Title :
Automatic sports classification
Author :
Messer, Kieron ; Christmas, William ; Kittler, Josef
Author_Institution :
Surrey Univ., Guildford, UK
Abstract :
ASSAVID is an EU sponsored project which is concerned with the development of a system for the automatic segmentation and semantic annotation of sports video. We describe the method which automatically classifies unknown sports video into the type of sport being played. This is an important task if a fully automatic sports video logging process is to be realised. The proposed technique relies upon the concept of "cues" which attach semantic meaning to low-level features computed on the video. Experimental results on sports video provided by the BBC demonstrate that this method is working well.
Keywords :
image classification; image segmentation; sport; video databases; ASSAVID; EU sponsored project; automatic sports classification; cues; experimental results; image segmentation; semantic annotation; semantic meaning; sports video; sports video logging process; video database; Broadcasting; Computer vision; Databases; Engines; Feeds; Information analysis; Layout; Multimedia communication; Production systems; Video compression;
Conference_Titel :
Pattern Recognition, 2002. Proceedings. 16th International Conference on
Print_ISBN :
0-7695-1695-X
DOI :
10.1109/ICPR.2002.1048475