Skip to main content

Class based reconstruction techniques using singular apparent contours

Part of the Lecture Notes in Computer Science book series (LNCS,volume 1064)

Abstract

We present methods for the global reconstruction of some classes of special surfaces. The contour ending (cusp on the apparent contour) is tracked under a dynamic monocular perspective observer. The classes of surfaces considered are surfaces of revolution (SOR), canal surfaces and ruled surfaces. This paper presents theoretical methods for surface reconstruction and error analysis of reconstruction under noise. We find the techniques used exhibit stability even under large noise. This work has added to the accumulating body of work that has arisen in the computer vision community, concerning the differential geometric aspects of special surface classes.

Keywords

  • Camera Motion
  • Cusp Point
  • Image Sphere
  • Asymptotic Direction
  • Canal Surface

These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. J.W.Bruce, P.J.Giblin, F.Tari, 'special surfaces and their duals; preliminary version', Liverpool University Preprint. (1995).

    Google Scholar 

  2. R.Cipolla and A.Blake, ‘Surface shape from deformation of apparent contours', Int. J. of Computer Vision 9 (1992), 83–112.

    Google Scholar 

  3. R.Cipolla, G.Fletcher, P.Giblin, 'surface geometry from cusps of apparent contours', Proc. Fifth Int. Conf. on Computer Vision, Cambridge, Mass, June 1995, pp.858–863.

    Google Scholar 

  4. R.Cipolla, G.Fletcher, P.Giblin, ‘Following Cusps', to appear in Int.J.Computer Vision.

    Google Scholar 

  5. R.Cipolla, K.E.Åström and P.J.Giblin, ‘Motion from the frontier of curved surfaces', Proc. Fifth Int. Conf. on Computer Vision, Cambridge, Mass, June 1995, pp.269–275

    Google Scholar 

  6. D.A.Forsyth, J.L.Mundy, A.Zisserman, C.A.Rothwell, ‘Recognising rotationally symmetric surfaces from their outlines', Proc. Second European Conf. on Computer Vision, Santa Margherita Ligure (Italy), pp.639–647, May 1992.

    Google Scholar 

  7. R.Glachet, M.Dhome, J.T.Lapreste, ‘Finding the pose of an object of revolution', Proc. Second European Conf. on Computer Vision, Santa Margherita Ligure (Italy), pp.681–686, May 1992.

    Google Scholar 

  8. J.J.Koenderink, Solid Shape, M.I.T.Press 1990.

    Google Scholar 

  9. B.O'Neill, Elementary Differential Geometry, Academic Press 1966.

    Google Scholar 

  10. J.Ponce, ‘Invariant properties of straight homogeneous generalized cylinders'. IEEE PAMI, vol.11,no.9,pp.951–965, 1989.

    Google Scholar 

  11. J.Ponce, D.Chelberg, ‘Finding the limbs and cusps of Generalized Cylinders.’ Int. J.Comp. Vision 1, (1987) 195–210.

    Google Scholar 

  12. J.H.Rieger,'Projections of generic surfaces of revolution', Geometriae Dedicata, 1993, Vol.48, No.20, pp.211–230.

    Google Scholar 

  13. A.Zisserman, J.Mundy, D.Forsyth, J.Liu, N.Pillow, C.Rothwell and S.Utcke, ‘Class-Based Groupings in Perspective Images', Proc. Fifth Int. Conf. on Computer Vision, Cambridge, Mass, June 1995.

    Google Scholar 

  14. M.Zerroug, R.Nevatia, ‘Segmentation and recovery of SHGCs from a real intensity image.', Proc. Third European Conf. on Computer Vision, Stockholm, Sweden Vol.I pp.319–330, May 1994.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 1996 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Fletcher, G.J., Giblin, P.J. (1996). Class based reconstruction techniques using singular apparent contours. In: Buxton, B., Cipolla, R. (eds) Computer Vision — ECCV '96. ECCV 1996. Lecture Notes in Computer Science, vol 1064. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0015527

Download citation

  • DOI: https://doi.org/10.1007/BFb0015527

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-61122-6

  • Online ISBN: 978-3-540-49949-7

  • eBook Packages: Springer Book Archive