Spatio-temporal Descriptor Using 3D Curvature Scale Space

  • A. Dyana
  • Sukhendu Das
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4815)

Abstract

This paper presents a novel technique to jointly represent the shape and motion of video objects for the purpose of content based video retrieval (CBVR). It enables to retrieve similar objects undergoing similar motion patterns, that are not captured only using motion trajectory or shape descriptors. In our approach, both shape and motion information are integrated in a unified spatio-temporal representation. Curvature scale space theory proposed by Mokhtarian is extended (in 3D) to represent shape as well as motion trajectory of video objects. A sequence of 2D contours are taken as input and convolved with a 2D Gaussian. The zero crossings are found out from the curvature of evolved surfaces, which form the 3D CSS surface. The peaks from the 3D CSS surface form the features for joint spatio-temporal representation of video objects. Experiments are carried out on CBVR and results show good performance of the algorithm.

Keywords

Curvature scale space motion trajectory content based video retrieval spatio-temporal descriptor 

References

  1. 1.
    Davies, E.R.: Machine Vision: Theory, Algorithms, Practicalities. Morgan Kaufmann, San Francisco (2005)Google Scholar
  2. 2.
    Belongie, S., J.M., Puzicha, J.: Matching shapes. In: Eighth IEEE International Conference on Computer Vision, pp. 456–461 (2001)Google Scholar
  3. 3.
    Lu,, Sajjanhar, A.: Region-based shape representation and similarity measure suitable for content-based image retrieval. Multimedia System 7(2), 165–174 (1999)CrossRefGoogle Scholar
  4. 4.
    Kunttu, I., Lepistö, L., Rauhamaa, J., Visa, A.: Multiscale fourier descriptor for shape-based image retrieval. In: Proceedings of the 17th International Conference on Pattern Recognition (ICPR 2004), vol. 2, pp. 765–768.Google Scholar
  5. 5.
    Ogniewicz, L.R.: Skeleton-space: a multiscale shape description combining region and boundary information. In: Proc. Comput. Vision Pattern Recogn.Google Scholar
  6. 6.
    Latecki, L.J., Lakamper, R., Eckhardt, U.: Shape descriptors for non-rigid shapes with a single closed contour. In: CVPR, pp. 424–429Google Scholar
  7. 7.
    Mokhtarian, F., Bober, M.: Curvature Scale Space Representation: Theory, Applications and MPEG-7 Standardization. Kluwer Academic Publishers, The Netherlands (2003)MATHGoogle Scholar
  8. 8.
    Adamek, T., O’Connor, N.E.: A multiscale representation method for nonrigid shapes with a single closed contour. IEEE Transactions on Ciruits and systems for video technology 14(5), 742–753 (2004)CrossRefGoogle Scholar
  9. 9.
    Jalba, A.C., Wilkinson, M.H.F., Roerdink, J.B.T.M.: Shape representation and recognition through morphological curvature scale spaces. IEEE Transactions on Image Processing 15(2), 331–341 (2006)CrossRefGoogle Scholar
  10. 10.
    Dimitrova, N., Golshani, F.: Motion recovery for video content classification. ACM Trans. Inf. Syst. 13(14), 408–439 (1995)CrossRefGoogle Scholar
  11. 11.
    Little, J.J., Gu, Z.: Video retrieval by spatial and temporal structure of trajectories. In: Proc. SPIE Storage and Retrieval for Media Databases, vol. 13, pp. 408–439 (1995)Google Scholar
  12. 12.
    Sahouria, E.: Video indexing based on object motion. Master’s thesis, Dept. Elect. Eng. Comp. Sci, Univ. California, Berkeley (1997)Google Scholar
  13. 13.
    Dagtas, S., et al.: Models for motion-based video indexing and retrieval. IEEE Transactions on Image Processing 9(1), 88–101 (2000)CrossRefGoogle Scholar
  14. 14.
    DeMenthon, D., Doermann, D.: Video retrieval using spatio-temporal descriptors. In: ACM Multimedia, pp. 508–517 (2003)Google Scholar
  15. 15.
    Chatzis, S., Doulamis, A., Kosmopoulos, D., Varvarigou, T.: Video representation and retrieval using spatio-temporal descriptors and region relations. In: ICANN (2), pp. 94–103 (2006)Google Scholar
  16. 16.
    Deng, Y., Manjunath, B.S.: Netra-v: Toward an object-based video representation. IEEE Transactions on Ciruits and systems for video technology 8(5), 116–127 (1998)Google Scholar
  17. 17.
    Chang, S.F., et al.: A fully automated content-based video search engine supporting spatiotemporal queries. IEEE Transactions on Ciruits and systems for video technology 8(5), 602–615 (1998)CrossRefGoogle Scholar
  18. 18.
  19. 19.
    Mokhtarian, F., Abbasi, S., Kittler, J.: Robust and efficient shape indexing through curvature scale space. In: British Machine Vision Conference, pp. 53–62 (1996)Google Scholar
  20. 20.
  21. 21.

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • A. Dyana
    • 1
  • Sukhendu Das
    • 1
  1. 1.Visualization and Perception Lab, Computer Science and Engineering Deptt., Indian Institute of Technology Madras, ChennaiIndia

Personalised recommendations