Advertisement

Global Motion Fourier Series Expansion for Video Indexing and Retrieval

  • E. Bruno
  • D. Pellerin
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1929)

Abstract

This paper describes a new framework for global motion fea- ture extraction and presents a video indexing and retrieval application. Optical ow between two frames is expanded, directly from the image derivatives, in a Fourier series. This technique provides a good global motion representation over a few Fourier components. These Fourier components are relevant to discriminate complex motions, such as human activities. Results of indexing and retrieval on a database of human activities sequences are presented.

Keywords

Video Sequence Motion Estimation Fourier Component Global Motion Fourier Series Expansion 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    J.L. Barron, D.J. Fleet, and S.S. Beauchemin. Performance of optical ow tech-niques. International Journal of Computer Vision, 1(12):43–77, 1994.CrossRefGoogle Scholar
  2. 2.
    E. Bruno and D. Pellerin. Robust motion estimation using spatial gabor filters. In X European Signal Processing Conference, September 2000.Google Scholar
  3. 3.
    O. Chomat and J. Crowley. Probabilistic recognition of activity using local ap-pearance. In Conference on Computer Vision ans Pattern Recognition (CVPR), June 1999.Google Scholar
  4. 4.
    E. Diday, G. Govaert, Y. Lechevallier, and J. Sidi. Clustering in pattern recogni-tion. Digital Image Processing, pages 19–58, 1981.Google Scholar
  5. 5.
    R. Fablet and P. Bouthemy. Motion-based feature extraction and ascendant hierar-chical classification for video indexing and retrieval. In Proc. of the 3rd Int. Conf. on Visual Information Systems, VISual99, volume 1614, pages 221–228, June 1999.Google Scholar
  6. 6.
    D. J. Fleet, M. J. Black, and A. D. Jepson. Motion feature detection using steerable ow fields. In IEEE Conf. on Computer Vision and Pattern Recognition, CVPR-98, 1998.Google Scholar
  7. 7.
    B.K.P. Horn and B.G. Schunk. Determing optical flow. Artificial Intelligence, 17:185–204, 1981.CrossRefGoogle Scholar
  8. 8.
    F. Idris and S. Panchantan. Review of image and video indexing. Journal of Visual Communication and Image Representation, 8(2):146–147, June 1997.CrossRefGoogle Scholar
  9. 9.
    R. Milanese, D. Squire, and T. Pun. Correspondence analysis and hierarchical indexing for content-based image retrieval. In ICIP’96, September 1996.Google Scholar
  10. 10.
    R. Nelson and P. Polana. Qualitative recognition of motions using temporal tex-ture. In CVGIP: Image Understanding, volume 1, July 1992.Google Scholar
  11. 11.
    K. Otsuka, T. Horikoshi, S. Suzuki, and M. Fujii. Feature extraction of temporal texture based on spatio-temporal motion trajectory. In Proc. Int. Conf. on Pattern Recognition, ICPR’98, August 1998.Google Scholar
  12. 12.
    W. H. Press, S.A. Teukolsky, W.T. Vetterling, and B.P. Flannery. Numerical Recipies in C, Second Edition. Cambridge University Press, 1992.Google Scholar
  13. 13.
    M. Szummer and R.W. Picard. Temporal texture modeling. In ICIP’96, September 1996.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • E. Bruno
    • 1
  • D. Pellerin
    • 1
    • 2
  1. 1.INPGLaboratoire des Images et des Signaux (LIS)Grenoble CedexFrance
  2. 2.ISTGUniversité Joseph FourierGrenobleFrance

Personalised recommendations