Implicit Free-Form-Deformations for Multi-frame Segmentation and Tracking

  • Konstantinos Karantzalos
  • Nikos Paragios
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3752)


In this paper, we propose a novel technique to address motion estimation and tracking. Such technique represents the motion field using a regular grid of thin-plate splines, and the moving objects using an implicit function on the image plane that is a cubic interpolation of a ”level set function” defined on this grid. Optical flow is determined through the deformation of the grid and consequently of the underlying image structures towards satisfying the constant brightness constraint. Tracking is performed in similar fashion through the consistent recovery in the temporal domain of the zero iso-surfaces of a level set that is the projection of the Free Form Deformation (FFD) implicit function according to the cubic spline formulation. Such an approach is a compromise between dense motion estimation and parametric motion models, introduces smoothness in an implicit fashion, is intrinsic, and can cope with important object deformations. Promising results demonstrate the potentials of our approach.


Motion Estimation Active Contour Object Boundary Active Contour Model Initial Contour 
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.
    Barron, J., Fleet, D., Beauchemin, S.: Performance of Optical Flow Techniques. International Journal of Computer Vision 12, 43–77 (1994)CrossRefGoogle Scholar
  2. 2.
    Horn, B., Schunck, B.: Determinating Optical Flow. Artificial Intelligence 17, 185–203 (1981)CrossRefGoogle Scholar
  3. 3.
    Weickert, J., Schnorr, C.: Variational optic flow computation with a spatio-temporal smoothness constraint. Journal of Mathematical Imaging and Vision 14, 245–255 (2001)zbMATHCrossRefGoogle Scholar
  4. 4.
    Lucas, B., Kanade, T.: An Iterative Image Registration Technique with an Application to Stereo Vision. In: International Joint Conference on Artificial Intelligence, pp. 674–679 (1981)Google Scholar
  5. 5.
    Huber, P.: Robust Statistics. John Wiley & Sons, Chichester (1981)zbMATHCrossRefGoogle Scholar
  6. 6.
    Black, M., Jepson, A.: Estimating optical flow in segmented images using variable-order parametric models with local deformations. IEEE Transactions on Pattern Analysis and Machine Intelligence 18, 973–986 (1996)CrossRefGoogle Scholar
  7. 7.
    Odobez, J.-M., Bouthemy, P.: Robust multiresolution estimation of parametric motion models. Journal of Visual Communication and Image Representation 6, 348–365 (1995)CrossRefGoogle Scholar
  8. 8.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active Contour Models. In: IEEE International Conference in Computer Vision, pp. 261–268 (1987)Google Scholar
  9. 9.
    Isard, M., Blake, A.: Contour Tracking by Stochastic Propagation of Conditional Density. In: European Conference on Computer Vision, vol. I, pp. 343–356 (1996)Google Scholar
  10. 10.
    Cootes, T., Taylor, C., Cooper, D., Graham, J.: Active shape models - their training and application. Computer Vision and Image Understanding 61, 38–59 (1995)CrossRefGoogle Scholar
  11. 11.
    Osher, S., Sethian, J.: Fronts propagating with curvature-dependent speed: Algorithms based on the Hamilton-Jacobi formulation. Journal of Computational Physics 79, 12–49 (1988)zbMATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    Osher, S., Paragios, N.: Geometric Level Set Methods in Imaging, Vision and Graphics. Springer, Heidelberg (2003)zbMATHGoogle Scholar
  13. 13.
    Paragios, N., Deriche, R.: Geodesic Active Contours and Level Sets for the Detection and Tracking of Moving Objects. IEEE Transactions on Pattern Analysis and Machine Intelligence 22, 266–280 (2000)CrossRefGoogle Scholar
  14. 14.
    Cremers, D.: A Variational Framework for Image Segmentation Combining Motion Estimation and Shape Regularization. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 53–58 (2003)Google Scholar
  15. 15.
    Sethian, J.: Level Set Methods. Cambridge University Press, Cambridge (1996)zbMATHGoogle Scholar
  16. 16.
    Weber, M., Blake, A., Cipolla, R.: Sparse Finite Elements for Geodesic Contours with Level-Sets. In: European Conference on Computer Vision, pp. 391–404 (2004)Google Scholar
  17. 17.
    Paragios, N., Deriche, R.: Unifying Boundary and Region-based Information for Geodesic Active Tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. II-300–305 (1999)Google Scholar
  18. 18.
    Yezzi, A., Zollei, L., Kapur, T.: A Variational Framework for Joint Segmentation and Registration. IEEE Mathematical Methods in Biomedical Image Analysis, 44–51 (2001)Google Scholar
  19. 19.
    Dydenko, I., Friboulet, D., Magnin, I.: A Variational Framework for Affine Registration and Segmentation with Shape Prior: Application in Echocardiographic Imaging. In: Faugeras, O., Paragios, N. (eds.) IEEE Workshop in Variational and Level Set Methods, pp. 209–217 (2003)Google Scholar
  20. 20.
    Yilmaz, A., Li, X., Shah, B.: Contour based object tracking with occlusion handling in video acquired using mobile cameras. IEEE Transactions on Pattern Analysis and Machine Intelligence (2004)Google Scholar
  21. 21.
    Sederberg, T., Parry, S.: Free-Form Deformation of Solid Geometric Models. In: ACM SIGGRAPH, vol. 4, pp. 151–160 (1986)Google Scholar
  22. 22.
    Faloutsos, P., van de Panne, M., Terzopoulos, D.: Dynamic Free-Form Deformations for Animation Synthesis. IEEE Transactions on Visualization and Computer Graphics 3, 201–214 (1997)CrossRefGoogle Scholar
  23. 23.
    Zhao, H.-K., Chan, T., Merriman, B., Osher, S.: A variational Level Set Approach to Multiphase Motion. Journal of Computational Physics 127, 179–195 (1996)zbMATHCrossRefMathSciNetGoogle Scholar
  24. 24.
    Chan, T., Vese, L.: Active Contours without Edges. IEEE Transactions on Image Processing 10, 266–277 (2001)zbMATHCrossRefGoogle Scholar
  25. 25.
    Caselles, V., Kimmel, R., Sapiro, G.: Geodesic Active Contours. In: IEEE International Conference in Computer Vision, pp. 694–699 (1995)Google Scholar
  26. 26.
    Kichenassamy, S., Kumar, A., Olver, P., Tannenbaum, A., Yezzi, A.: Gradient flows and geometric active contour models. In: IEEE International Conference in Computer Vision, pp. 810–815 (1995)Google Scholar
  27. 27.
    Brox, T., Bruhn, A., Weickert, J.: High accuracy optical flow estiation based on a theory for warping. In: European Conference on Computer Vision, pp. 158–163 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Konstantinos Karantzalos
    • 1
    • 2
  • Nikos Paragios
    • 1
  1. 1.ATLANTIS, CERTISEcole Nationale des Ponts et ChausseesMarne-La-ValleeFrance
  2. 2.School of Rural and Survey EngineeringNational Technical University of AthensZographouGreece

Personalised recommendations