An Algorithm for Highlights Identification and Summarization of Broadcast Soccer Videos

  • Waldez Azevedo Gomes Junior
  • Díbio Leandro Borges
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7441)


This paper presents an algorithm that aims to perform automatic summarization in broadcast soccer videos. The summarization considers identifying and keeping only the highlights of the match. A situation that could be considered a highlight is defined as one with high convergence of players to a spot. Our approach considers velocities and positions of the players, and an inferred movement of the TV camera as basic features to be extracted. The movement of the TV cameras are approximated using the movement of all the players in the image. A motion field is computed over the image in order to analyze aspects of the match. The algorithm was tested with real data of a soccer match and results are promising considering the approach uses as input broadcast videos only, and it has no a priori knowledge of cameras positions or other fixed parameters.


Motion field analysis soccer video analysis video summarization 


  1. 1.
    Carr, J.C., et al.: Surface Interpolation with Radial Basis Functions for Medical Imaging. IEEE Transactions on Medical Imaging 16(1), 96–107 (1997)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Choi, K., Seo, Y.: Tracking Soccer Ball in TV Broadcast Video. In: Roli, F., Vitulano, S. (eds.) ICIAP 2005. LNCS, vol. 3617, pp. 661–668. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  3. 3.
    Choi, K., Seo, Y.: Probabilistic Tracking of the Soccer Ball. In: Comaniciu, D., Mester, R., Kanatani, K., Suter, D. (eds.) SMVP 2004. LNCS, vol. 3247, pp. 50–60. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  4. 4.
    Kim, K., et al.: Motion Fields to Predict Play Evolution in Dynamic Sport Scenes. In: Proceedings of CVPR 2010, pp. 840–847 (2010)Google Scholar
  5. 5.
    Seo, Y., et al.: Where are the Ball and the Players? Soccer Game Analysis with Color-based Tracking and Image Mosaick. In: Del Bimbo, A. (ed.) ICIAP 1997. LNCS, vol. 1311, pp. 196–203. Springer, Heidelberg (1997)CrossRefGoogle Scholar
  6. 6.
    Sgarbi, E., Borges, D.L.: Structure in Soccer Videos: Detecting and Classifying Highlights for Automatic Summarization. In: Sanfeliu, A., Cortés, M.L. (eds.) CIARP 2005. LNCS, vol. 3773, pp. 691–700. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  7. 7.
    Shi, J., Tomasi, C.: Good Features to Track. In: Proceedings of CVPR, pp. 593–600 (1994)Google Scholar
  8. 8.
    Mountney, P.: Tracking Football Players using Conditional Density Propagation. Master Thesis, University of Bristol UK (2003)Google Scholar
  9. 9.
    Wu, Y., Fan, J.: Contextual flow. In: Proceedings of CVPR, pp. 33–40 (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Waldez Azevedo Gomes Junior
    • 1
  • Díbio Leandro Borges
    • 1
  1. 1.Department of Computer ScienceUniversity of BrasiliaBrasíliaBrazil

Personalised recommendations