Video background modeling: recent approaches, issues and our proposed techniques
Identifieur interne : 003E90 ( Main/Exploration ); précédent : 003E89; suivant : 003E91Video background modeling: recent approaches, issues and our proposed techniques
Auteurs : Munir Shah [Nouvelle-Zélande] ; Jeremiah D. Deng [Nouvelle-Zélande] ; Brendon J. Woodford [Nouvelle-Zélande]Source :
- Machine vision and applications [ 0932-8092 ] ; 2014.
Descripteurs français
- Pascal (Inist)
- Signal vidéo, Soustraction image, Traitement image, Vision ordinateur, Analyse scène, Classification automatique, Estimation mouvement, Analyse contenu, Concordance forme, Eclairement, Réutilisation, Estimation densité, Mélange loi probabilité, Corps mobile, Masque, Luminance, Modélisation, Processus Gauss, Filtre spatio-temporel, Algorithme en ligne, ., Segmentation image, Arrière plan, Détection objet, Analyse en composantes connexes.
English descriptors
- KwdEn :
- ABackground, Automatic classification, Computer vision, Connected component analysis, Content analysis, Density estimation, Gaussian process, Illumination, Image processing, Image segmentation, Image subtraction, Luminance, Mask, Mixed distribution, Modeling, Motion estimation, Moving body, Object detection, Online algorithm, Pattern matching, Reuse, Scene analysis, Spatiotemporal filter, Video signal.
Abstract
Effective and efficient background subtraction is important to a number of computer vision tasks. We introduce several new techniques to address key challenges for background modeling using a Gaussian mixture model (GMM) for moving objects detection in a video acquired by a static camera. The novel features of our proposed model are that it automatically learns dynamics of a scene and adapts its parameters accordingly, suppresses ghosts in the foreground mask using a SURF features matching algorithm, and introduces a new spatio-temporal filter to further refine the foreground detection results. Detection of abrupt illumination changes in the scene is dealt with by a model shifting-based scheme to reuse already learned models and spatio-temporal history of foreground blobs is used to detect and handle paused objects. The proposed model is rigorously tested and compared with several previous models and has shown significant performance improvements.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000362
- to stream PascalFrancis, to step Curation: 005B00
- to stream PascalFrancis, to step Checkpoint: 000017
- to stream Main, to step Merge: 003F41
- to stream Main, to step Curation: 003E90
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Video background modeling: recent approaches, issues and our proposed techniques</title><author><name sortKey="Shah, Munir" sort="Shah, Munir" uniqKey="Shah M" first="Munir" last="Shah">Munir Shah</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Information Science, University of Otago, PO Box 56</s1><s2>Dunedin 9054</s2><s3>NZL</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ></inist:fA14><country>Nouvelle-Zélande</country><wicri:noRegion>Dunedin 9054</wicri:noRegion></affiliation></author><author><name sortKey="Deng, Jeremiah D" sort="Deng, Jeremiah D" uniqKey="Deng J" first="Jeremiah D." last="Deng">Jeremiah D. Deng</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Information Science, University of Otago, PO Box 56</s1><s2>Dunedin 9054</s2><s3>NZL</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ></inist:fA14><country>Nouvelle-Zélande</country><wicri:noRegion>Dunedin 9054</wicri:noRegion></affiliation></author><author><name sortKey="Woodford, Brendon J" sort="Woodford, Brendon J" uniqKey="Woodford B" first="Brendon J." last="Woodford">Brendon J. Woodford</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Information Science, University of Otago, PO Box 56</s1><s2>Dunedin 9054</s2><s3>NZL</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ></inist:fA14><country>Nouvelle-Zélande</country><wicri:noRegion>Dunedin 9054</wicri:noRegion></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">INIST</idno><idno type="inist">14-0172017</idno><date when="2014">2014</date><idno type="stanalyst">PASCAL 14-0172017 INIST</idno><idno type="RBID">Pascal:14-0172017</idno><idno type="wicri:Area/PascalFrancis/Corpus">000362</idno><idno type="wicri:Area/PascalFrancis/Curation">005B00</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">000017</idno><idno type="wicri:explorRef" wicri:stream="PascalFrancis" wicri:step="Checkpoint">000017</idno><idno type="wicri:doubleKey">0932-8092:2014:Shah M:video:background:modeling</idno><idno type="wicri:Area/Main/Merge">003F41</idno><idno type="wicri:Area/Main/Curation">003E90</idno><idno type="wicri:Area/Main/Exploration">003E90</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Video background modeling: recent approaches, issues and our proposed techniques</title><author><name sortKey="Shah, Munir" sort="Shah, Munir" uniqKey="Shah M" first="Munir" last="Shah">Munir Shah</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Information Science, University