Elastically adaptive deformable models

  • Dimitri Metaxas
  • Ioannis A. Kakadiaris
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1065)


We present a novel technique for the automatic adaptation of a deformable model's elastic parameters within a Kalman filter frame-work for shape estimation applications. The novelty of the technique is that the model's elastic parameters are not constant, but time varying. The model for the elastic parameter variation depends on the local error of fit and the rate of change of the error of fit. By augmenting the state equations of an extended Kalman filter to incorporate these additional variables and take into account the noise in the data, we are able to significantly improve the quality of the shape estimation. Therefore, the model's elastic parameters are initialized always to the same value and they subsequently modified depending on the data and the noise distribution. In addition, we demonstrate how this technique can be parallelized in order to increase its efficiency. We present several experiments to demonstrate the effectiveness of our method.


Kalman Filter Extended Kalman Filter Elastic Parameter Deformable Model Active Contour Model 
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.
    A. Blake and M. Isard, “3D position, attitude and shape input using video tracking of hands and lips”, Proc. Siggraph'94, pp. 185–192, 1994.Google Scholar
  2. 2.
    T. Broida and R. Chellappa, “Estimation of object motion parameters from noisy images”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(1):90–98, January 1986.Google Scholar
  3. 3.
    L. D. Cohen. “On Active Contour Models and Balloons”. CVGIP: IU, 53(2), 1991.Google Scholar
  4. 4.
    C. W. Chen and T. S. Huang, “Epicardial Motion and Deformation Estimation from Coronary Artery Bifurcation Points”, IEEE Proc. Third International Conference on Computer Vision (ICCV '90), pp. 456–459, Osaka, Japan, Dec. 1990.Google Scholar
  5. 5.
    E. D. Dickmanns and Volker Graefe, “Dynamic Monocular Machine Vision”, Machine Vision and Applications, 1:223–240, 1988.Google Scholar
  6. 6.
    J. S. Duncan and R. L. Owen and P. Anandan, “Measurement of Nonrigid Motion Using Contour Shape Descriptors”, IEEE Computer Vision and Pattern Recognition Conference (CVPR'91), pp. 318–324, Hawaii, 1991.Google Scholar
  7. 7.
    A. Gelb. “Applied Optimal Estimation”, MIT Press, Cambridge, MA, 1974.Google Scholar
  8. 8.
    M. S. Grewal and A. P. Andrews. Kalman Filtering: Theory and Applications. Prentice Hall, 1993.Google Scholar
  9. 9.
    D. B. Goldgof and H. Lee and T. S. Huang, “Motion Analysis of Nonrigid Structures”, IEEE Computer Vision and Pattern Recognition Conference (CVPR'88), pp. 375–380, 1988.Google Scholar
  10. 10.
    T. S. Huang, “Modeling, Analysis and Visualization of Nonrigid Object Motion”, IEEE 10th International Conference on Pattern Recognition, Atlantic City, NJ, pp. 361–364, 1990.Google Scholar
  11. 11.
    M. Kass and A. Witkin and D. Terzopoulos, “Snakes: Active Contour Models”, International Journal of Computer Vision, 1(4), pp. 321–331, 1988.Google Scholar
  12. 12.
    I. A. Kakadiaris and D. Metaxas, 3D Human Body Model acquisition from Multiple views, Proc. ICCV'95, pp. 618–623, June 20–23, Boston, MA, 1995.Google Scholar
  13. 13.
    O. V. Larsen, P. Radeva, and E. Marti, Guidelines for choosing optimal parameters of elasticity for snakes, 6th International Conference on Computer Analysis of Images and Patterns, pp. 106–113, Praga, 1995.Google Scholar
  14. 14.
    L. Matthies, T. Kanade, and R. Szeliski, “Kalman Filter-based Algorithms for Estimating Depth from Image Sequences”, International Journal of Computer Vision, 3:209–236, 1989.Google Scholar
  15. 15.
    D. Metaxas and D. Terzopoulos. Recursive Estimation of Nonrigid Shape and Motion. Proc. IEEE Motion Workshop, Princeton, NJ, pp. 306–311, October 1991.Google Scholar
  16. 16.
    D. Metaxas and D. Terzopoulos. Shape and Nonrigid Motion Estimation Through Physics-Based Synthesis. IEEE Trans. Pattern Analysis and Machine Intelligence, June, 1993.Google Scholar
  17. 17.
    D. Metaxas and E. Koh. “Flexible Multibody Dynamics and Adaptive Finite Element Techniques for Model Synthesis and Estimation” Computer Methods in Applied Mechanics and Engineering, in press.Google Scholar
  18. 18.
    A. Pentland and B. Horowitz, “Recovery of Non-rigid Motion and Structure”, IEEE Trans. Pattern Analysis and Machine Intelligence, 13(7):730–742, 1991.Google Scholar
  19. 19.
    R. Samadani. Adaptive Snakes: Control of damping and material parameters. SPIE Geometric Methods in Computer Vision, Vol 1570, 1991.Google Scholar
  20. 20.
    O. Zienkiewicz. The Finite Element Method. McGraw-Hill, 1977.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Dimitri Metaxas
    • 1
  • Ioannis A. Kakadiaris
    • 1
  1. 1.Department of Computer and Information ScienceUniversity of PennsylvaniaPhiladelphia

Personalised recommendations