Matching and Clustering: Two Steps Toward Automatic Object Modeling in Computer Vision

Abstract

In this article, we present a general frame for a system of au tomatic modeling and recognition of 3D polyhedral objects. Such a system has many applications for robotics: e.g., recog nition, localization, and grasping. Here we focus on one main aspect of the system: when many images of one 3D object are taken from different unknown viewpoints, how to recognize those that represent the same aspect of the object? Briefly, is it possible to determine automatically if two images are similar or not? The two stages detailed in the article are the matching of two images and the clustering of a set of images. Matching consists of finding the common features of two images while no information is known about the image contents, the motion, or the calibration of the camera. Clustering consists of regrouping into sets the images representing a same aspect of the modeled objects. For both stages, experimental results on real images are shown.

Get full access to this article

View all access options for this article.

References

Arbogast, E. , and Mohr, R. 1991. 3D structures inference from images sequences. Int. J. Pattern Recognition Artificial Intell. 5(5):749.

Anandan, P. 1989. A computational framework and an algorithm for the measurement of visual motion. Int. J. Computer Vision 2:283-310.

Besl, P.J. 1988. Active Optical Range Imaging Sensors. New York: Springer-Verlag.

Bhanu, B. 1987 (August). CAD-Based Robot Vision. Computer (Special Issue on CAD-Based Robot Vision), 20(8):13-16.

Bowyer, K. 1991. Why aspect graphs are not (yet) practical for computer vision. In Proceedings of the IEEE workshop on Direction on automated CAD-based Vision, Maui, Hawaii, pp. 97-104.

Connell, J.H. , and Brady, M. 1987. Generating and generalizing models of visual objects . Artificial Intell. 31:159-183.

Crowley, J.L. , and Stelmazyk, P. 1990. Measurement and integration of 3D structures by tracking edges lines. In Faugeras, O. (ed.): Proceedings of the 1st European Conference on Computer Vision . New York: Springer-Verlag , pp. 269-280.

Deriche, R. , and Faugeras, O. 1990. Tracking line segments. In Proceedings of the 1st European Conference on Computer Vision. New York: Springer-Verlag, pp. 259-267.

Flynn, P.J. , and Jain, A.K. 1991. CAD-based computer vision: From CAD models to relational graphs. IEEE Trans. PAMI 13(2):114-132.

10.

Fua, P. 1993. A parallel stereo algorithm that produces dense depth maps and preserves image features. Machine Vision Applications , 6(1):35-49.

11.

Gros, P. , and Mohr, R. 1992 (August). Automatic object modelization in computer vision . In Bunke, H. (ed.): Proceedings of the Workshop "Advances in Structural and Syntactic Pattern Recognition ." Series on Machine Perception and Artificial Intelligence , Vol. 5. World Scientific, Singapore, pp. 385-400.

12.

Gros, P. , and Quan, L. 1992 (December). Projective invariants for vision. Technical report RT 90 IMAG-15 LIFIA, LIFIA-IRIMAG, Grenoble, France.

13.

Hérault. L. , Horaud, R. , Veillon, F. , and Niez, J.J. 1990 (September). Symbolic image matching by simulated annealing . In Proceedings of the British Machine Vision Conference, Oxford, England, pp. 319-324.

14.

Horaud, R. , Skordas, T. , and Veillon, F. 1990 (April). Finding geometric and relational structures in an image. In Proceedings of the 1st European Conference on Coniputer Vision. Antibes, France. New York: Springer-Verlag, pp. 374-384.

15.

Koenderink, J. , and Van Doom, A. 1979. The internal representation of solid shape with respect to vision. Biol. Cybernet. 32:211-216.

16.

Morin, L. 1993 (January). Quelques Contributions des Invariants Projectifs à la Vision par Ordinateur. Ph.D. thesis, Institut National Polytechnique de Grenoble.

17.

Mohr, R. , Veillon, F. , and Quan, L. 1993 (June). Relative 3D reconstruction using multiple uncalibrated images. In Proceedings of the Conference on Computer Vision and Pattern Recognition, New York, pp. 543-548.

18.

Nitzan, D. 1988. Three-dimensional vision structure for robot applications . IEEE Trans. PAMI 10(3):291-309.

19.

Petitjean, S. , Ponce, J. , and Kriegman, D.J. 1992. Computing exact aspect graphs of curved objects: Algebraic surfaces. Int. J. Computer Vision 9(3):231-255.

20.

Rothwell, C.A. , Zisserman, C. , Forsyth, D.A. , and Mundy, J.L. 1992. Fast recognition using algebraic invariants. In Mundy, J. L. , and Zisserman, A. (eds.): Geometric Invariance in Computer Vision . Cambridge, MA: MIT Press, pp. 398-407.

21.

Sossa, H. , and Horaud, R. 1992 (June). Model indexing: the graph-hashing approach . In Proceedings of the Conference on Computer Vision and Pattern Recognition, Urbana-Champaign, IL.

22.

Thompson, D.W. , and Mundy, J.L. 1987. Three-dimensional model matching from an unconstraint viewpoint. In Proceedings of IEEE International Conference on Robotics and Automation, Raleigh, NC, pp. 208-220.

23.

Weiss, I. 1992 (June). Noise-resistant projective and affine invariants . In Proceedings of the Conference on Computer Vision and Pattern Recognition, Urbana-Champaign, IL, pp. 115-121.