of Otago, PO Box 56</s1><s2>Dunedin 9054</s2><s3>NZL</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ></inist:fA14><country>Nouvelle-Zélande</country><wicri:noRegion>Dunedin 9054</wicri:noRegion></affiliation></author><author><name sortKey="Deng, Jeremiah D" sort="Deng, Jeremiah D" uniqKey="Deng J" first="Jeremiah D." last="Deng">Jeremiah D. Deng</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Information Science, University of Otago, PO Box 56</s1><s2>Dunedin 9054</s2><s3>NZL</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ></inist:fA14><country>Nouvelle-Zélande</country><wicri:noRegion>Dunedin 9054</wicri:noRegion></affiliation></author><author><name sortKey="Woodford, Brendon J" sort="Woodford, Brendon J" uniqKey="Woodford B" first="Brendon J." last="Woodford">Brendon J. Woodford</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Department of Information Science, University of Otago, PO Box 56</s1><s2>Dunedin 9054</s2><s3>NZL</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ></inist:fA14><country>Nouvelle-Zélande</country><wicri:noRegion>Dunedin 9054</wicri:noRegion></affiliation></author></analytic><series><title level="j" type="main">Machine vision and applications</title><title level="j" type="abbreviated">Mach. vis. appl.</title><idno type="ISSN">0932-8092</idno><imprint><date when="2014">2014</date></imprint></series></biblStruct></sourceDesc><seriesStmt><title level="j" type="main">Machine vision and applications</title><title level="j" type="abbreviated">Mach. vis. appl.</title><idno type="ISSN">0932-8092</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>ABackground</term><term>Automatic classification</term><term>Computer vision</term><term>Connected component analysis</term><term>Content analysis</term><term>Density estimation</term><term>Gaussian process</term><term>Illumination</term><term>Image processing</term><term>Image segmentation</term><term>Image subtraction</term><term>Luminance</term><term>Mask</term><term>Mixed distribution</term><term>Modeling</term><term>Motion estimation</term><term>Moving body</term><term>Object detection</term><term>Online algorithm</term><term>Pattern matching</term><term>Reuse</term><term>Scene analysis</term><term>Spatiotemporal filter</term><term>Video signal</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Signal vidéo</term><term>Soustraction image</term><term>Traitement image</term><term>Vision ordinateur</term><term>Analyse scène</term><term>Classification automatique</term><term>Estimation mouvement</term><term>Analyse contenu</term><term>Concordance forme</term><term>Eclairement</term><term>Réutilisation</term><term>Estimation densité</term><term>Mélange loi probabilité</term><term>Corps mobile</term><term>Masque</term><term>Luminance</term><term>Modélisation</term><term>Processus Gauss</term><term>Filtre spatio-temporel</term><term>Algorithme en ligne</term><term>.</term><term>Segmentation image</term><term>Arrière plan</term><term>Détection objet</term><term>Analyse en composantes connexes</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Effective and efficient background subtraction is important to a number of computer vision tasks. We introduce several new techniques to address key challenges for background modeling using a Gaussian mixture model (GMM) for moving objects detection in a video acquired by a static camera. The novel features of our proposed model are that it automatically learns dynamics of a scene and adapts its parameters accordingly, suppresses ghosts in the foreground mask using a SURF features matching algorithm, and introduces a new spatio-temporal filter to further refine the foreground detection results. Detection of abrupt illumination changes in the scene is dealt with by a model shifting-based scheme to reuse already learned models and spatio-temporal history of foreground blobs is used to detect and handle paused objects. The proposed model is rigorously tested and compared with several previous models and has shown significant performance improvements.</div></front></TEI><affiliations><list><country><li>Nouvelle-Zélande</li></country></list><tree><country name="Nouvelle-Zélande"><noRegion><name sortKey="Shah, Munir" sort="Shah, Munir" uniqKey="Shah M" first="Munir" last="Shah">Munir Shah</name></noRegion><name sortKey="Deng, Jeremiah D" sort="Deng, Jeremiah D" uniqKey="Deng J" first="Jeremiah D." last="Deng">Jeremiah D. Deng</name><name sortKey="Woodford, Brendon J" sort="Woodford, Brendon J" uniqKey="Woodford B" first="Brendon J." last="Woodford">Brendon J. Woodford</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Asie/explor/AustralieFrV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 003E90 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 003E90 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Asie
|area= AustralieFrV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= Pascal:14-0172017
|texte= Video background modeling: recent approaches, issues and our proposed techniques
}}
| This area was generated with Dilib version V0.6.33. |  |