Abstract An approach to user-orientated sports highlights extraction is proposed based on video excitement time curve. Firstly, some low-level features are extracted from visual and audio information and mapped into users excitement. Then, the excitement time curve of the whole video is computed. Next, the position and the length of each highlight are determined, and all highlights are ranked on the proposed concept of importance-level of highlights. Finally, all highlights are exhibited in a friendly user-interface. Experimental results show the proposed approach can effectively detect most sport video from users' perspective.
[1] Dian T, Chen Y P P, Pham B. Integrating Highlights for More Complete Sports Video Summarization. IEEE Trans on Multimedia, 2004, 11(4): 22-37 [2] Truong B T, Venkatesh S. Video Abstraction: A Systematic Review and Classification. ACM Trans on Multimedia Computing, Communication and Applications, 2007, 3(1): 1-37 [3] Otsuka I, Nakane K, Divakaran A, et al. A Highlight Scene Detection and Video Summarization System Using Audio Feature for a Personal Video Recorder. IEEE Trans on Consumer Electronics, 2005, 511(1):112-116 [4] Babaguchi N, Kawai Y, Ogura T, et al. Personalized Abstraction of Broadcasted American Football Video by Highlight Selection. IEEE Trans on Multimedia, 2004, 6(4): 575-586 [5] Sang H J, Song M Y, Cho H J. Semantic Classification of Sports News Video Using Color and Motion Features // Proc of the International Conference on Hybrid Information Technology. Cheju Island, Korea, 2006: 745-750 [6] Cheng C C, Hsu C T. Fusion of Audio and Motion Information on HMM-Based Highlight Extraction for Baseball Games. IEEE Trans on Multimedia, 2006, 8(3): 585-599 [7] Kolekar M H, Sengupta S. Event-Importance Based Customized and Automatic Cricket Highlight Generation // Proc of the IEEE International Conference on Multimedia and Expo. Toronto, Canada, 2006: 1617-1620 [8] Snoek C G M, Worring M. Multimodal Video Indexing: A Review of the State-of-Art. Multimedia Tools and Applications, 2005, 25(1): 5-35 [9] Zhao Zhao, Jiang Shuqiang, Huang Qingming, et al. Highlight Summarization in Sports Video Based on Replay Detection // Proc of the IEEE International Conference on Multimedia and Expo. Toronto, Canada, 2006: 1613-1616 [10] Li Baoxin, Errico J H, Pan Hao, et al. Bridging the Semantic Gap in Sports Video Retrieval and Summarization. Journal of Visual Communication and Image Representation, 2004, 15(3): 393-424 [11] Ma Yufei, Hua Xiaosheng, Lu Lei, et al. A Generic Framework of User Attention Model and Its Application in Video Summarization. IEEE Trans on Multimedia, 2005, 7(5): 907-919 [12] Snoek C G M, Worring M, Dennis C K, et al. A Learned Lexicon-Driven Paradigm for Interactive Video Retrieval. IEEE Trans on Multimedia, 2007, 9(2): 280-292 [13] Yoo H W, Cho S B. Video Scene Retrieval with Interactive Genetic Algorithm. Multimedia Tools and Applications, 2007, 34(3): 317-336 [14] Alan H, Xu Liqun. Affective Video Content Representation and Modeling. IEEE Trans on Multimedia, 2005, 7(1): 143-154 [15] Wang H L, Cheong L F. Affective Understanding in Film. IEEE Trans on Circuits and Systems for Video Technology, 2006, 16(6): 689-704 [16] Hanjalic A. Adaptive Extraction of Highlights from a Sport Video Based on Excitement Modeling. IEEE Trans on Multimedia, 2005, 7(6): 1114-1122 [17] Wu Wei, Fan Yingle, Pang Quan. A Speech Endpoint Detection Method Based on the Feature Distance of Generalized Dimension. Journal of Electronics & Information Technology, 2007, 29(2): 465-468 (in Chinese) (武 薇,范影乐,庞 全.基于广义维数距离的语音端点检测方法.电子与信息学报, 2007, 29(2): 465-468) [18] Geng Yuliang, Xu De, Feng Songhe. A Rapid and Effective Method for Shot Boundary Detection. Acta Electronica Sinica, 2006, 34(12): 2272-2277 (in Chinese) (耿玉亮,须 德,冯松鹤.一种快速有效的视频镜头边界检测方法.电子学报, 2006, 34(12): 2272-2277) [19] Liu Tianming, Zhang Hongjiang, Qi Feihu. A Novel Video Key-Frame-Extraction Algorithm Based on Perceived Motion Energy Model. IEEE Trans on Circuits and Systems for Video Technology, 2003, 13(10):1006-1013
2008, Vol. 21 
