Advertisement

Comparison of Statistical and Shape-Based Approaches for Non-rigid Motion Tracking with Missing Data Using a Particle Filter

  • Abir El Abed
  • Séverine Dubuisson
  • Dominique Béréziat
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4179)

Abstract

Recent developments in dynamic contour tracking in video sequences are based on prediction using dynamical models. The parameters of these models are fixed by learning the dynamics from a training set to represent plausible motions, such as constant velocity or critically damped oscillations. Thus, a problem arise in cases of non-constant velocity and unknown interframe motion, i.e. unlearned motions, and the CONDENSATION algorithm fails to track the dynamic contour. The main contribution of this work is to propose an adaptative dynamical model which parameters are based on non-linear/non-gaussian observation models. We study two different approaches, one statistical and one shape-based, to estimate the deformation of an object and track complex dynamics without learning from a training set neather the dynamical nor the deformation models and under the constraints of missing data, non-linear deformation and unknown interframe motion. The developed approaches have been successfully tested on several sequences.

Keywords

Video Sequence Discrete Fourier Transform Fourier Descriptor Tennis Table Inverse Discrete Fourier Transform 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Sorenson, H.: Kalman filtering: theory and application. IEEE Press, Los Alamitos (1985)Google Scholar
  2. 2.
    Jazwinski, A.: Stochastic processes and filtering theory. Academic Press, London (1974)Google Scholar
  3. 3.
    Doucet, A., Godsill, S., Andrieu, C.: On sequential monte carlo sampling methods for bayesian filtering. Statistics and computing, 197–208 (2000)Google Scholar
  4. 4.
    Doucet, A., Gordon, N., de Freitas, J.: An introduction to sequential monte carlo methods. In: Sequential Monte Carlo Methods in Practice. Springer, New York (2001)Google Scholar
  5. 5.
    Kitagawa, G.: Monte carlo filter and smoother for non-gaussian nonlinear state space models. Journal of Computational and Graphical Statistics 1(25) (1996)Google Scholar
  6. 6.
    Blake, A., Isard, M.: Active Contours. Springer, Heidelberg (1998)Google Scholar
  7. 7.
    North, B., Blake, A., Isard, M., Rittscher, J.: Learning and classification of complex dynamics. IEEE Transactions on pattern analysis and machine intelligence 22 (September 2000)Google Scholar
  8. 8.
    Isard, M., Blake, A.: Condensation - conditional density propagation for visual tracking. Int. J. Computer Vision (1998)Google Scholar
  9. 9.
    Doucet, A.: On sequential monte carlo methods for bayesian filtering. Technical report, University of Cambridge, UK, Department of Engineering (1998)Google Scholar
  10. 10.
    Liu, J.S., Chen, R.: Blind deconvolution via sequential imputation. J. Amer. Statist. Assoc., 567–576 (1995)Google Scholar
  11. 11.
    Jain, A.: Information and systems science series. Fundamentals of digital image processing (1989)Google Scholar
  12. 12.
    Bi, J., Bennett, K.P.: Regression error characteristic curves. In: Proceedings of the Twentieth International Conference on Machine Learning (ICML 2003), Washington DC (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Abir El Abed
    • 1
  • Séverine Dubuisson
    • 1
  • Dominique Béréziat
    • 1
  1. 1.Laboratoire d’Informatique de Paris 6Université Pierre et Marie CurieParisFrance

Personalised recommendations