Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICME.2005.1521653
Title: Fusion of multiple asynchronous information sources for event detection in soccer video
Authors: Xu, H.
Fong, T.-H.
Chua, T.-S. 
Issue Date: 2005
Source: Xu, H.,Fong, T.-H.,Chua, T.-S. (2005). Fusion of multiple asynchronous information sources for event detection in soccer video. IEEE International Conference on Multimedia and Expo, ICME 2005 2005 : 1242-1245. ScholarBank@NUS Repository. https://doi.org/10.1109/ICME.2005.1521653
Abstract: Our previous research shows that the use of multiple sources of information based on intrinsic AV features and external knowledge helps to detect events in soccer video. To make the system scalable, we process each source of information independently before fusing the detection results. The fusion of results is vital to the success under this architecture. However, this fusion problem is unique in that the detection results in terms of likelihood values to be fused are asynchronous. Thus, the fusion scheme has to determine which likelihood values are corresponding as well as the final likelihood. This paper formulates three fusion schemes, namely, rule-based scheme, aggregation and Bayesian inference, and studies their properties. Our results show that Bayesian inference has the best capabilities to tackle asynchronism. © 2005 IEEE.
Source Title: IEEE International Conference on Multimedia and Expo, ICME 2005
URI: http://scholarbank.nus.edu.sg/handle/10635/42076
ISBN: 0780393325
DOI: 10.1109/ICME.2005.1521653
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

12
checked on Dec 13, 2017

Page view(s)

43
checked on Dec 16, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.