Recovering in Video Documents

  • Georges Quénot
  • Philippe Mulhem
  • Damien Paulin
  • Dinesh Kumar
  • Raghav Bhaskar
  • Arvind Bhusnurmath
Part of the Multimedia Systems and Applications Series book series (MMSA, volume 22)


Most of video databases are being converted into digital video archives or are now directly built as such. Being able to retrieve a document or a segment of a document corresponding to a given user need from these very large video databases is essential for their practical usability. This is a very difficult and challenging task especially when the type of user query is not known in advance. The most common way to solve this task is to index many different aspects of document contents from the “signal” level up to the “semantic” level. This includes for instance color and texture distributions (signal level) people detection and identification (semantic level), or speech transcription (intermediate level). Many of them have been integrated into the “Multimedia Content Description Interface” standard [MPEG-7, 2001, MPEG-7.3, 2001].


Optical Flow Camera Motion Mobile Object Camera Location Optical Flow Method 
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. [MPEG-7, 2001]
    Overview of the MPEG-7 standard. In ISO/IEC JTC1/SC29/WG11 N4031, Singapore, March 2001.Google Scholar
  2. [MPEG-7.3, 2001]
    Text of ISO/IEC 15938-3/FCD Information Technology — Multimedia Content Description Interface — Part 3 Visual. In ISO/IEC JTC1/SC29/WG11 N4062, Singapore, March 2001.Google Scholar
  3. [Kobla, 1996]
    Kobla V., Doermann D.S., Lin K-I. and Faloutsos C.: Compressed domain video indexing techniques using DCT and motion vector information in MPEG Video. In Proceedings of the SPIE conference on Storage and Retrieval for Image and Video Databases V, Volume 3022, pp. 200–211, 1996.Google Scholar
  4. [Nicolas, 2001]
    Nicolas H.: New Methods for Dynamic Mosaicing. In IEEE Transactions on Image Processing, 10(8), August 2001.Google Scholar
  5. [Irani, 1995]
    Irani M., Anandan P. and Hsu S.: Mosaic based representations of video sequences and their applications, In Proceedings of the International Conference on Computer Vision, pp 22–30, 1995.Google Scholar
  6. [Odone, 2000]
    Odone F., Fusiello A. and Trucco E.: Robust motion segmentation for content-based video coding. In Recherche d’ Information Assistée par Ordinateur, Paris, France, 12–14 Apr. 2000.Google Scholar
  7. [Poelman, 1993]
    Poelman C.J. and Kanade T.: A Paraperspective Factorization Method for Shape and Motion Recovery, tech. report CMU-CS-93-219, Computer Science Department, Carnegie Mel lon University, December, 1993.Google Scholar
  8. [Lin, 1999]
    Lin Y., Kankanhalli M. and Chua T.-S.: Temporal multi-resolution analysis for video segmentation, In ACM Multimedia Conference, 1999.Google Scholar
  9. [Aigrain, 1997]
    Aigrain P., Joly P. and Longueville V.,: Medium-Knowledge-Based Macro-Segmentation of Video into Sequences, In Intelligent Multimedia Information Retrieval, Ed. Mark MAYBURY, AAAI Press, MIT Press, pp 159–173, 1997Google Scholar
  10. [Aigrain, 1996]
    Aigrain P., Zhang H.J. and Petkovic D.,: Content-based representation and retrieval of visual media: a state-of-the-art review, In Multimedia Tools and Applications, 3(3): 179–202, November 1996Google Scholar
  11. [Boreczky, 1996]
    Boreczky J. S. and Rowe L. A.: Comparison of video shot boundary detection technique. In IS&T/SPIE Conference on Electronic Imaging Technology and Science, San Jose, USA, February 1996.Google Scholar
  12. [Lupatini, 1998]
    Lupatini G., Saraceno C. and Leonardi R.: Scene break detection: a comparison, In Proc. VIIIth Intern. Workshop on Research Issues in Data Engineering: Continuous-Media Databases and Applications, 34–41, Feb. 98.Google Scholar
  13. [Quénot, 2001]
    Quénot G.M.: TREC-10 Shot Boundary Detection Task: CLIPS System Description and Evaluation In Text Retrieval Conference, Gaithersburg, MD, November 2001.Google Scholar
  14. [Quénot, 1999]
    Quénot G.M. and Mulhem P.: Two systems for temporal video segmentation. In Content Based Multimedia Indexing, Toulouse, October 1999.Google Scholar
  15. [Nagasaka, 1991]
    Nagasaka A. and Tanaka Y.: Automatic Video Indexing and Full-Video Search for Objects Appearances, In 2nd Conference on Visual Database Systems, October 1991.Google Scholar
  16. [Zabih, 1995]
    Zabih R., Miller J. and Mai K.: Feature-Based Algorithms for Detecting and Classifying Scenes Breaks, In Third ACM Conference on Multimedia, USA, Nov. 1995.Google Scholar
  17. [Quénot, 1996]
    Quénot G.M.: Computation of Optical Flow Using Dynamic Programming. In IAPR Workshop on Machine Vision Applications, pp. 249–252, Tokyo, Japan, 12–14 Nov. 1996.Google Scholar
  18. [Barron, 1994]
    Barron J.L., Fleet D.J. and Beauchemin S.S., Performance of Optical Flow Techniques, In International Journal of Computer Vision, Vol. 12, No 1, pp. 43–77, 1994.Google Scholar
  19. [Quénot, 1992]
    Quénot G.M.: The “Orthogonal Algorithm” for Optical Flow Detection using Dynamic Programming, Proc. IEEE ICASSP-92, Vol III, pp. 249–252, San-Francisco, 23–36 March 1992.Google Scholar
  20. [Sakoe, 1978]
    Sakoe H. and Chiba S.: Dynamic Programming Optimization for Spoken Word Recognition, IEEE Trans. Acoust., Speech, and Signal Proc., Vol. ASSP-26, p.43, February 1978.Google Scholar
  21. [Huang, 1994]
    Huang T.S. and Netravali A.N.: Motion and structure from feature correspondences: A review. In Proceedings of IEEE, Vol. 82, No 2, pp 252–267, 1994.Google Scholar
  22. [Noble, 1988]
    Noble J.A.: Finding Corners, In Image and Vision Computing, Vol. 6, No 2, pp 121–128, 1988.Google Scholar
  23. [Tomasi, 1991]
    Tomasi C. and Kanade T.: Detection and Tracking of point features, Technical Report CMU-CS-91-132, Carnegie Mellon University, Pittsburg, PA, 1991.Google Scholar
  24. [Shi, 1994]
    Shi J. and Tomasi C.: Good features to track, In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 593–600, 1994.Google Scholar
  25. [Semple, 1952]
    Semple J.G. and Kneebone G.T.: Algebraic Projective Geometry, Oxford University Press, 1952.Google Scholar

Copyright information

© Springer Science+Business Media New York 2003

Authors and Affiliations

  • Georges Quénot
    • 1
  • Philippe Mulhem
    • 1
  • Damien Paulin
    • 1
  • Dinesh Kumar
    • 1
  • Raghav Bhaskar
    • 1
  • Arvind Bhusnurmath
    • 1
  1. 1.CLIPS-IMAGGrenoble Cedex 9France

Personalised recommendations