Advertisement

Simultaneous Inpainting and Motion Estimation of Highly Degraded Video-Sequences

  • Jean Pierre Cocquerez
  • Laurent Chanas
  • Jacques Blanc-Talon
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2749)

Abstract

This article deals with new restoration algorithms of strongly degraded videos. Degradations appears either as missing data in every image or as a large magnitude impulse noise. The proposed algorithm is based upon a partial differential equation formalism coming from recent works on image inpainting and video sequence restoration. It use a 3D representation of the video sequences and can process moving background sequence. Simultaneous inpainting and motion estimation are carried out. High quality results are presented in the context of the restoration of degraded films.

Keywords

Video Sequence Image Sequence Motion Estimation Motion Compensation High Quality Result 
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.

References

  1. 1.
    Masnou, S., Morel, J.M.: Level-lines based disocclusion. In: Proceedings of 5th IEEE Int’l Conf. on Image Process., Chicago (1998) 3:259–263Google Scholar
  2. 2.
    Dekeyser, F., Bouthemy, P., Prez, P.: Spatio-temporal wiener filtering of images using a parametric motion model. In: Proceedings of the IEEE International Conference on Image Processing, ICIP’2000, Vancouver, British Columbia (2000)Google Scholar
  3. 3.
    Chanas, l., Cocquerez, J.P., Blanc-Talon, J.: Numerical energy minimization for removing high luminous energy in dazzled images. Advanced Concepts for Intelligent Vision Systems (ACIVS’99), Baden-Baden, Germany (1999)Google Scholar
  4. 4.
    Kleihorst, R., De Haan, G., Lagendijk, R., Biemond, J.: of Signal Processing VI: Theories and Applications. In: Motion compensated noise filtering of image sequences. Elsevier science (1992) 1385–1388Google Scholar
  5. 5.
    Giaccone, P., G.A., J., Minelly, S., Curley, A.: Motion-compensated multi-channel noise reduction of colour film sequences. SPIE Journal of Electronic Imaging 8(99) 246–254Google Scholar
  6. 6.
    Kalivas, D., Sawchuk, A.: Motion compensated enhancement of noisy image sequences. In: Proceedings of the IEEE International conference on acoustics, speech and signal processing, Albuquerque (1990) 2121–2124Google Scholar
  7. 7.
    Kokaram, A.: Motion Picture Restoration. Springer-Verlag London (1998)Google Scholar
  8. 8.
    Woods, J., Kim, J.: 12. In: Motion compensated spatio-temporal kalman filter. Kluwer Academic (1993) 349–373Google Scholar
  9. 9.
    VanRoosmalen, P.M.B., Westen, S.J.P., Lagendijk, R.L., Biemond, J.: Noise reduction for image sequences using an pyramid thresholding technique. In: Proceedings of the IEEE International Conference on Image Processing, Lausanne (1996) 375–378Google Scholar
  10. 10.
    Geman, S., McClure, D., Geman, D.: A nonlinear filter for film restoration and other problems in image processing. Graphical models and image processing 54 (1992) 281–289CrossRefGoogle Scholar
  11. 11.
    Fan, C., Namazi, N.: Simultaneous motion estimation and filtering of images sequences. IEEE Transactions on image processing 8 (1999) 1788–1795CrossRefGoogle Scholar
  12. 12.
    Kornprobst, P., Deriche, R., Aubert, G.: Image sequence restoration: a pde based coupled method for image restoration and motion segmentation. In: Proceedings of the European Conference on Computer Vision, Freiburg, Allemagne (1998) 548–562Google Scholar
  13. 13.
    Aubert, G., Deriche, R., Kornprobst, P.: Computing optical flow via variational techniques. SIAM Journal on Applied Mathematics 60 (2000) 156–182CrossRefMathSciNetGoogle Scholar
  14. 14.
    Kornprobst, P.: Contribution la restauration d’images et l’analyse de squences: Approches Variationnelles et Solutions de Viscosit. PhD thesis, Universit de Nice-Sophia Antipolis (1998)Google Scholar
  15. 15.
    Black, M.J.: Robust incremental optical flow. PhD thesis, Yale university (1992)Google Scholar
  16. 16.
    Chanas, L.: Methodes variationnelles pour la restauration de squences d’images fortement degradees. PhD thesis, Cergy University (2001)Google Scholar
  17. 17.
    Chan, T., Shen, J.: Non-texture inpainting by curvature-driven diffusions (ccd). Technical report, UCLA CAM Report (2000)Google Scholar
  18. 18.
    Charbonnier, P., Aubert, G., Blanc-Ferraud, M., Barlaud, M.: Two-deterministic half-quadratic regularization algorithms for computed imaging. In: Proc. IEEE int. Conf. on Image Proc. ICIP. Volume 1., Austin (Texas) (1994) 168–172CrossRefGoogle Scholar
  19. 19.
    Charbonnier, P., Aubert, G., Blanc-Ferraud, M., Barlaud, M.: Deterministic edge-preserving regularization in computed imaging. IEEE Transactions on Image Processing 6 (1997) 298–311CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Jean Pierre Cocquerez
    • 1
  • Laurent Chanas
    • 2
  • Jacques Blanc-Talon
    • 3
  1. 1.Universite de Technologie de Compiegne(UTC)CompiegneFrance
  2. 2.Vision IQBoulogneFrance
  3. 3.GIP departmentCTAArcueil

Personalised recommendations