Advertisement

Direct model-based image motion segmentation for dynamic scene analysis

  • Jean-Marc Odobez
  • Patrick Bouthemy
Motion Estimation and Segmentation
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1035)

Abstract

Analysing the dynamic content of a scene observed by a mobile camera often requires the segmentation of each image of the sequence into region entities of apparent homogeneous motion. To each region is associated a 2D polynomial model (e.g., an affine one) able to describe at each location the underlying 2D “true” motion with a predefined precision η. Thanks to the use of a multiresolution robust estimator [1] to compute the motion models, the determination of the boundaries between the different regions, which is stated as a statistical regularization based on multiscale Markov Random Field (MRF) models, can be achieved in one pass only. This avoids the time consuming iterations between motion estimation and boundary identification that are encountered in almost all other motion-segmentation schemes (for instance [2, 3, 4]). We explicitly detect areas where the error between the underlying motion and the one given by the estimated models is not whithin the precision η. This allows us to handle the appearance of new objects in the scene. We have performed numerous experiments with real indoor and outdoor image sequences which demonstrate the efficiency of the method.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    J.-M. Odobez and P. Bouthemy. Robust multiresolution estimation of parametric motion models. To appear in Int. Jal of Visual Communication and Image Representation, September 1995.Google Scholar
  2. 2.
    D.W. Murray and H. Buxton. Scene segmentation from visual motion using global optimization. IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 9, No.2:220–228, March 1987.Google Scholar
  3. 3.
    P. Bouthemy and E. François. Motion segmentation and qualitative dynamic scene analysis from an image sequence. Int. Journal of Computer Vision, Vol. 10, No 2:157–182, April 1993.Google Scholar
  4. 4.
    E.H. Adelson and J.Y.A Wang. Representing moving images with layers. IEEE Trans. on Image Processing, 3(5):625–638, September 1994.Google Scholar
  5. 5.
    S. Ayer, P. Schroeter, and J. Bigün. Segmentation of moving objects by robust motion parameter estimation over multiple frames. In Proc. of the 3rd ECCV, volume 2, pages 316–327, Stockholm, May 1994.Google Scholar
  6. 6.
    M.M. Chang, M.I. Sezan, and A.M. Tekalp. An algorithm for simultaneous motion estimation and scene segmentation. In Proc. of ICCASP 94, volume 5, pages 221–224, Adelaide, Australia, June 1994.Google Scholar
  7. 7.
    F. Meyer and P. Bouthemy. Estimation of time-to-collision maps from first order motion models and normal flows. In Proc. 11th Intern. Conf. on Pattern Recognition, The Hague, pages 78–82, 1992.Google Scholar
  8. 8.
    C. Nelson and J. Aloimonos. Obstacle avoidance using flow field divergence. IEEE Trans. Pattern Anal. Machine Intell., Vol. 11, No.10:1102–1106, Oct. 1989.Google Scholar
  9. 9.
    S. Negahdaripour and S. Lee. Motion recovery from image sequences using only first order optical flow information. Intern. J. Comput. Vis., 9(3):163–184, 1992.Google Scholar
  10. 10.
    G. Adiv. Determining three-dimensional motion and structure from optical flow generated by several moving objects. IEEE Trans. Pattern Anal. Machine Intell., Vol 7:384–401, July 1985.Google Scholar
  11. 11.
    Jean-Marc Odobez. Estimation, détection et segmentation du mouvement dans une séquence d'images: une approche robuste et markovienne. PhD thesis, IRISA, University of Rennes I, N∘ 1304, December 1994.Google Scholar
  12. 12.
    P. Perez, F. Heitz, and P. Bouthemy. Multiscale minimization of global energy functions in some visual recovery problems. CVGIP: Image Understanding, 59(1):125–134, January 1994.Google Scholar
  13. 13.
    P.B. Chou and C.M. Brown. The theory and practice of Bayesian image modeling. Int. Jal of Computer Vision, Vol. 4:185–210, 1990.Google Scholar
  14. 14.
    J-M. Odobez and P. Bouthemy. Detection of multiple moving objects using multiscale MRF with camera motion compensation. In Proc. 1st IEEE ICIP, volume 2, pages 257–261, Austin, Texas, November 1994.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Jean-Marc Odobez
    • 1
  • Patrick Bouthemy
    • 1
  1. 1.IRISA/INRIA, Campus universitaire de BeaulieuRennes CedexFrance

Personalised recommendations