25 September 2003 Bayesian-network-based soccer video event detection and retrieval
Author Affiliations +
Proceedings Volume 5286, Third International Symposium on Multispectral Image Processing and Pattern Recognition; (2003) https://doi.org/10.1117/12.538784
Event: Third International Symposium on Multispectral Image Processing and Pattern Recognition, 2003, Beijing, China
Abstract
This paper presents an event based soccer video retrieval method, where the scoring even is detected based on Bayesian network from six kinds of cue information including gate, face, audio, texture, caption and text. The topology within the Bayesian network is predefined by hand according to the domain knowledge and the probability distributions are learned in the case of the known structure and full observability. The resulting event probability from the Bayesian network is used as the feature vector to perform the video retrieval. Experiments show that the true and false detection rations for the scoring event are about 90% and 16.67% respectively, and that the video retrieval result based on event is superior to that based on low-level features in the human visual perception.
© (2003) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xinghua Sun, Xinghua Sun, Guoying Jin, Guoying Jin, Mei Huang, Mei Huang, Guangyou Xu, Guangyou Xu, } "Bayesian-network-based soccer video event detection and retrieval", Proc. SPIE 5286, Third International Symposium on Multispectral Image Processing and Pattern Recognition, (25 September 2003); doi: 10.1117/12.538784; https://doi.org/10.1117/12.538784
PROCEEDINGS
6 PAGES


SHARE
RELATED CONTENT

Developing power tools for video indexing and retrieval
Proceedings of SPIE (March 31 1994)
Human body posture recognition using MPEG-7 descriptors
Proceedings of SPIE (January 17 2004)
Semantic filtering of video content
Proceedings of SPIE (December 31 2000)
Automatic home video abstraction using audio contents
Proceedings of SPIE (August 29 2002)
Semantic video indexing using context-dependent fusion
Proceedings of SPIE (January 27 2008)

Back to Top