Feature Correspondences from Multiple Views of Coplanar Ellipses

  • C. Barat
  • J. F. Menudet
  • H. Louhichi
  • T. Fournel
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4292)


We address the problem of feature correspondences in images of coplanar ellipses with objective to benefit of robust ellipse fitting algorithm. The main difficulty is the lack of projective invariant points immediately available. Therefore, our key idea is to construct virtual line and point features using the property of tangent invariance under perspective projection. The proposed method requires first a robust detection of ellipse edge points to fit a parametric model on each ellipse. The feature lines are then obtained by computing the 4 bitangents to each couple of ellipses. The points are derived by considering the tangent points and the intersection points between bitangents. Results of experimental studies are presented to demonstrate the reliability and robustness of the feature extraction process. Subpixel accuracy is easily achieved. A real application to camera self-calibration is also described.


Point Cloud Feature Point Camera Calibration Multiple View Tangent Point 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ducottet, C., Fournel, T., Barat, C.: Scale-adaptive detection and local characterization of edges based on wavelet transform. Signal Processing 84, 2115–2137 (2004)MATHCrossRefGoogle Scholar
  2. 2.
    Fitzgibbon, A., Pilu, M., Fisher, R.B.: Direct Least Square Fitting of Ellipses. IEEE Trans. PAMI 21(5), 476–480 (1999)Google Scholar
  3. 3.
    Habert, L.: Computing bitangents for ellipses. In: Proc. 17th Canadian Conference on Computational Geometry (CCCG 2005), pp. 294-297 (2005)Google Scholar
  4. 4.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2002)Google Scholar
  5. 5.
    Schmid, C., Zisserman, A.: The geometry and matching of lines and curves over multiple views. International Journal on Computer Vision 40(3), 199–234 (2000)MATHCrossRefGoogle Scholar
  6. 6.
    Kaminski, J.Y., Shashua, A.: Multiple View Geometry of General Algebraic Curves. International Journal on Computer Vision 56(3), 195–219 (2004)CrossRefGoogle Scholar
  7. 7.
    Kahl, F., Heyden, A.: Using Conic Correspondence in Two Images to Estimate the Epipolar Geometry. In: Proceedings of the International Conference on Computer Vision (1998)Google Scholar
  8. 8.
    Mudigonda, P.K., Jawahar, C.V., Narayanan, P.J.: Geometric Structure Computation from Conics. In: Proceedings of Indian Conference on Computer Vision, Graphics & Image Processing (2004)Google Scholar
  9. 9.
    Rothwell, C.A., Zisserman, A., Forsyth, D.A., Mundy, J.L.: Planar Object Recognition using Projective Shape Representation. International Journal on Computer Vision 16(1), 57–99 (1995)CrossRefGoogle Scholar
  10. 10.
    Sampson, S.P.: Fitting conic sections to very scattered data: an iterative refinement of the Bookstein algorithm. Computer Graphics and Image Processing 18, 97–108 (1982)CrossRefGoogle Scholar
  11. 11.
    Triggs, B.: Autocalibration from planar sequences. In: Proc. of the European Conference on Computer Vision, Freiburg, Germany (June 1998)Google Scholar
  12. 12.
    Wu, Y., Li, X., Wu, F., Hu, Z.: Coplanar circles, quasi-affine invariance and calibration. Image and Vision Computing 24(4), 319–326 (2006)CrossRefGoogle Scholar
  13. 13.
    Zhang, Z.: A flexible new technique for camera calibration. IEEE Trans. PAMI 22, 1330–1334 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • C. Barat
    • 1
  • J. F. Menudet
    • 1
  • H. Louhichi
    • 1
  • T. Fournel
    • 1
  1. 1.Laboratoire Traitement du Signal et Instrumentation, UMR CNRS 5516Université Jean MonnetSaint-EtienneFrance

Personalised recommendations