Please use this identifier to cite or link to this item: https://doi.org/10.1145/1386352.1386416
Title: An instant semantics acquisition system of live soccer video with application to live event alert and on-the-fly language selection
Authors: Yu, X.
Yan, X.
Li, L.
Leong, H.W. 
Keywords: Gamelog
Icon-based input
Instant semantics acquisition
Live event alert
On-the-fly language selection
Sports video
Issue Date: 2008
Source: Yu, X.,Yan, X.,Li, L.,Leong, H.W. (2008). An instant semantics acquisition system of live soccer video with application to live event alert and on-the-fly language selection. CIVR 2008 - Proceedings of the International Conference on Content-based Image and Video Retrieval : 495-504. ScholarBank@NUS Repository. https://doi.org/10.1145/1386352.1386416
Abstract: Automatic indexing of recorded sports video is a hard problem, even more so for live sports video, though a lot of advances have been achieved in the recent years. This paper presents a semiautomatic instant semantics generation system of live soccer video and its two applications: live event alert and instant semantics embedding. A key technical challenge of building the proposed system is how to acquire the desired semantics in a very short time lag. To confront this challenge, we develop a threechannel approach to accurately and quickly acquire semantics. The three channels are (1) developing the tool for inputting gamelog, (2) signal communication for getting commands of referee and director, and (3) video analysis for finding event boundary. The proposed system requires only a very small amount of manual work to operate gamelog acquisition tool using an icon-based interface for entering event log. Experimental results show that our system can quickly obtain the semantics of live soccer video, alert live events with a very small latency, and embed semantics into broadcasting video with a short time lag. Copyright 2008 ACM.
Source Title: CIVR 2008 - Proceedings of the International Conference on Content-based Image and Video Retrieval
URI: http://scholarbank.nus.edu.sg/handle/10635/41488
ISBN: 9781605580708
DOI: 10.1145/1386352.1386416
Appears in Collections:Staff Publications

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

SCOPUSTM   
Citations

3
checked on Dec 13, 2017

Page view(s)

56
checked on Dec 16, 2017

Google ScholarTM

Check

Altmetric


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