Abstract
This paper describes a modular and coherent approach to 3D object recognition. The basic theme behind the approach is constraint satisfaction networks, motivated by connectionist networks. The use of such networks allows fusion of evidence and a fundamental homogeneity of the entire recognition paradigm. Here evidence can be about fundamentally different geometric objects, such as curves and surfaces, or can be evidence obtained from different sensory modalities. We emphasize the former.
In particular, we discuss the problems that arise when dealing with large object databases and complex input scenery. We propose solutions that will keep the size of the networks from growing beyond control.
Preview
Unable to display preview. Download preview PDF.
Bibliography
A.V. Aho, J.E. Hoperoft, and J.D. Ullman, The Design and Analysis of Computer Algorithms. Reading, MA: Addison-Wesley Publishing Company, 1976
J. Aloimonos and A. Bandyopadhyay, “Active vision,” in Proc. First Int. Conf. on Comp. Vision, June 1987, pp. 35–55.
D.H. Ballard, “Parameter nets: A theory of low level vision,” in Proc. 7th Int. Joint Conf. on Artificial Intell., Aug. 1981, pp. 1068–1078.
D.H. Ballard and A. Ozcandarli, “Eye fixation and early vision: Kinetic depth,” in Proc. Second Int. Conf. on Comp. Vision, Dec. 1988, pp. 524–531.
P.J. Besl and R.C. Jain, “Three-dimensional object recognition,” Computing Surveys, Vol. 17, No. 1, March 1985, pp. 75–145.
T.O. Binford, “Survey of model-based image analysis systems,” The Int. Journal of Robotics Research, Vol. 1, No. 1, Spring 1982, pp. 18–64.
R.M. Bolle, R. Kjeldsen, and D. Sabbah, “Primitive shape extraction from range data,” in Proc. IEEE Workshop on Comp. Vision, Nov.-Dec. 1987, pp. 324–326.
R.M. Bolle, A. Califano, R. Kjeldsen, and R.W. Taylor, “Visual recognition using concurrent and layered parameter transforms,” in Proc. IEEE Conf. on Comp. Vision and Pattern Recognition, June 1989, pp. 625–631.
R.A. Brooks, “Model-based three-dimensional interpretations of two-dimensional images,” IEEE Trans. on Pattern Analysis and Machine Intell., Vol. 5, No. 2, March 1983, pp. 140–150.
A. Califano, “Feature recognition using correlated information contained in multiple neighborhoods,” in Proc. 7th Nat. Conf. on Artificial Intell., July 1988, pp. 831–836.
A. Califano, R.M. Bolle, and R.W. Taylor, “Generalized neighborhoods: A new approach to complex feature extraction,” in Proc. IEEE Conf. on Comp. Vision and Pattern Recognition, June 1989, pp. 192–199.
A. Califano, Multiple window parameter transform for image feature extraction, U.S. Patent application, 1989.
M.P. DoCarmo, Differential geometry of curves and surfaces. New Jersey: Prentice-Hall, 1976.
S.E. Fahlman and G.E. Hinton, “Connectionist architectures for artificial intelligence,” IEEE Computer, Jan. 1987, pp. 100–109.
J.A. Feldman and D.H. Ballard, “Connectionist models and their properties,” Cognitive Science, Vol. 6, 1981, pp. 205–254.
K.S. Fu, “Robot vision for machine part recognition,” Robotics and Sensing Systems, 441, Aug. 1983, pp. 2–14.
S. Grossberg, “Competitive learning: From interactive activation to adaptive resonance,” Cognitive Science, Vol. 11, 1987, pp. 23–63.
D.G. Hakala, R.C. Hillyard, P.F. Malraison, and B.F. Nource, “Natural quadrics in mechanical design,” in Proc. CAD/CAM VII, Nov. 1980, pp. 363–378.
P.V.C. Hough, Methods and means for recognizing complex patterns, U.S. Patent 3,069, 654, Dec. 1962.
K. Ikeuchi and K.S. Hong, “Determining linear shape change: Toward automatic generation of object recognition programs,” in Proc. IEEE Conf on Comp. Vision and Pattern Recognition, June 1989, pp. 450–457.
D.G. Lowe, “The viewpoint consistency constraint,” International Journal of Computer Vision, Vol. 1, No. 1, 1987, pp. 57–72.
J.J. Koenderink and A.J. van Doom, “Internal representation of solid shape with respect to vision,” Biological Cybernetics, Vol. 32, No. 4, 1979, pp. 211–216.
D. Marr, Vision. San Francisco, CA: Freeman and Company, 1982
R. Mohan and R. Nevatia, “Segmentation and description based on perceptual organization,” in Proc. IEEE Conf. on Comp. Vision and Pattern Recognition, June 1989, pp. 333–341.
A.M. Nazif and M.D. Levine, “Low level image segmentation: An expert system,” IEEE Trans. on Pattern Analysis and Machine Intell.Vol. 6, No. 5, Sept. 1984, pp. 555–577.
D.E. Rumelhart, G.E. Hinton, and R.J. Williams, “Learning internal representations by error propagation,” in J.L. McClelland, D.E Rumelhart, and PDP Research Group, Parallel distributed processing. Cambridge, MA: MIT Press, 1986.
D. Sabbah, “Computing with connections in visual recognition of origami objects,” Cognitive Science, Vol$19, No. 1, Jan.-March 1985, pp. 25–50.
D. Sabbah and R.M. Bolle, “Extraction of surface parameters from depth maps viewing planes and quadrics of revolution,” in Proc. SPIE Conf. Intell. Robots and Comp. Vision, Oct. 1986, pp. 222–232.
H.G. Schuster, Deterministic Chaos: An Introduction. FDR: Weinheim, 1988
T.J. Sejnowski and C.R. Rosenberg, NETtalk: A parallel network that learns to read aloud, Tech. Rep. No. JHU/EECS-86–01, Elec. Engin. and Comp. Science, Johns Hopkins University, 1986.
R. Shapira and H. Freeman, “Reconstruction of curved-surface bodies from a set of imperfect projections,” in Proc. 5th Int. Joint Conf on Artificial Intell., Aug. 1977, pp. 22–26.
Technical Arts Corporation, 100X 3D Scanner: User’s manual & application programming guide. Redmond, WA: 1986.
A.K.C. Wong, S.W. Lu, M. Rioux, “Recognition and shape synthesis of 3-D objects based on attributed hypergraphs,” IEEE Trans. on Pattern Analysis and Machine Intell., Vol. 11, No. 3, March 1989, pp. 279–290.
G.M. Zaslayskii, Chaos in Dynamical Systems. Chur, NY: Harwood Academic Publisher, 1985.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Califano, A., Bolle, R.M., Kjeldsen, R., Taylor, R.W. (1993). Evidence Fusion Using Constraint Satisfaction Networks. In: Aggarwal, J.K. (eds) Multisensor Fusion for Computer Vision. NATO ASI Series, vol 99. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-02957-2_14
Download citation
DOI: https://doi.org/10.1007/978-3-662-02957-2_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-08135-4
Online ISBN: 978-3-662-02957-2
eBook Packages: Springer Book Archive