Scene text recognition and tracking to identify athletes in sport videos
Identifieur interne : 000186 ( Main/Exploration ); précédent : 000185; suivant : 000187Scene text recognition and tracking to identify athletes in sport videos
Auteurs : Stefano Messelodi [Italie] ; Carla Maria Modena [Italie]Source :
- Multimedia tools and applications [ 1380-7501 ] ; 2013.
Descripteurs français
- Pascal (Inist)
- Wicri :
- topic : Sport.
English descriptors
- KwdEn :
Abstract
We present an athlete identification module forming part of a system for the personalization of sport video broadcasts. The aim of this module is the localization of athletes in the scene, their identification through the reading of names or numbers printed on their uniforms, and the labelling of frames where athletes are visible. Building upon a previously published algorithm we extract text from individual frames and read these candidates by means of an optical character recognizer (OCR). The OCR-ed text is then compared to a known list of athletes' names (or numbers), to provide a presence score for each athlete. Text regions are tracked in subsequent frames using a template matching technique. In this way blurred or distorted text, normally unreadable by the OCR, is exploited to provide a denser labelling of the video sequences. Extensive experiments show that the method proposed is fast, robust and reliable, out-performing results of other systems in the literature.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000049
- to stream PascalFrancis, to step Curation: 000719
- to stream PascalFrancis, to step Checkpoint: 000029
- to stream Main, to step Merge: 000189
- to stream Main, to step Curation: 000186
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Scene text recognition and tracking to identify athletes in sport videos</title><author><name sortKey="Messelodi, Stefano" sort="Messelodi, Stefano" uniqKey="Messelodi S" first="Stefano" last="Messelodi">Stefano Messelodi</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>FBK-irst, Via Sommarive 18, 38123 Povo</s1><s2>Trento</s2><s3>ITA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>Italie</country><wicri:noRegion>Trento</wicri:noRegion></affiliation></author><author><name sortKey="Modena, Carla Maria" sort="Modena, Carla Maria" uniqKey="Modena C" first="Carla Maria" last="Modena">Carla Maria Modena</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>FBK-irst, Via Sommarive 18, 38123 Povo</s1><s2>Trento</s2><s3>ITA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>Italie</country><wicri:noRegion>Trento</wicri:noRegion></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">INIST</idno><idno type="inist">13-0287896</idno><date when="2013">2013</date><idno type="stanalyst">PASCAL 13-0287896 INIST</idno><idno type="RBID">Pascal:13-0287896</idno><idno type="wicri:Area/PascalFrancis/Corpus">000049</idno><idno type="wicri:Area/PascalFrancis/Curation">000719</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">000029</idno><idno type="wicri:doubleKey">1380-7501:2013:Messelodi S:scene:text:recognition</idno><idno type="wicri:Area/Main/Merge">000189</idno><idno type="wicri:Area/Main/Curation">000186</idno><idno type="wicri:Area/Main/Exploration">000186</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Scene text recognition and tracking to identify athletes in sport videos</title><author><name sortKey="Messelodi, Stefano" sort="Messelodi, Stefano" uniqKey="Messelodi S" first="Stefano" last="Messelodi">Stefano Messelodi</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>FBK-irst, Via Sommarive 18, 38123 Povo</s1><s2>Trento</s2><s3>ITA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>Italie</country><wicri:noRegion>Trento</wicri:noRegion></affiliation></author><author><name sortKey="Modena, Carla Maria" sort="Modena, Carla Maria" uniqKey="Modena C" first="Carla Maria" last="Modena">Carla Maria Modena</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>FBK-irst, Via Sommarive 18, 38123 Povo</s1><s2>Trento</s2><s3>ITA</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ></inist:fA14><country>Italie</country><wicri:noRegion>Trento</wicri:noRegion></affiliation></author></analytic><series><title level="j" type="main">Multimedia tools and applications</title><title level="j" type="abbreviated">Multimed. tools appl.</title><idno type="ISSN">1380-7501</idno><imprint><date when="2013">2013</date></imprint></series></biblStruct></sourceDesc><seriesStmt><title level="j" type="main">Multimedia tools and applications</title><title level="j" type="abbreviated">Multimed. tools appl.</title><idno type="ISSN">1380-7501</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Character recognition</term><term>Customization</term><term>Image analysis</term><term>Image matching</term><term>Image processing</term><term>Image sequence</term><term>Information retrieval</term><term>Labelling</term><term>Localization</term><term>Optical character recognition</term><term>Pattern matching</term><term>Pattern recognition</term><term>Scene analysis</term><term>Sport</term><term>Text</term><term>Tracking</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Analyse scène</term><term>Reconnaissance caractère</term><term>Texte</term><term>Reconnaissance forme</term><term>Pistage</term><term>Localisation</term><term>Etiquetage</term><term>Reconnaissance optique caractère</term><term>Concordance forme</term><term>Séquence image</term><term>Recherche information</term><term>Analyse image</term><term>Sport</term><term>Personnalisation</term><term>Traitement image</term><term>Appariement image</term></keywords><keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Sport</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">We present an athlete identification module forming part of a system for the personalization of sport video broadcasts. The aim of this module is the localization of athletes in the scene, their identification through the reading of names or numbers printed on their uniforms, and the labelling of frames where athletes are visible. Building upon a previously published algorithm we extract text from individual frames and read these candidates by means of an optical character recognizer (OCR). The OCR-ed text is then compared to a known list of athletes' names (or numbers), to provide a presence score for each athlete. Text regions are tracked in subsequent frames using a template matching technique. In this way blurred or distorted text, normally unreadable by the OCR, is exploited to provide a denser labelling of the video sequences. Extensive experiments show that the method proposed is fast, robust and reliable, out-performing results of other systems in the literature.</div></front></TEI><affiliations><list><country><li>Italie</li></country></list><tree><country name="Italie"><noRegion><name sortKey="Messelodi, Stefano" sort="Messelodi, Stefano" uniqKey="Messelodi S" first="Stefano" last="Messelodi">Stefano Messelodi</name></noRegion><name sortKey="Modena, Carla Maria" sort="Modena, Carla Maria" uniqKey="Modena C" first="Carla Maria" last="Modena">Carla Maria Modena</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000186 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000186 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= Pascal:13-0287896
|texte= Scene text recognition and tracking to identify athletes in sport videos
}}
| This area was generated with Dilib version V0.6.32. |  |