The general principles of geometric reasoning for computer vision are discussed and some previous attempts at imple menting reasoners reviewed. A new implementation is pro posed that involves interval arithmetic to cope with uncer tainties and has a network structure that promotes efficiency from parallelism and accuracy from feedback. Typical con straints from a 3D model/3D image vision system are dis cussed and used to evaluate the network performance.
Get full access to this article
View all access options for this article.
References
1.
Alefeld, G., and Herzberger, J.1983. Introduction to Interval Computations. London: Academic Press.
2.
Ayache, N., and Faugeras, O.D.1988. Building, registering and fusing noisy visual maps . Int. J. Robot. Res.7(6):45-65.
3.
Ballard, D.H., and Tanaka, H.1985. Transformational form perception in 3D: Constraints, algorithms and implementation. Proc. 9th Int. Joint Conf. on Artificial Intelligence . Los Angeles: Morgan Kaufmann , pp. 964-968.
4.
Bledsoe, W.W., 1974. The sup-inf method in Presburger arithmetic. Memo ATP 18, Dept. of Math and Comp. Science, Univ. of Texas at Austin .
5.
Brooks, R.A.1981. Symbolic reasoning among 3-D models and 2-D images . Artificial Intell.17(1):285-349.
6.
Davis, E.1987. Constraint propagation with interval labels. Artificial Intell.32(3):281-331.
7.
Durrant-Whyte, H.F.1988a. Sensor models and multi-sensor integration. Int. J. Robot. Res.7(6):97-113.
8.
Durrant-Whyte, H.F.1988b. Uncertain geometry in robotics. IEEE J. Robot. Automat.4(1):23-31.
9.
Faugeras, O.D., and Hebert, H.1983. A 3-D recognition and positioning algorithm using geometrical matching between primitive surfaces. Proc. 8th Int. Joint Conf. on Artificial Intelligence. Karlsruhe: Morgan Kaufmann, pp. 996-1002.
10.
Fisher, R.B.1986. SMS—a suggestive modeling system for object recognition . Image Vision Comp.5(2):98-104.
11.
Fisher, R.B.1989. From surfaces to objects: Computer vision and three dimensional scene analysis. Chichester, Great Britain: John Wiley.
12.
Fisher, R.B., and Orr, M.J.L.1988. Solving geometric constraints in a parallel network . Image Vision Comp.6(2):100-106.
13.
Fisher, R.B., and Orr, M.J.L.1989. Experiments with a network-based geometric reasoning engine. Proc. 11th Int. Joint Conf. on Artificial Intelligence. Detroit: Morgan Kaufmann, pp. 1623-1628.
14.
Fleming, A.D.1988. Analyses of uncertainties and geometric tolerances in assemblies of parts. Ph.D. dissertation. Department of Artificial Intelligence, University of Edinburgh .
15.
Hinton, G.E., and Lang, K.1985. Shape recognition and illusory conjunctions. Proc. 9th Int. Joint Conf. on Artificial Intelligence. Los Angeles : Morgan Kaufmann, pp. 252-259.
16.
Orr, M.J.L., and Fisher, R.B.1987. Geometric reasoning for computer vision. Image Vision Comp.5(3):233-238.
17.
Popplestone, R.J., Ambler, A.P., and Bellos, I.M.1980. An interpreter for a language describing assemblies . Artificial Intell.14(1):79-107.
18.
Porrill, J.1988. Optimal combination and constraints for geometrical sensor data. Int. J. Robot. Res.7(6):66-77.
19.
Shostak, R.E.1977. On the sup-inf method for proving Presburger formulas . J. Assoc. Comp. Mach.24, pp. 529-543.
