Advertisement

MPEG-2 Compressed-Domain Algorithms for Video Analysis

  • Wolfgang Hesseler
  • Stefan Eickeler
Open Access
Research Article
Part of the following topical collections:
  1. Information Mining from Multimedia Databases

Abstract

This paper presents new algorithms for extracting metadata from video sequences in the MPEG-2 compressed domain. Three algorithms for efficient low-level metadata extraction in preprocessing stages are described. The first algorithm detects camera motion using the motion vector field of an MPEG-2 video. The second method extends the idea of motion detection to a limited region of interest, yielding an efficient algorithm to track objects inside video sequences. The third algorithm performs a cut detection using macroblock types and motion vectors.

Keywords

Information Technology Vector Field Quantum Information Video Sequence Motion Vector 
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.

References

  1. 1.
    Manjunath BS, Salembier P, Sikora T: Introduction to MPEG-7: Multimedia Content Description Interface. John Wiley & Sons, New York, NY, USA; 2002.Google Scholar
  2. 2.
    Wang R, Huang T: Fast camera motion analysis in MPEG domain. Proceedings of IEEE International Conference on Image Processing (ICIP '99), October 1999, Kobe, Japan 3: 691-694.CrossRefGoogle Scholar
  3. 3.
    Smolic A, Hoeynck M, Ohm J-R: Low-complexity global motion estimation from P-frame motion vectors for MPEG-7 applications. Proceedings of IEEE International Conference on Image Processing (ICIP '00), September 2000, Vancouver, BC, Canada 2: 271-274.CrossRefGoogle Scholar
  4. 4.
    Kuhn PM: Camera motion estimation using feature points in MPEG compressed domain. Proceedings of IEEE International Conference on Image Processing (ICIP '00), September 2000, Vancouver, BC, Canada 3: 596-599.Google Scholar
  5. 5.
    Kobla V, Doermann D, Rosenfeld A: Compressed domain video segmentation. In Tech. Rep. CAR-TR-839 (CS-TR-3688). University of Maryland, College Park, Md, USA; 1996.Google Scholar
  6. 6.
    Comaniciu D, Meer P: Mean shift analysis and applications. Proceedings of 7th IEEE International Conference on Computer Vision (ICCV '99), September 1999, Kerkyra, Greece 2: 1197-1203.CrossRefGoogle Scholar
  7. 7.
    Danette Allen B, Bishop G: Tracking: Beyond 15 Minutes of Thought. SIGGRAPGH 2001 Course 11 Booklet, August 2001, Los Angeles, Calif, USAGoogle Scholar
  8. 8.
    Gyaourova A, Kamath C, Cheung S-C: Block matching for object tracking. In Tech. Rep. UCRL-TR-200271. Lawrence Livermore National Laboratory, Livermore, Calif, USA; 2003.Google Scholar
  9. 9.
    Kobla V, Doermann D, Lin K-I, Faloutsos C: Feature normalization for video indexing and retrieval. In Tech. Rep. CAR-TR-847 (CS-TR-3732). University of Maryland, College Park, Md, USA; 1996.Google Scholar
  10. 10.
    Khan JI, Guo Z, Oh W: Motion based object tracking in MPEG-2 stream for perceptual region discriminating rate transcoding. Proceedings of 9th ACM International Conference on Multimedia (ACM Multimedia '01), September–October 2001, Ottawa, Ontario, Canada 572-576.CrossRefGoogle Scholar
  11. 11.
    Zhang H, Kankanhalli A, Smoliar SW: Automatic partitioning of full-motion video. ACM Multimedia Systems 1993, 1(1):10-28. 10.1007/BF01210504CrossRefGoogle Scholar
  12. 12.
    Nagasaka A, Tanaka Y: Automatic video indexing and full-video search for object appearances. In Proceedings of IFIP 2nd Working Conference on Visual Database Systems, September–October 1991. North-Holland; 113-127.Google Scholar
  13. 13.
    Zabih R, Miller J, Mai K: A feature-based algorithm for detecting and classifying scene breaks. Proceedings of 3rd ACM International Conference on Multimedia (ACM Multimedia '95), November 1995, San Francisco, Calif, USA 189-200.CrossRefGoogle Scholar
  14. 14.
    Bozdagi G, Sencar HT: Preprocessing tool for compressed video editing. Proceedings of IEEE 3rd Workshop on Multimedia Signal Processing, September 1999, Copenhagen, Denmark 283-288.Google Scholar
  15. 15.
    Bovik A (Ed): Handbook of Image and Video Processing. Academic Press, New York, NY, USA; 2000.MATHGoogle Scholar
  16. 16.
    Calic J, Izquierdo E: Towards real-time shot detection in the MPEG-compressed domain. Proceedings of Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS '01), May 2001, Tampere, Finland 95-100.Google Scholar
  17. 17.
    Viola P, Jones MJ: Robust real-time object detection. In Tech. Rep. CRL 2001/01. Cambridge Research Laboratory, Cambridge, Mass, USA; 2001.Google Scholar
  18. 18.
    Chang S-F, Messerschmitt DG: Manipulation and compositing of MC-DCT compressed video. IEEE Journal on Selected Areas in Communications 1995, 13(1):1-11. 10.1109/49.363151CrossRefGoogle Scholar
  19. 19.
    Shen K, Delp EJ: A fast algorithm for video parsing using MPEG compressed sequences. Proceedings of IEEE International Conference on Image Processing (ICIP '95), October 1995, Washington, DC, USA 2: 252-255.CrossRefGoogle Scholar
  20. 20.
    Yeo B-L, Liu B: On the extraction of DC sequence from MPEG compressed video. Proceedings of IEEE International Conference on Image Processing (ICIP '95), October 1995, Washington, DC, USA 2: 260-263.CrossRefGoogle Scholar
  21. 21.
    Rowley HA, Baluja S, Kanade T: Neural network-based face detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 1998, 20(1):23-38. 10.1109/34.655647CrossRefGoogle Scholar
  22. 22.
    Wang H, Chang S-F: A highly efficient system for automatic face region detection in MPEG video. IEEE Transactions on Circuits and Systems for Video Technology 1997, 7(4):615-628. 10.1109/76.611173MathSciNetCrossRefGoogle Scholar

Copyright information

© Hesseler and Eickeler 2006

Authors and Affiliations

  1. 1.Fraunhofer IMKSankt AugustinGermany

Personalised recommendations