Building new tools for synthetic image animation by using evolutionary techniques

  • Jean Louchet
  • Michael Boccara
  • David Crochemore
  • Xavier Provot
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1063)


Particle-based models and articulated models are increasingly used in synthetic image animation applications. This paper aims at showing examples of how Evolutionary Algorithms can be used as tools to build realistic physical models for image animation.

First, a method to detect regions with rigid 2D motion in image sequences, without solving explicitly the Optical Flow equation, is presented. It is based on the resolution of an equation involving rotation descriptors and first-order image derivatives. An evolutionary technique is used to obtain a raw segmentation based on motion; the result of segmentation is then refined by an accumulation technique in order to determine more accurate rotation centres and deduce articulation points.

Second, an evolutionary algorithm designed to identify internal parameters of a mass-spring animation model from kinematic data (“Physics from Motion”) is presented through its application to cloth animation modelling.


Computer vision motion analysis image animation evolutionary algorithms 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [BHW94]
    D.Breen, D. House, M. Wozny, “Predicting the drape of woven cloth using interacting particles”, Proc. Siggraph 94, Comp. Graph. Proc., 1994, pp. 365–372.Google Scholar
  2. [BL95]
    M.Boccara, J.Louchet “Recherche de points d'articulation dans les séquences d'images”, internal report, Ecole Nationale Supérieure de Techniques Avancées, 1995.Google Scholar
  3. [G89]
    D.A.Goldberg, “Genetic Algorithms in Search, Optimization and Machine Learning”, Addison-Wesley 1989.Google Scholar
  4. [GVP90]
    M.-P. Gascuel, A. Verroust, C.Puech “Animation with collisions of deformable articulated bodies”, Eurographics Workshop on Animation & Simulation, Sep. 1990.Google Scholar
  5. [HW83]
    B.K.P. Horn, E.J. Weldon Jr., “Determining Optical Flow”, Artificial Intelligence 17: 185–204, 1981.Google Scholar
  6. [IP94).
    Jim Ivins, John Porrill, Statistical Snakes: Active Region Models, British Machine Vision Conference, York, Sep. 1994.Google Scholar
  7. [K92]
    John Koza, Genetic Programming, MIT Press, 1992.Google Scholar
  8. [L94]
    J. Louchet, “An Evolutionary Algorithm for Physical Motion Analysis”, British Machine Vision Conference, York, Sep. 1994.Google Scholar
  9. [L94a]
    J.Louchet, “Identification évolutive de modèles physiques d'animation”, Journées Evolution Artificielle 94, Toulouse Sep. 1994.Google Scholar
  10. [LJFCR91]
    A. Luciani, S. Jimenez, J.L. Florens, C. Cadoz, O. Raoult, “Computational Physics: a Modeller Simulator for Animated Physical Objects”, Proc. Eurographics Conference, Wien, Sep. 1991, Elsevier.Google Scholar
  11. [P95]
    X.Provot, “Deformation Constraints in a Mass-Spring Model to describe Rigid Cloth behavior”, Graphics Interface 1995, Québec, April 1995.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Jean Louchet
    • 1
    • 2
  • Michael Boccara
    • 1
  • David Crochemore
    • 1
  • Xavier Provot
    • 2
  1. 1.Laboratoire d'Electronique et d'InformatiqueENSTAParis cedex 15France
  2. 2.INRIA, projet SYNTIM RocquencourtLe Chesnay CedexFrance

Personalised recommendations