An efficient iterative pose estimation algorithm

  • S. H. Or
  • W. S. Luk
  • K. H. Wong
  • I. King
Poster Session III
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1352)


We propose a novel model-based algorithm which finds the 3D pose of an object from an image by breaking down the estimation process into two linear processing stages, namely the depth recovery and the pose calculation. The depth recovery stage determines the new positions of the model point set in 3D space whereas the pose calculation step is a least-square estimation of the transformation parameters between the point set formed from the previous stage and the model set. The estimates are iteratively refined until converged. The advantage of using our algorithm is that the computational cost is much reduced. We test our algorithm by applying it to both synthetic as well as real time head tracking problem with satisfactory results.


Pose Estimation Real time vision Human-computer Interface 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    K. S. Arun, T. S. Huang, and S. D. Blostein. Least-square fitting of two 3-D point sets. IEEE Trans. Pattern Anal. Machine Intell., 9(5):698–700, Sept. 1987.Google Scholar
  2. 2.
    A. Azarbayejani and A. Pentland. Recursive estimation of motion, structure, and focal length. IEEE Trans. Pattern Anal. Machine Intell., 17(6):562–575, June 1995.Google Scholar
  3. 3.
    T. J. Broida. Recursive 3-D motion estimation from a monocular image sequence. IEEE Trans. Aerospace Electronic Systems, 26(4):639–655, July 1990.Google Scholar
  4. 4.
    D. F. Dementhon and L. S. Davis. Model-based object pose in 25 lines of code. Intl. Journal of Comput. Vision, 15:123–141, 1995.Google Scholar
  5. 5.
    B. K. P. Horn. Closed-form solution of absolute orientation using unit quaternions. J. Opt. Soc. Amer., 4:629–642, Apr. 1987.Google Scholar
  6. 6.
    H. Li, P. Roivainen, and R. Forchheimer. 3-D motion estimation in model-based facial image coding. IEEE Trans. Pattern Anal. Machine Intell., 15(6):545–555, June 1993.Google Scholar
  7. 7.
    D. G. Lowe. Fitting parameterized three dimensional models to images. IEEE Trans. Pattern Anal. Machine Intell., 13(5):441–450, May 1991.Google Scholar
  8. 8.
    R. Szeliski and S. B. Kang. Recovering 3D shape and motion from image streams using non-linear least squares. Cambridge Research Laboratory Technical Report, Mar. 1993.Google Scholar
  9. 9.
    S. Umeyama. Least-square estimation of transformation parameters between two point pattern. IEEE Trans. Pattern Anal. Machine Intell., 13(4):376–380, Apr. 1991.Google Scholar
  10. 10.
    K. Waters. A muscle model for animating three-dimensional facial expression. Comput. Graphics, 21(4):17–24, 1987.Google Scholar
  11. 11.
    J. Weng, N. Ahuja, and T. S. Huang. Optimal motion and structure estimation. IEEE Trans. Pattern Anal. Machine Intell., 15(9):864–884, Sept. 1993.Google Scholar
  12. 12.
    P. Wunsch and G. Hirzinger. Registration of CAD-models to images by iterative inverse perspective matching. Proc. ICPR 96, pages 78–83, Nov. 1996.Google Scholar
  13. 13.
    Z. Zhang and O. Faugeras. 3D Dynamic Scene Analysis. Springer-Verlag, 1992.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • S. H. Or
    • 1
  • W. S. Luk
    • 2
  • K. H. Wong
    • 1
  • I. King
    • 1
  1. 1.Department of Computer Science & EngineeringThe Chinese University of Hong KongShatin, N.T.Hong Kong
  2. 2.Departement ComputerwetenschappenKatholieke Universiteit LeuvenHeverleeBelgium

Personalised recommendations