Video Object Segmentation Using Multiple Features

  • Alvaro Pardo
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3287)


In this paper we present an algorithm for semi-automatic object extraction from video sequences using multiple features. This work is part of an ongoing effort to study video segmentation using multiple features, and the relative contribution of each one of them. For this reason, the algorithm here presented will be very simple and made up from of the shelf algorithms. We will show that even with a simple algorithm, with the right steps, we can successfully segment video objects in moderate complex sequences.


Gaussian Mixture Model Motion Estimation Multiple Feature Object Shape Video Object 
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.


  1. 1.
    Marlow, S., Oconnor, N.: Supervised Object Segmentation and Tracking for MPEG4 VOP Generation. In: ICPR 2000 - International Conference on Pattern Recognition, vol. 1, pp. 1125–1128 (2000)Google Scholar
  2. 2.
    Castagno, R., Ebrahimi, T., Kunt, M.: Video Segmentation Based on Multiple Features for Interactive Multimedia Applications. IEEE Transactions on Circuits and Systems for Video Technology 8, 562–571 (1998)CrossRefGoogle Scholar
  3. 3.
    Gu, C., Lee, M.C.: Semiautomatic Segmentation and TRacking of Semantic Video Objects. IEEE Transactions on Image Processing 8, 572–584 (1998)Google Scholar
  4. 4.
    Everingham, M., Thomas, B.: Supervised Segmentation adn Tracking of Nonrigid Objects using a Mixture of Histograms Model. In: ICIP 2001 - International Conference on Image Processing, pp. 62–65 (2001)Google Scholar
  5. 5.
    Khan, S., Shah, M.: Object Based Segmentation of Video using Color, Motion and Saptial Information. In: CVPR 2001 - Int. Conf. Computer Vision and Pattern Recogbition, vol. 2, pp. 746–751 (2001)Google Scholar
  6. 6.
    Greenspan, H., Goldberger, J., Meyer, A.: Probabilistic Space-Time Video Modeling via Piecewise GMM. IEEE Transactions on Pattern Analysis and Machine Intelligence 26, 384–396 (2004)CrossRefGoogle Scholar
  7. 7.
    Thirde, D., Jones, G., Flack, J.: Spatio-Temporal Semantic Object Segmentation using Probabilistic Sub-Object Regions. In: BMVC 2003 - British Machine Vision Conf. (2003)Google Scholar
  8. 8.
    Pardo, A., Sapiro, G.: Vector Probability Diffusion. IEEE Signal Processing Letters 8, 106–109 (2001)CrossRefGoogle Scholar
  9. 9.
    Duda, R., Hart, P., Stork, D.: Pattern Classification, 2nd edn. John Wiley and Sons, Chichester (2000)Google Scholar
  10. 10.
    Barron, J., Fleet, D., Beauchemin, S.: Performance of Optical Flow Techniques. International Journal of Computer Vision 12, 43–77 (1994)CrossRefGoogle Scholar
  11. 11.
    Baker, S., Matthews, I.: Lucas-Kanade 20 Years on: A Unifying Approach. International Journal of Computer Vision 56, 221–255 (2004)CrossRefGoogle Scholar
  12. 12.
    Figueiredo, M., Jain, A.: Unsupervised Learning of Finite Mixture Models. IEEE Transaction on Pattern and Machine Intelligence 24, 381–396 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Alvaro Pardo
    • 1
  1. 1.IIE & IMERL Faculty of EngineeringUniversidad de la República, CC 30, and Faculty of Engineering and Technologies, Universidad Católica del UruguayMontevideoUruguay

Personalised recommendations