Skip to main content
SpringerLink
Log in

A systematic approach to geometry-based grouping and non-accidentalness

  • Recognition of Visual Structure
  • Conference paper
  • First Online:
Algebraic Frames for the Perception-Action Cycle (AFPAC 1997)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1315))

Abstract

Geometric regularities have often been used for grouping. Nonetheless, their foundations have typically been rather ad hoc - with “regular” or “non-accidental” features being listed according to intuition or based on application-specific considerations. This paper describes a more systematic line of thought towards such visual grouping. Based on an earlier observation that fixed structures in images are directly related to object regularities and grouping specific invariants, fixed structures are propounded as a theoretical glue. Moreover, grouping strategies with less than combinatorial complexity are difficult to develop. The propounded approach is also intended to keep grouping complexity under control. To that end, it combines the use of invariants with a Cascaded Hough Transform to efficiently extract candidate fixed structures.

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

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. S. Carlsson, R. Mohr, T. Moons, L. Morin, C. Rothwell, M. Van Diest, L. Van Gool, F. Veillon, and A. Zisserman, Semi-local projective invariants for the recognition of smooth plane curves, to appear in Int. Journal of Computer Vision

    Google Scholar 

  2. R. Glachet, J. Lapreste, M. Dhome, Locating and modelling a flat symmetric object from a single projective image, Computer Vision, Graphics, and Image Processing: Image Understanding, Vo1.57, pp.219–226, 1993

    Google Scholar 

  3. T. Kanade, Recovery of the 3-dimensional shape of an object from a single view, Artificial Intelligence, Vol.17, pp.75–116, 1981

    Article  Google Scholar 

  4. D. Lowe, Perceptual Organization and Visual Recognition Stanford University technical report STAN-CS-84-1020, 1984

    Google Scholar 

  5. D. Lowe, The Viewpopint Consistency Constraint, International Journal of Computer Vision, pp.57–72, Voll, 1987

    Article  Google Scholar 

  6. D. Lowe, Perceptual organisation and visual recognition, Kluwer Academic Publishers, 1985

    Google Scholar 

  7. J. Mundy and A. Zisserman (eds.), Geometric invariance in computer vision, MIT Press, Cambridge, 1992

    Google Scholar 

  8. J. Ponce, On characterizing ribbons and finding skewed symmetries, Proc. Int. Conf. on Robotics and Automation, pp. 49–54, 1989

    Google Scholar 

  9. C. Rothwell, Recognition using perspective invariance, PhD Thesis, Univ. of Oxford, 1993

    Google Scholar 

  10. C. Rothwell, D. Forsyth, A. Zisserman, and J. Mundy, Extracting projective structure from single perspective views of 3D points sets, Proc. 3rd Int. Conf. Computer Vision, Belin, pp. 573–582, 1993

    Google Scholar 

  11. C. Rothwell and J. Stern, Understanding the shape properties of trihedral polyhedra, Eur. Conf. Computer Vision, pp. 175–185, Cambridge, UK, 1996

    Google Scholar 

  12. J. Semple and G. Kneebone, Algebraic projective geometry, Clarendon, 1979

    Google Scholar 

  13. D. Sinclair, H. Christensen, and C. Rothwell, Using the relation between a plane projectivity and the fundamental matrix, Britsh Machine Vision Conference

    Google Scholar 

  14. C. Springer, Geometry and analysis of projective spaces, Freeman, 1964

    Google Scholar 

  15. T. Tuytelaars, M. Proesmans, and L. Van Gool, The Cascaded Hough Transform as support for grouping and finding vanishing points and lines, published in these proceedings.

    Google Scholar 

  16. L. Van Gool, T. Moons, E. Pauwels, and A. Oosterlinck, Semi-differential invariants, in Applications of invariance in vision, J. Mundy and A. Zisserman (eds.), pp. 157–192, MIT Press, Boston, 1992

    Google Scholar 

  17. L. Van Gool, M. Proesmans, and A. Zisserman, Grouping and invariants using planar homologies, Proc. Europe-China Workshop on Geometrical Modeling and Invariants for Computer Vision, pp. 182–189, 1995

    Google Scholar 

  18. L. Van Gool, T. Moons, D. Ungureanu, and A. Oosterlinck, The characterisation and detection of skewed symmetry, Computer Vision and Image Understanding (previously CVGIP), Vol. 61, No. 1, pp. 138–150, 1995

    Article  Google Scholar 

  19. L. Van Gool, T. Moons, and M. Proesmans, Groups for grouping: a strategy for the exploitation of geometrical constraints, Proc. 6th Int. Conf. on Computer Analysis of Images and Patterns, Prague, pp. 1–8, sept. 1995

    Google Scholar 

  20. L. Van Gool, T. Moons, and M. Proesmans, Mirror and point symmetry under perspective skewing, IEEE Conf. Computer Vision and Pattern Recognition, pp. 285–292, San Francisco, june 1996

    Google Scholar 

  21. M. Wertheimer, Laws of organization in perceptual forms, in A source-book of Gestalt Psychology, ed. D. Ellis, Harcourt, Brace and Co., pp.71–88, 1938

    Google Scholar 

  22. A. Zisserman, J. Mundy, D. Forsyth, and J. Liu, Class-based grouping in perspective images, Proc. Int. Conf. Computer Vision, pp.183–188, 1995

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Katholieke Universiteit Leuven, ESAT-M12 Kardinaal Mercierlaan 94, B-3001, Leuven, Belgium

    Luc Van Gool

Authors
  1. Luc Van Gool
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Gerald Sommer Jan J. Koenderink

Rights and permissions

Reprints and permissions

Copyright information

© 1997 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Van Gool, L. (1997). A systematic approach to geometry-based grouping and non-accidentalness. In: Sommer, G., Koenderink, J.J. (eds) Algebraic Frames for the Perception-Action Cycle. AFPAC 1997. Lecture Notes in Computer Science, vol 1315. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0017864

Download citation

  • DOI: https://doi.org/10.1007/BFb0017864

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-63517-8

  • Online ISBN: 978-3-540-69589-9

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation