Multimodal Automatic Indexing for Broadcast Soccer Video

  • Naoki Uegaki
  • Masao Izumi
  • Kunio Fukunaga
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3540)


In this paper, we propose a novel method for estimating major soccer scenes from cameraworks and players trajectories based on probabilistic inference, and annotating scene indexes to broadcast soccer videos automatically. In our method, we define relations between cameraworks and scenes, and between players trajectories and scenes by conditional probabilities. Moreover defining temporal relations of scenes by transition probabilities, we represent those relations as dynamic bayesian networks (DBNs). And those probabilities are evaluated by learning parameters of the networks. After extracting the cameraworks and the players trajectories, we compute the posterior probability distribution of scenes, and give the computed results to the soccer video as the scene index. Finally, we discuss the extendibility of the proposal indexing technique in the case of adding ball trajectories and audios.


  1. 1.
    Leonardi, R., Migliorati, P.: Semantic Indexing of Multimedia Documents. In: IEEE Multimedia, pp. 44–51 (April-June 2002)Google Scholar
  2. 2.
    Xinghua, S., Guoying, J., Mei, H., Guangyou, X.: Bayesian network based soccer video event detection and retrieval. In: Proceedings of SPIE - The International Society for Optical Engineering, vol. 5286, pp. 71–76 (2003)Google Scholar
  3. 3.
    Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach, 2nd edn., ch. 15, pp. 537–581. Prentice Hall, Englewood Cliffs (2002)Google Scholar
  4. 4.
    Murphy, K.P.: Dynamic Bayesian Networks: Representation, Inference and Learning. PhD thesis, University of California (2002)Google Scholar
  5. 5.
    Assfalg, J., Bertini, M., Colombo, C., Del Bimbo, A.: Semantic Annotation of Sports Videos. In: IEEE Multimedia, pp. 52–60 (April-June 2002)Google Scholar
  6. 6.
    Uegaki, N., Nakatsuji, K., Izumi, M., Fukunaga, K.: Automatic indexing for broadcast soccer video using multiple information. In: MIRU 2004, pp. II-329–334 (July 2004) (in Japanese) Google Scholar
  7. 7.
    Nakatsuji, K., Uegaki, N., Izumi, M., Fukunaga, K.: Estimation of Players’ Position from Image Sequences of Soccer Game TV Program, IEICE Technical Report, PRMU2003-214, pp. 95-100 (January 2004) (in Japanese)Google Scholar
  8. 8.
    Uegaki, N., Nakatsuji, K., Izumi, M., Fukunaga, K.: Tracking of Multiple Players from Soccer Game TV Programs. In: IEICE General Conference, vol. D-12-112, p. 273 (March 2003) (in Japanese) Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Naoki Uegaki
    • 1
  • Masao Izumi
    • 1
  • Kunio Fukunaga
    • 1
  1. 1.Osaka Prefecture UniversitySakai, OsakaJapan

Personalised recommendations