Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/13136
Title: Integrated analysis of audiovisual signals and external information sources for event detection in team sports video
Authors: XU HUAXIN
Keywords: Event Detection, Sports Video Analysis, Fusion
Issue Date: 28-Apr-2008
Source: XU HUAXIN (2008-04-28). Integrated analysis of audiovisual signals and external information sources for event detection in team sports video. ScholarBank@NUS Repository.
Abstract: Audiovisual signals and external information sources (news reports, live commentaries, Web casts, etc.) are found to have complementary strengths for detecting events in sports video. This thesis reports research on integrated analysis of them, focusing on tackling the asynchronism between them. The thesis presents a template domain model which adapts to different games and keeps the system design stable. Based on this domain model, two frameworks , namely the late and early fusion are developed to perform integrated analysis. Key findings are (a) integrated analysis outperforms analysis of any single source of information; (b) both frameworks are capable of handling asynchronism and give acceptable results, however the late fusion framework gives higher accuracy as it represents the domain knowledge better.
URI: http://scholarbank.nus.edu.sg/handle/10635/13136
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Thesis_XU_Huaxin_HT016894E.pdf1.24 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

195
checked on Dec 11, 2017

Download(s)

214
checked on Dec 11, 2017

Google ScholarTM

Check


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