Motion-Based Segmentation of Transparent Layers in Video Sequences

  • Vincent Auvray
  • Patrick Bouthemy
  • Jean Liénard
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4105)


We present a method for segmenting moving transparent layers in video sequences. We assume that the images can be divided into areas containing at most two moving transparent layers. We call this configuration (which is the mostly encountered one) bi-distributed transparency. The proposed method involves three steps: initial block-matching for two-layer transparent motion estimation, motion clustering with 3D Hough transform, and joint transparent layer segmentation and parametric motion estimation. The last step is solved by the iterative minimization of a MRF-based energy function. The segmentation is improved by a mechanism detecting areas containing one single layer. The framework is applied to various image sequences with satisfactory results.


Video Sequence Motion Estimation Motion Model Markov Random Field Transparent Layer 
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.
    Auvray, V., Liénard, J., Bouthemy, P.: Multiresolution parametric estimation of transparent motions. In: Proc. Int. Conf. on Image Processing (ICIP 2005), Genova (2005)Google Scholar
  2. 2.
    Irani, M., Sarel, B.: Separating Transparent Layers through Layer Information Exchange. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3024, pp. 328–341. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  3. 3.
    Pingault, M., Pellerin, D.: Motion estimation of transparent objects in the frequency domain. Signal Processing 84, 709–719 (2004)MATHCrossRefGoogle Scholar
  4. 4.
    Shizawa, M., Mase, K.: Principle of superposition: A common computational framework for analysis of multiple motions. In: IEEE Workshop on Visual Motion, Princetown, New-Jersey, pp. 164–172 (1991)Google Scholar
  5. 5.
    Pingault, M., Bruno, E., Pellerin, D.: A robust multiscale B-spline function decomposition for estimating motion transparency. IEEE Trans. on Image Processing 12, 1416–1426 (2003)CrossRefGoogle Scholar
  6. 6.
    Stuke, I., Aach, T., Mota, C., Barth, E.: Estimation of multiple motions: Regularization and performance evaluation. In: Image and Video Communications and Processing 2003, SPIE, vol. 5022, pp. 75–86 (2003)Google Scholar
  7. 7.
    Stuke, I., Aach, T., Mota, C., Barth, E.: Estimation of multiple motions by block matching. In: 4th ACIS Int. Conf. on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD 2003), Luebeck, pp. 358–362 (2003)Google Scholar
  8. 8.
    Toro, J., Owens, F., Medina, R.: Multiple motion estimation and segmentation in transparency. In: Proc. of the IEEE Int. Conference on Acoustics, Speech and Signal Processing, Istanbul, pp. 2087–2090 (2000)Google Scholar
  9. 9.
    Odobez, J.-M., Bouthemy, P.: Robust multiresolution estimation of parametric motion models. Journal of Vis. Com. and Image Repr. 6, 348–365 (1995)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Vincent Auvray
    • 1
    • 2
  • Patrick Bouthemy
    • 1
  • Jean Liénard
    • 2
  1. 1.IRISA/INRIARennesFrance
  2. 2.General Electric HealthcareBucFrance

Personalised recommendations