Advertisement

Spectral Structuring of Home Videos

  • Jean-Marc Odobez
  • Daniel Gatica-Perez
  • Mael Guillemot
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2728)

Abstract

Accessing and organizing home videos present technical challenges due to their unrestricted content and lack of storyline. In this paper, we propose a spectral method to group video shots into scenes based on their visual similarity and temporal relations. Spectral methods have been shown to be effective in capturing perceptual organization features. In particular, we investigate the problem of automatic model selection, which is currently an open research issue for spectral methods, and propose measures to assess the validity of a grouping result. The methodology is used to group scenes from a six-hour home video database, and is assessed with respect to a ground-truth generated by multiple people. The results indicate the validity of the proposed approach, both compared to existing techniques as well as the human ground-truth.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    F.R.K. Chung, Spectral Graph Theory, American Mathematical Society, 1997.Google Scholar
  2. [2]
    D. Comaniciu, V. Ramesh, and P. Meer, “Real-Time Tracking of Non-Rigid Objects using Mean Shift,” in Proc. IEEE CVPR., Hilton Head Island, S. C., June 2000.Google Scholar
  3. [3]
    D. Gatica-Perez, A. Loui, and M.T. Sun, “Finding Structure in Home Videos by Probabilistic Hierarchical Clustering,” IEEE Trans. on Circuits and Systems for Video Technology, Vol. 13, No. 5, Jun. 2003.Google Scholar
  4. [4]
    G. Iyengar and A. Lippman, “Content-based browsing and edition of unstructured video,” in Proc. IEEE ICME, New York City, Aug. 2000.Google Scholar
  5. [5]
    J.R. Kender and B. L. Yeo, “On the Structure and Analysis of Home Videos,” in Proc. ACCV, Taipei, Jan. 2000.Google Scholar
  6. [6]
    S. Vempala R. Kannan and A. Vetta, “On clusterings-good, bad and spectral,” in Proc. 41st Symposium on the Foundation of Computer Science, FOCS, 2000.Google Scholar
  7. [7]
    A. Ng, M. I. Jordan, and Y. Weiss, “On spectral clustering: analysis and an algorithm,” in Proc. NIPS, Vancouver, Dec 2001.Google Scholar
  8. [8]
    J.-M. Odobez, D. Gatica-Perez and M. Guillemot, “On Spectral Methods and Structuring of Home Videos,” IDIAP Technical Report, IDIAP-RR-55, Nov. 2002.Google Scholar
  9. [9]
    J. Platt “AutoAlbum: Clustering Digital Photographs using Probablisitic Model Merging,” in Proc. IEEE Workshop on CBAIVL, Hilton Head Island, S. C.,2000.Google Scholar
  10. [10]
    A. Savakis, S. Etz, and A. Loui, “Evaluation of image appeal in consumer photography,” in Proc. SPIE Conf. on Human Vision and EI, Jan. 2000.Google Scholar
  11. [11]
    G. L. Scott and H.C. Longuet-Higgins, “Feature grouping by relocalisation of eigenvectors of the proximity matrix,” in Proc. BMVC, 1990, pp. 103–108.Google Scholar
  12. [12]
    J. Shi and J. Malik, “Normalized cuts and image segmentation,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 888–905, 2000.CrossRefGoogle Scholar
  13. [13]
    M. Yeung, B. L. Yeo, and B. Liu, “Segmentation of Video by Clustering and Graph Analysis,” Comp. Vision and Image Underst., Vol. 71, No. 1, pp. 94–109, July 1998.CrossRefGoogle Scholar
  14. [14]
    Y. Weiss, “Segmentation using eigenvectors: a unifying view,” in Proc. ICCV, 1999.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Jean-Marc Odobez
    • 1
  • Daniel Gatica-Perez
    • 1
  • Mael Guillemot
    • 1
  1. 1.IDIAPMartignySwitzerland

Personalised recommendations