No Cover Image

Journal article 550 views

Automated 3-D Animation From Snooker Videos With Information-Theoretical Optimization

Richard Jiang, Matthew L. Parry, Phillip A. Legg, David H. S. Chung, Iwan Griffiths

IEEE Transactions on Computational Intelligence and AI in Games, Volume: 5, Issue: 4, Pages: 337 - 345

Swansea University Author: Iwan Griffiths

Full text not available from this repository: check for access using links below.

DOI (Published version): 10.1109/TCIAIG.2013.2275164

Abstract

Automated 3-D modeling from real sports videos can provide valuable resources for visual design in sports-related computer games, saving a lot of effort in manual design of visual features. However, image-based 3-D reconstruction often suffers from inaccuracies caused by statistic image analysis. In...

Full description

Published in: IEEE Transactions on Computational Intelligence and AI in Games
Published: 2013
URI: https://cronfa.swan.ac.uk/Record/cronfa27696
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2016-05-06T01:16:02Z
last_indexed 2018-02-09T05:11:04Z
id cronfa27696
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2016-05-05T10:52:00.3188898</datestamp><bib-version>v2</bib-version><id>27696</id><entry>2016-05-05</entry><title>Automated 3-D Animation From Snooker Videos With Information-Theoretical Optimization</title><swanseaauthors><author><sid>2ed2cc8d3dff635184def8d15afa21a9</sid><firstname>Iwan</firstname><surname>Griffiths</surname><name>Iwan Griffiths</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2016-05-05</date><deptcode>STSC</deptcode><abstract>Automated 3-D modeling from real sports videos can provide valuable resources for visual design in sports-related computer games, saving a lot of effort in manual design of visual features. However, image-based 3-D reconstruction often suffers from inaccuracies caused by statistic image analysis. In this paper, we propose an information-theoretical scheme to minimize errors of automated 3-D modeling from monocular sports videos. In the proposed scheme, mutual information (MI) was exploited to compute the fitting scores of a 3-D model against the observed single-view scene, and the optimization of model fitting was carried out subsequently. With this optimization scheme, errors in model fitting were minimized without human intervention, allowing automated reconstruction of 3-D animation from consecutive monocular video frames at high accuracy. In our work, the Snooker videos were taken as our case study, balls were positioned in 3-D space from single-view frames, and 3-D animation was reproduced from real Snooker videos. Our experimental results validated that the proposed information-theoretical scheme can assist in attaining better accuracy in the automated reconstruction of 3-D animation, and demonstrated that information-theoretical evaluation can be an effective approach for model-based reconstruction from single-view videos</abstract><type>Journal Article</type><journal>IEEE Transactions on Computational Intelligence and AI in Games</journal><volume>5</volume><journalNumber>4</journalNumber><paginationStart>337</paginationStart><paginationEnd>345</paginationEnd><publisher/><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords>video modelling animation three-dimensional</keywords><publishedDay>31</publishedDay><publishedMonth>12</publishedMonth><publishedYear>2013</publishedYear><publishedDate>2013-12-31</publishedDate><doi>10.1109/TCIAIG.2013.2275164</doi><url/><notes/><college>COLLEGE NANME</college><department>Sport and Exercise Sciences</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>STSC</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2016-05-05T10:52:00.3188898</lastEdited><Created>2016-05-05T10:52:00.3188898</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Sport and Exercise Sciences</level></path><authors><author><firstname>Richard</firstname><surname>Jiang</surname><order>1</order></author><author><firstname>Matthew L.</firstname><surname>Parry</surname><order>2</order></author><author><firstname>Phillip A.</firstname><surname>Legg</surname><order>3</order></author><author><firstname>David H. S.