Exciting event detection in broadcast soccer video with mid-level description and incremental learning

ABSTRACT

In this paper, we propose a method for exciting event detection in broadcast soccer video with mid-level description and SVM-based incremental learning. In the method, video frames are firstly classified and grouped into views in terms of low-level playfield features. Mid-level description including view label, motion descriptor and shot descriptor are then extracted to present the characteristics of a view. By using the fixed temporal structure of views, SVM classification models are constructed to detected exciting events in a soccer match. In the view classification and event detection procedures, SVM-based incremental learning method is explored to improve the extensibility of view classification and event detection. Experiments on real soccer video programs demonstrate encouraging results.

REFERENCES

• 1: H. Pan, P. Van Beek and M.I. Sezan. "Detection of slow-motion replay segments in sports video for highlights generation," In Proc. IEEE ICASSP 2001.
• 2: Hanjalic, "Generic approach to highlights extraction from a sport video," ICIP 2003.
• 3: E.A. Murat Tekalp and A. M. Tekalp, "Generic play-break event detection for summarization and hierarchical sports video analysis," to appear in Proc. IEEE ICME 2003.
• 4: Ling-Yu Duan , Min Xu , Tat-Seng Chua , Qi Tian , Chang-Sheng Xu, A mid-level representation framework for semantic sports video analysis, Proceedings of the eleventh ACM international conference on Multimedia, November 02-08, 2003, Berkeley, CA, USA [doi>10.1145/957013.957020]
• 5: N. Babaguchi, Y.Kawai, T. Kitahashi, "Event Based Indexing of Broadcasted Sports Video by Intermodal Collaboration," IEEE Trans. On Multimedia 2002.
• 6: Surya Nepal , Uma Srinivasan , Graham Reynolds, Automatic detection of 'Goal' segments in basketball videos, Proceedings of the ninth ACM international conference on Multimedia, September 30-October 05, 2001, Ottawa, Canada [doi>10.1145/500141.500181]
• 7: Chua Hock Chuan, Automatic Parsing of TV Soccer Programs, Proceedings of the International Conference on Multimedia Computing and Systems, p.167, May 15-18, 1995 [doi>10.1109/MMCS.1995.484921]
• 8: Lexing Xie , Peng Xu , Shih-Fu Chang , Ajay Divakaran , Huifang Sun, Structure analysis of soccer video with domain knowledge and hidden Markov models, Pattern Recognition Letters, v.25 n.7, p.767-775, May 2004 [doi>10.1016/j.patrec.2004.01.005]
• 9: E.A. Murat Tekalp, and R. Mehrotra, "Automatic soccer video analysis and summarization," IEEE Trans. on Image Process, Volume: 12, Issue: 7, July 2003
• 10: R. Leonardi, P. Migliorati, and M. Prandini,"Semantic indexing of soccer audio-visual sequences: a multimodal approach based on controlled Markov chains," IEEE Trans on CSVT 2004 Vol.14, No.5.
• 11: Jürgen Assfalg , Marco Bertini , Carlo Colombo , Alberto Del Bimbo , Walter Nunziati, Semantic annotation of soccer videos: automatic highlights identification, Computer Vision and Image Understanding, v.92 n.2-3, p.285-305, November/December 2003 [doi>10.1016/j.cviu.2003.06.004]
• 12: Y. Liu, S.Q. Jiang, Q.X. Ye, W. Gao, and Q.M. Huang, "Playfield Detection Using Adaptive GMM and Its Application," ICASSP2004.
• 13: Ling-Yu Duan , Min Xu , Tat-Seng Chua , Qi Tian , Chang-Sheng Xu, A mid-level representation framework for semantic sports video analysis, Proceedings of the eleventh ACM international conference on Multimedia, November 02-08, 2003, Berkeley, CA, USA [doi>10.1145/957013.957020]
• 14: Y. Liu, W. Zeng, W. Q. Wang, W. Gao, "A Novel Compressed domain Shot Segmentation Algorithm on H.264/AVC," Accepted by ICIP 2004.
• 15: G. Cauwenberghs, G. and T. Poggio. "Incremental and Decremental Support Vector Machine Learning," In: Advances in Neural Information Processing Systems, MIT Press, Vol. 13, 409--415, Cambridge, MA, 2001.

INDEX TERMS

General Terms:
Algorithms, Experimentation

Keywords:
exciting event detection, sports video analysis