Occlusion-Based Accurate Silhouettes from Video Streams

  • Pedro M. Q. Aguiar
  • António R. Miranda
  • Nuno de Castro
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4141)


We address the problem of segmenting out moving objects from video. The majority of current approaches use only the image motion between two consecutive frames and fail to capture regions with low spatial gradient, i.e., low textured regions. To overcome this limitation, we model explicitly: i) the occlusion of the background by the moving object and ii) the rigidity of the moving object across a set of frames. The segmentation of the moving object is accomplished by computing the Maximum Likelihood (ML) estimate of its silhouette from the set of video frames. To minimize the ML cost function, we developed a greedy algorithm that updates the object silhouette, converging in few iterations. Our experiments with synthetic and real videos illustrate the accuracy of our segmentation algorithm.


Video Sequence Initial Guess Motion Estimation Video Stream Active Contour 
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.
    Aguiar, P., Jasinschi, R., Moura, J., Pluempitiwiriyawej, C.: Content-based image sequence representation. In: Reed, T. (ed.) Digital Video Processing, ch. 2, pp. 7–72. CRC Press, Boca Raton (2004)Google Scholar
  2. 2.
    Li, H., Lundmark, A., Forchheimer, R.: Image sequence coding at very low bitrates: A review. IEEE Trans. on Image Processing 3(5) (1994)Google Scholar
  3. 3.
    Diehl, N.: Object-oriented motion estimation and segmentation in image sequences. Signal Processing: Image Communication 3(1) (1991)Google Scholar
  4. 4.
    Jasinschi, R., Moura, J.: Content-based video sequence representation. In: Proc of IEEE Int. Conf. on Image Processing, Washigton D.C., USA (1995)Google Scholar
  5. 5.
    Sawhney, H., Ayer, S.: Compact representations of videos through dominant and multiple motion estimation. IEEE Trans. on Pattern Analysis and Machine Intelligence 18(8) (1996)Google Scholar
  6. 6.
    Jasinschi, R., Moura, J.: Generative Video: Very Low Bit Rate Video Compression. U.S. Patent and Trademark Office, S.N. 5, 854, 856 (1998)Google Scholar
  7. 7.
    Tao, H., Sawhney, H., Kumar, R.: Dynamic layer representation with applications to tracking. In: Proc. of IEEE Int. Conf. on Computer Vision and Pattern Recognition, Hilton Head Island, South Carolina (2000)Google Scholar
  8. 8.
    Jojic, N., Frey, B.: Learning flexible sprites in video layers. In: Proc. of IEEE Int. Conf. on Computer Vision and Pattern Recognition, Hawaii (2001)Google Scholar
  9. 9.
    Dubuisson, M.P., Jain, A.: Contour extraction of moving objects in complex outdoor scenes. Int. Jounal of Computer Vision 14(1) (1995)Google Scholar
  10. 10.
    Bouthemy, P., François, E.: Motion segmentation and qualitative dynamic scene analysis from an image sequence. Int. Jounal of Computer Vision 10(2) (1993)Google Scholar
  11. 11.
    Irani, M., Peleg, S.: Motion analysis for image enhancement: Resolution, occlusion, and transparency. Journal of Visual Communications and Image Representation 4(4), 324–335 (1993)CrossRefGoogle Scholar
  12. 12.
    Irani, M., Rousso, B., Peleg, S.: Computing occluding and transparent motions. Int. Journal of Computer Vision 12(1) (1994)Google Scholar
  13. 13.
    Aguiar, P., Moura, J.: Maximum likelihood estimation of the template of a rigid moving object. In: Figueiredo, M., Zerubia, J., Jain, A.K. (eds.) EMMCVPR 2001. LNCS, vol. 2134. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  14. 14.
    Aguiar, P., Moura, J.: Figure–ground segmentation from occlusion. IEEE Trans. on Image Processing 14(8) (2005)Google Scholar
  15. 15.
    Bergen, J., et al.: Hierarchical model-based motion estimation. In: Sandini, G. (ed.) ECCV 1992. LNCS, vol. 588. Springer, Heidelberg (1992)Google Scholar
  16. 16.
    Mumford, D., Shah, J.: Boundary detection by minimizing functionals. In: Prof. of IEEE Int. Conf. on Computer Vision and Pattern Recognition, San Francisco, CA, USA (1985)Google Scholar
  17. 17.
    Morel, J., Solimini, S.: Variational Methods in Image Segmentation. Birkhäuser, Boston (1995)Google Scholar
  18. 18.
    Malladi, R., Sethian, J., Vemuri, B.: Shape modeling with front propagation: A level set approach. IEEE Trans. on Pattern Analysis and Machine Intelligence 17(2), 158–175 (1995)CrossRefGoogle Scholar
  19. 19.
    Sapiro, G.: Geometric Partial Differential Equations and Image Analysis. Cambridge University Press, Cambridge (2001)CrossRefMATHGoogle Scholar
  20. 20.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. Int. Journal of Computer Vision 1(4), 321–331 (1988)CrossRefGoogle Scholar
  21. 21.
    Caselles, V., Kimmel, R., Sapiro, G.: Geodesic snakes. Int. Journal of Computer Vision 22, 61–79 (1997)CrossRefMATHGoogle Scholar
  22. 22.
    Chan, T., Vese, L.: Active contours without edges. IEEE Trans. on Image Processing 10(2), 266–277 (2001)CrossRefMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Pedro M. Q. Aguiar
    • 1
  • António R. Miranda
    • 1
  • Nuno de Castro
    • 1
  1. 1.Institute for Systems and Robotics / Instituto Superior TécnicoLisboaPortugal

Personalised recommendations