</firstname><surname>Chung</surname><order>4</order></author><author><firstname>Iwan</firstname><surname>Griffiths</surname><order>5</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2016-05-05T10:52:00.3188898 v2 27696 2016-05-05 Automated 3-D Animation From Snooker Videos With Information-Theoretical Optimization 2ed2cc8d3dff635184def8d15afa21a9 Iwan Griffiths Iwan Griffiths true false 2016-05-05 STSC Automated 3-D modeling from real sports videos can provide valuable resources for visual design in sports-related computer games, saving a lot of effort in manual design of visual features. However, image-based 3-D reconstruction often suffers from inaccuracies caused by statistic image analysis. In this paper, we propose an information-theoretical scheme to minimize errors of automated 3-D modeling from monocular sports videos. In the proposed scheme, mutual information (MI) was exploited to compute the fitting scores of a 3-D model against the observed single-view scene, and the optimization of model fitting was carried out subsequently. With this optimization scheme, errors in model fitting were minimized without human intervention, allowing automated reconstruction of 3-D animation from consecutive monocular video frames at high accuracy. In our work, the Snooker videos were taken as our case study, balls were positioned in 3-D space from single-view frames, and 3-D animation was reproduced from real Snooker videos. Our experimental results validated that the proposed information-theoretical scheme can assist in attaining better accuracy in the automated reconstruction of 3-D animation, and demonstrated that information-theoretical evaluation can be an effective approach for model-based reconstruction from single-view videos Journal Article IEEE Transactions on Computational Intelligence and AI in Games 5 4 337 345 video modelling animation three-dimensional 31 12 2013 2013-12-31 10.1109/TCIAIG.2013.2275164 COLLEGE NANME Sport and Exercise Sciences COLLEGE CODE STSC Swansea University 2016-05-05T10:52:00.3188898 2016-05-05T10:52:00.3188898 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Sport and Exercise Sciences Richard Jiang 1 Matthew L. Parry 2 Phillip A. Legg 3 David H. S. Chung 4 Iwan Griffiths 5
title Automated 3-D Animation From Snooker Videos With Information-Theoretical Optimization
spellingShingle Automated 3-D Animation From Snooker Videos With Information-Theoretical Optimization
Iwan Griffiths
title_short Automated 3-D Animation From Snooker Videos With Information-Theoretical Optimization
title_full Automated 3-D Animation From Snooker Videos With Information-Theoretical Optimization
title_fullStr Automated 3-D Animation From Snooker Videos With Information-Theoretical Optimization
title_full_unstemmed Automated 3-D Animation From Snooker Videos With Information-Theoretical Optimization
title_sort Automated 3-D Animation From Snooker Videos With Information-Theoretical Optimization
author_id_str_mv 2ed2cc8d3dff635184def8d15afa21a9
author_id_fullname_str_mv 2ed2cc8d3dff635184def8d15afa21a9_***_Iwan Griffiths
author Iwan Griffiths
author2 Richard Jiang
Matthew L. Parry
Phillip A. Legg
David H. S. Chung
Iwan Griffiths
format Journal article
container_title IEEE Transactions on Computational Intelligence and AI in Games
container_volume 5
container_issue 4
container_start_page 337
publishDate 2013
institution Swansea University
doi_str_mv 10.1109/TCIAIG.2013.2275164
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Sport and Exercise Sciences{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Sport and Exercise Sciences
document_store_str 0
active_str 0
description Automated 3-D modeling from real sports videos can provide valuable resources for visual design in sports-related computer games, saving a lot of effort in manual design of visual features. However, image-based 3-D reconstruction often suffers from inaccuracies caused by statistic image analysis. In this paper, we propose an information-theoretical scheme to minimize errors of automated 3-D modeling from monocular sports videos. In the proposed scheme, mutual information (MI) was exploited to compute the fitting scores of a 3-D model against the observed single-view scene, and the optimization of model fitting was carried out subsequently. With this optimization scheme, errors in model fitting were minimized without human intervention, allowing automated reconstruction of 3-D animation from consecutive monocular video frames at high accuracy. In our work, the Snooker videos were taken as our case study, balls were positioned in 3-D space from single-view frames, and 3-D animation was reproduced from real Snooker videos. Our experimental results validated that the proposed information-theoretical scheme can assist in attaining better accuracy in the automated reconstruction of 3-D animation, and demonstrated that information-theoretical evaluation can be an effective approach for model-based reconstruction from single-view videos
published_date 2013-12-31T03:33:39Z
_version_ 1763751408734044160
score 11.012678

Similar Items