Skip to main content

Restructuring aspect graphs into aspect- and cell-equivalence classes for use in computer vision

  • Computer Vision
  • Conference paper
  • First Online:
Graph-Theoretic Concepts in Computer Science (WG 1987)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 314))

Included in the following conference series:

Abstract

A potential disadvantage of using aspect graphs as object models in a computer vision system is their large size. The upper bound on the number of nodes in the aspect graph of an N-face convex object is O(Nā‹†ā‹†3). In this paper we introduce the concepts of "aspect-equivalence" and "cell-equivalence" and present a method of using them to restructure a data base of aspect graphs. This process identifies an interconnected set of equivalence classes which we use to form an Equivalence Class Graph (ECG).

This work is supported by the Air Force Office of Scientific Research under Grant AFOSR-87-0316.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

6. References

  1. Castore, G. and Crawford, C.G. From Solid Model to Robot Vision, IEEE International Conference on Robotics, 90ā€“92, (1984).

    Google ScholarĀ 

  2. Chakravarty, I. and Freeman, H. Characteristic Views As a Basis of Three-Dimensional Object Recognition, SPIE Volume 36: Robot Vision, 37ā€“45, (1982).

    Google ScholarĀ 

  3. Crawford, C.G. Aspect Graphs and Robot Vision, IEEE International Conference on Computer Vision and Pattern Recognition, 382ā€“384, (1985).

    Google ScholarĀ 

  4. Fekete, G. and Davis, L.S. Property Spheres: A New Representation for 3-D Object Recognition, IEEE Workshop on Computer Vision: Representation and Control, 192ā€“201, (1984).

    Google ScholarĀ 

  5. Goad, C. Automatic Construction of Special Purpose Programs for Hidden Surface Elimination, Computer Graphics 16 (3), 167ā€“178 (July, 1982).

    Google ScholarĀ 

  6. Goad, C. Special Purpose Automatic Programming for 3-D Model-Based Vision, 1983 DARPA Image Understanding Workshop, 94ā€“104, (1984).

    Google ScholarĀ 

  7. Kim, H., Jain, R.C., and Volz, R.A. Object Recognition Using Multiple Views, IEEE International Conference on Computer Vision and Pattern Recognition, 28ā€“33, (1985).

    Google ScholarĀ 

  8. Koenderink, J.J and van Doorn, A.J. The Internal Representation of Solid Shape with Respect to Vision, Biological Cybernetics 32, 211ā€“216, (1979).

    PubMedĀ  Google ScholarĀ 

  9. Korn, M.R. and Dyer, C.R. 3-D Multiview Object Representations for Model-Based Object Recognition, Pattern Recognition 20 (1), 91ā€“103, (1987).

    ArticleĀ  Google ScholarĀ 

  10. Stewman, J. and Bowyer, K. Aspect Graphs for Planar-face Convex Objects, Proceedings of the IEEE Computer Society Workshop on Computer Vision, 123ā€“130, (1987).

    Google ScholarĀ 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Herbert Gƶttler Hana-JĆ¼rgen Schneider

Rights and permissions

Reprints and permissions

Copyright information

Ā© 1988 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Stewman, J., Stark, L., Bowyer, K. (1988). Restructuring aspect graphs into aspect- and cell-equivalence classes for use in computer vision. In: Gƶttler, H., Schneider, HJ. (eds) Graph-Theoretic Concepts in Computer Science. WG 1987. Lecture Notes in Computer Science, vol 314. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-19422-3_18

Download citation

  • DOI: https://doi.org/10.1007/3-540-19422-3_18

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-19422-4

  • Online ISBN: 978-3-540-39264-4

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics