A Rule-Based Sports Video Event Detection Method

Video event detection is an important research topic in semantic video content analysis and it aims to locate the position where events are happening. A rule- based sports video analysis method is proposed in this paper. It combines structural analysis and semantic tagging to generate the video events positions. Experiments based on real-world sports video verify the effectiveness of the proposed method. Keyword: feature extraction; slow motion; rule

[1]  Aggelos K. Katsaggelos,et al.  Abnormal Event Detection from Surveillance Video by Dynamic Hierarchical Clustering , 2007, 2007 IEEE International Conference on Image Processing.

[2]  Shiqiang Yang,et al.  Motion based event recognition using HMM , 2002, Object recognition supported by user interaction for service robots.

[3]  Chung-Lin Huang,et al.  Semantics-based highlight extraction of soccer program using DBN , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[4]  Chih-Wen Su,et al.  Real-time event detection and its application to surveillance systems , 2006, 2006 IEEE International Symposium on Circuits and Systems.