Chinese Journal of Computers   Full Text
Title	A Survey on Sports Video Analysis
Authors	TONG Xiao-Feng LIU Qing-Shan LU Han-Qing
Address	(National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190)
Year	2008
Issue	No.7(1242—1251)
Abstract &   Background	Abstract Sports video is a hot research topic for its wide viewer-ship and enormous application potential in recent years. This paper gives a review of relative research work including low-level feature extraction, mid-level keyword generation, high-level semantics inference, relative applications and system prototypes, and finally indicates potential trend. Keywords sports video analysis； semantic inference； event detection； video summarization； feature extraction Background This paper gives a survey on sports video analysis, including the important ideas, algorithms, research roadmap, achievements and possible trends. This work was supported by the National Natural Science Foundation of China with title "Sports Video Analysis Based on Semantic Events" (grant No.60475010). Sports video analysis has attracted much attention of academic and industry researchers. Its applications are somehow definite and wide-range, but involve many domains, for examples, video and audio processing, information fusion, pattern recognition and semantics inference, communication, algorithm parallelism, etc. The National Lab of Pattern Recognition of CASIA has devoted much effort in this topic. The work involves with low-level feature extraction, middle-level key-words detection, and high-level event detection. The project team has published about 20 papers, applied for 1 patent, and 1 registration of computer software copyright.