Pose refinement of active models using forces in 3D

  • A. D. Worrall
  • G. D. Sullivan
  • K. D. Baker
Shape Modelling
Part of the Lecture Notes in Computer Science book series (LNCS, volume 800)


A new algorithm is described for refining the pose of a model of a rigid object, to conform more accurately to the image structure. Elemental 3D forces are considered to act on the model. These are derived from directional derivatives of the image local to the projected model features. The convergence properties of the algorithm is investigated and compared to a previous technique. Its use in a video sequence of a cluttered outdoor traffic scene is also illustrated and assessed.


Active Model Configuration Space Boundary Line Model Line Simplex Algorithm 
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.


  1. 1.
    K.D. Baker, G.D. Sullivan: Performance Assessment of Model-based Tracking. IEEE workshop on Applications of Computer Vision, California, 28–35 (1992).Google Scholar
  2. 2.
    A. Blake, R. Curwen, A. Zisserman: Affine-invariant contour tracking with automatic control of spatiotemporal scale. Proc 4th ICCV, 66–75 (1993)Google Scholar
  3. 3.
    K.S. Brisdon, G.D. Sullivan, K.D. Baker: Feature Aggregation in Iconic Model Matching. Proc Alvey Vision Conference, AVC-88, Manchester, 19–24 (1988).Google Scholar
  4. 4.
    K.S. Brisdon: Hypothesis Verification using Iconic Matching. PhD Thesis, The University of Reading, 1990.Google Scholar
  5. 5.
    T.F. Cootes, C.J. Taylor: Active Shape Models — Smart Snakes. Proc BMVC-92 Springer-Verlag, 266–275 (1992).Google Scholar
  6. 6.
    T.F. Cootes, C.J. Taylor, A. Lanitis, D.H. Cooper, J. Graham: Building and Using Flexible Models Incorporating Grey-Level Information. Proc 4th ICCV, 242–246 (1993)Google Scholar
  7. 7.
    R. Curwen, A. Blake: Dynamic Contours: Real-time active splines. In: A. Blake, Yuille (eds.): Active Vision. MIT Press 1932 pp. 39–57Google Scholar
  8. 8.
    C. Harris: Tracking with Rigid Models. In: A. Blake, A. Yuille (eds.): Active Vision. MIT Press 1992 pp. 59–73Google Scholar
  9. 9.
    C. Harris, C. Stennett: RAPID — A Video rate Object Tracker. BMVC90, 73–77 (1990).Google Scholar
  10. 10.
    A. Hill, T.F. Cootes, C.J. Taylor: A Generic system for Image Interpretation using Flexible Templates. Imag & Vis Comp J, 295–300 (1992).Google Scholar
  11. 11.
    M. Kass, A. Witkin, D. Terzopoulos: Snakes: Active Contours Models. ICCV-1 (IEEE Press) 259–68 (1987).Google Scholar
  12. 12.
    Kollers, Daniilidis, H.H. Nagel: Model-Based Object Tracking in Monocular Image Sequences of Road Traffic Scenes. Int J of Comp Vision, 257–821 (1993)Google Scholar
  13. 13.
    D.G. Lowe: Perceptual organisation and visual recognition. Boston, Kluwer Academic Publishers (1985).Google Scholar
  14. 14.
    D.G. Lowe: Fitting Parameterized 3-D Models to Images. IEEE Trans. on Pattern Analysis and Machine Intelligence. Vol 13, No. 5, 441–450 (1991).Google Scholar
  15. 15.
    W.H. Press, et al.: Numerical Recipes. Cambridge University Press 1986Google Scholar
  16. 16.
    R.S. Stevens: Real-time 3D Object Tracking. Proc Alvey Vision Conf, 85–90 (1989).Google Scholar
  17. 17.
    G.D. Sullivan: Visual interpretation of known objects in constrained scenes. Phil. Trans. Roy Soc (B) 337, 361–370 (1992).Google Scholar
  18. 18.
    G.D. Sullivan: Visual Traffic Understanding using the Ground-plane Constraint. Proc 2nd Intnl Conf on Comp Applic to Eng Systems (Cyprus), 473–478 (1993)Google Scholar
  19. 19.
    T.N. Tan, G.D. Sullivan, K.D. Baker: Recognising Objects on the Ground Plane. BMVC93 BMVA Press, 85–94 (1993).Google Scholar
  20. 20.
    A.D. Worrall, K.D. Baker, G.D. Sullivan: Model-based Perspective Inversion. Image and Vision Computing Journal, 17–23 (1989)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • A. D. Worrall
    • 1
  • G. D. Sullivan
    • 1
  • K. D. Baker
    • 1
  1. 1.Dept of Computer ScienceUniversity of ReadingReadingUK

Personalised recommendations