Title :
Research and develope of badminton sports video retrieval system
Author :
Li, Xiaoyan ; Li, Wei ; Qi, Xiang
Author_Institution :
State Key Lab. of Virtual Reality Technol. & Syst., Beihang Univ., Beijing, China
Abstract :
Content-based sports video retrieval becomes an important branch of multimedia retrieval which is free from traditional manual text labeling. A content-based retrieval system of Badminton sports video based on visual feature is researched and developed in this paper. A Badminton video is first automatically segmented into many sub-clips based on visual features, and then similar video clips can be obtained using sliding sub-clip window algorithm and matching function, among these sub-clips, similar video clips are ranked by a sorting model. The experimental results showed that our system could effectively and efficiently retrieve similar Badminton sports video corresponding with a query clip.
Keywords :
content-based retrieval; feature extraction; image segmentation; multimedia computing; sport; text analysis; video retrieval; content-based sports video retrieval; manual text labeling; matching function; multimedia retrieval; query clip; sliding subclip window algorithm; sorting model; video clips; visual feature-based badminton sports video retrieval system; visual features-based subclips; Databases; Feature extraction; Image segmentation; Visualization; content-based video retrieval; ranking model; sliding window;
Conference_Titel :
Computer Science and Network Technology (ICCSNT), 2011 International Conference on
Conference_Location :
Harbin
Print_ISBN :
978-1-4577-1586-0
DOI :
10.1109/ICCSNT.2011.6182331
