A Novel Sports Video Logo Detector Based on Motion Analysis

  • Hongliang Bai
  • Wei Hu
  • Tao Wang
  • Xiaofeng Tong
  • Changping Liu
  • Yimin Zhang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4233)


Replays are key cues for events detection in sport videos since they are the immediate consequence of highlights or important events happened in sports. In many sports videos, replays are usually sandwiched with two identical logo transitions, prompt the beginning and end of a replay. A logo transition is a kind of special digital video effects, usually contains 12-35 consecutive frames, describe a flying or variable object. In this paper, a novel automatic logo detection approach is proposed. It contains two main stages: a logo transition template is automatically learned by dynamic programming and unsupervised clustering, a key frame is also extracted; then the extracted key frame and the learned logo template are used jointly to detect logos in sports videos. The optical flow features are used to depict the motion characteristics of the logo transitions. Experiments on different types of sports videos show that the proposed approach can reliably detect logos in sports videos efficiently.


Gaussian Mixture Model Logo Sequence Detection Stage Sport Video Table Tennis 
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. 1.
    Nepal, S., Srinivasan, U., Reynolds, G.: Automatic detection of ’goal’ segments in basketball videos. In: Proceedings of the ninth ACM international conference on Multimedia, pp. 261–269 (2001)Google Scholar
  2. 2.
    Tjondronegoro, D., Chen, Y.P.P., Pham, B.: The power of play-break for automatic detection and browsing of self-consumable sport video highlights. In: ACM SIGMM, pp. 267–274 (2004)Google Scholar
  3. 3.
    Kobla, V., DeMenthon, D., Doermann, D.: Detection of slow-motion replays for identifying sports videos. In: Proceedings of IEEE Workshop on Multimedia Signal Processing, pp. 135–140 (1999)Google Scholar
  4. 4.
    Pan, H., Van Beek, P., Sezan, M.: Detection of slow-motion replay segments in sports video for highlights generation. In: ICASSP, pp. 1649–1652 (2001)Google Scholar
  5. 5.
    Wang, L., Liu, X., Lin, S., Xu, G., Shum, H.Y.: Generic slow-motion replay detection in sports video. In: ICIP, pp. 1585–1588 (2004)Google Scholar
  6. 6.
    Pan, H., Li, B., Sezan, M.I.: Automatic detection of replay segments in broadcast sports programs by detection of logos in scene transitions. In: ICASSP, pp. 3385–3388 (2002)Google Scholar
  7. 7.
    Duan, L.Y., Xu, M., Tian, Q., Xu, C.S.: Mean shift based video segment representation and applications to replay detection. In: ICASSP, pp. 709–712 (2004)Google Scholar
  8. 8.
    Tong, X., Lu, H., Liu, Q., Jin, H.: Replay detection in broadcasting sports video. In: Proceedings - Third International Conference on Image and Graphics, pp. 337–340 (2004)Google Scholar
  9. 9.
    Yuan, J., Zhang, W., et al.: Tsinghua university at trecvid2004: Shot boundary detection and high-level feature extraction. In: TRECVID Workshops (2004)Google Scholar
  10. 10.
    Horn, B.K.P., Schunck, B.G.: Determining optical flow. Artificial Intelligence 17(1-3), 185–203 (1981)CrossRefGoogle Scholar
  11. 11.
  12. 12.
    Needleman, S.B., Wunsch, C.D.: An efficient method applicable to the search for similarities in the amino acid sequences of two proteins. Journal of Molecular Biology 48, 444–453 (1970)CrossRefGoogle Scholar
  13. 13.
    Sellers, P.H.: An algorithm for the distance between two finite sequences. Journal of Combinatorial Theory A16, 253–258 (1974)MathSciNetGoogle Scholar
  14. 14.
    Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the em algorithm. Journal of Royal Statistical Society 39B, 1–38 (1977)MathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Hongliang Bai
    • 1
  • Wei Hu
    • 2
  • Tao Wang
    • 2
  • Xiaofeng Tong
    • 2
  • Changping Liu
    • 3
  • Yimin Zhang
    • 2
  1. 1.Graduate SchoolChinese Academy of Sciences, Automation of Institute 
  2. 2.Intel China Research Center 
  3. 3.Automation of InstituteChinese Academy of Sciences 

Personalised recommendations