Audio-Based Event Detection for Sports Video

  • Mark Baillie
  • Joemon M. Jose
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2728)


In this paper, we present an audio-based event detection approach shown to be effective when applied to the Sports broadcast data. The main benefit of this approach is the ability to recognise patterns that indicate high levels of crowd response which can be correlated to key events. By applying Hidden Markov Model-based classifiers, where the predefined content classes are parameterised using Mel-Frequency Cepstral Coefficients, we were able to eliminate the need for defining a heuristic set of rules to determine event detection, thus avoiding a two-class approach shown not to be suitable for this problem. Experimentation indicated that this is an effective method for classifying crowd response in Soccer matches, thus providing a basis for automatic indexing and summarisation.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Y.L. Chang, W. Zeng, I. Kamel, and R. Alonso. Integrated image and speech analysis for content-based video indexing. In ICMCS, pages 306–313. IEEE, 1996.Google Scholar
  2. [2]
    D. Keislar E. Wold, T. Blum and J. Wheaton. Content-based classification, search, and retrieval of audio. In In IEEE Multimedia, volume 3, pages 27–36. IEEE, 1996.CrossRefGoogle Scholar
  3. [3]
    Y. Gong, T. S. Lim, and H.C. Chua. Automatic parsing of tv soccer programs. In ICMCS, pages 167–174, Washington DC, May 1995.Google Scholar
  4. [4]
    TiVo Inc. Last visited 24th April 2003.Google Scholar
  5. [5]
    S. Intille and A. Bobick. Visual tracking using closed worlds. Technical report, MIT Media Laboratory, 1995. intille/.Google Scholar
  6. [6]
    A.K. Jain, R.P.W. Duin, and J. Mao. Statistical pattern recognition: A review. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(1):4–37, January 2000.CrossRefGoogle Scholar
  7. [7]
    J.P. Cambell Jnr. Speaker recognition: A tutorial. In Proceedings of the IEEE, volume 85, pages 1437–1462, September 1997.CrossRefGoogle Scholar
  8. [8]
    J. Kittler, K. Messer, W. Christmas, B Levienaise-Obadia, and D. Koubaroulis. Generation of semantic cues for sports video annotation. In ICIP, pages 26–29, Thessaloniki, Greece, October 2001.Google Scholar
  9. [9]
    K. Kobla, D. Doermann, and D. DeMenthon. Identification of sports videos using replay, text, and camera motion features. In Conference on Storage and Retrieval for Media Databases, volume 3972, pages 332–343. SPIE, January 2000.Google Scholar
  10. [10]
    C. Li and G. Biswas. A bayesian approach to temporal data clustering using hidden markov models. In ICML, pages 543–550, Stanford, California, 2000.Google Scholar
  11. [11]
    M. R. Naphade, A. Garg, and T. S. Huang. Duration dependent input output markov models for audio-visual event detection. In ICME, Tokyo, Japan, August 2001. IEEE.Google Scholar
  12. [12]
    OPTA. Last visited 24th April 2003.Google Scholar
  13. [13]
    D. Pye. Content-based methods for the management of digital music. In ICASSP, volume IV, pages 2437–2400, 2000.Google Scholar
  14. [14]
    L. Rabiner and B.H. Juang. Fundamentals of Speech Recognition. Prentice Hall, Englewood Cliffs, NJ, USA, 1993.Google Scholar
  15. [15]
    Y. Rui, A. Gupta, and A. Acero. Automatically extracting highlights for tv baseball programs. In ACM Multimedia, pages 105–115, LA, 2000.Google Scholar
  16. [16]
    Sky+. Last visited 24th April 2003.Google Scholar
  17. [17]
    P. van Beek, H. Pan, and M. I. Sezan. Detection of slow-motion replay segments in sports video for highlights generation. In ICASSP, Utah, May 7–11 2001.Google Scholar
  18. [18]
    Y. Wang, Z. Liu, and J. Huang. Multimedia content analysis using both audio and visual clues. In IEEE Signal Processing Magazine, volume 17, pages 12–36. 2000.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Mark Baillie
    • 1
  • Joemon M. Jose
    • 1
  1. 1.Department of Computing ScienceUniversity of GlasgowGlasgowUK

Personalised recommendations