Mixture of Merged Gaussian Algorithm using RTDENN
Identifieur interne : 004057 ( Main/Exploration ); précédent : 004056; suivant : 004058Mixture of Merged Gaussian Algorithm using RTDENN
Auteurs : Manuel Alvar [Espagne] ; Andrea Rodriguez-Calvo [Espagne] ; Alvaro Sanchez-Miralles [Espagne] ; Alvaro Arranz [Espagne]Source :
- Machine vision and applications [ 0932-8092 ] ; 2014.
Descripteurs français
- Pascal (Inist)
- Vision ordinateur, Monitorage, Surveillance, Estimation mouvement, Temps exécution, Temps réel, Fiabilité, Intelligence artificielle, Mise à jour, Signal vidéo, Analyse image, Traitement image, Détection mouvement, Eclairage, Ombre, Occlusion, Occultation, Processus Gauss, Robustesse, Approche probabiliste, Modélisation, Théorie mélange, Réseau neuronal, Modèle dynamique, Ellipsoïde, Dynamique processus, Segmentation image, Détection objet.
- Wicri :
- topic : Intelligence artificielle.
English descriptors
- KwdEn :
- Artificial intelligence, Computer vision, Dynamic model, Ellipsoid, Execution time, Gaussian process, Image analysis, Image processing, Image segmentation, Lighting, Mixture theory, Modeling, Monitoring, Motion detection, Motion estimation, Neural network, Object detection, Occlusion, