, pp. 793-801, 1992.
9. V.P. Kumar, and U.B. Desai, "Image Interpretation Using Bayesian Networks," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 1, pp. 74-77, Jan. 1996.
10. B.M. Krebs, M. Burkhardt, and B. Korn, "A Task Driven 3D Object Recognition System Using Bayesian Networks," Proc. Int'l Conf. Computer Vision, 1998.
11. B.A. Draper, A.R. Hanson, and E.M. Riseman, "Knowledge-Directed Vision: Control, Learning, and Integration," Proc. IEEE, vol. 84, no. 11, pp. 1625-1637, 1996.
12. D. Crevier, and R. Lepage, "Knowledge-Based Image Understanding Systems: A Survey," Computer Vision and Image Understanding, vol. 67,
no. 2, pp. 161-185, 1997.
13. R. Collins, Y. Cheng, C. Jaynes, F. Stolle, X. Wang, A. Hanson, and E. Riseman, "Site Model Acquisition and Extension from Aerial Images," Proc. Int'l Conf. Computer Vision, pp. 888-893, 1995.
14. C. Jaynes,, et al. "Three-Dimensional Grouping and Information Fusion for Site Modeling from Aerial Images," Proc. DARPA Image Understanding Workshop, pp. 479-490, 1996.
15. R. Collins, Y. Cheng, C. Jaynes, F. Stolle, X. Wang, A. Hanson, and E. Riseman, "The Ascender System: Automated Site Modelling from Multiple Aerial Images," Computer Vision and Image Understanding, 1998.
16. G.F. Cooper, "The Computational Complexity of Probabilistic Inference Using Bayesian Belief Networks," Artificial Intelligence, vol. 42, pp. 393-405, 1990.
17. C. Jaynes, M. Marengoni, A. Hanson, and E. Riseman, "3D Model Acquisition Using a Bayesian Controller," Proc. Int'l Symp. Eng. of Intelligent Systems, 1998.
18. S.K. Andersen, K.G. Olesen, F.V. Jensen, and F. Jensen, "HUGIN—A Shell for Building Bayesian Belief Universes for Expert Systems," Proc. 11th Int'l Congress on Uncertain Artificial Intelligence, pp. 1080-1085, 1989.
19. C. Jaynes, M. Marengoni, A. Hanson, and E. Riseman, "Intelligent Control for Automatic Model Acquisition from Aerial Images," Proc. IASTED Int'l Conf. Intelligent Systems and Control, pp. 30-35, 1998.
20. M. Marengoni, C. Jaynes, A. Hanson, and E. Riseman, "Ascender II, A Visual Framework for 3D Reconstruction," Proc. Int'l Conf. Vision Systems, 1999.
21. D.V. Lindley, Making Decisions, second ed. John Wiley and Sons, 1985.
22. R.A. Howard, and J.E. Matheson, "Influence Diagrams," Readings on the Principles and Applications of Decision Analysis, R.A. Howard and J.E. Matheson, eds. pp. 721-762, Menlo Park, Calif.: Strategic Decision Group, 1984.
23. F.V. Jensen, Bayesian Networks and Decision Graphs. Springer-Verlag, 2001.
24. E. Castillo, J.M. Gutierrez, and A.S. Hadi, Expert Systems and Probabilistic Network Models. Springer, 1997.
25. J. Cheng, D. Bell, and W. Liu, "An Algorithm for Bayesian Belief Network Construction from Data," Proc. AI & STAT, pp. 83-90, 1997.
26. N. Friedman, and M. Goldszmidt, "Learning Bayesian Networks with Local Structures," Proc. Conf. Uncertainty in Artificial Intelligence, pp. 252-262, 1996.
27. G.F. Cooper, and E. Herskovits, "A Bayesian Method for Constructing Bayesian Belief Networks from Databases," Proc. Conf. Uncertainty in Artificial Intelligence, pp. 86-94, 1991.
28. D. Heckerman, "A Tutorial on Learning with Bayesian Networks," Technical Report MSR-TR-95-06, Microsoft Research, Mar. 1995.
29. J. Cheng, D. Bell, and W. Liu, "Learning Bayesian Networks from Data: An Efficient Approach Based on Information
Theory," technical report, Dept. of Computer Science, Univ. of Alberta, 1998.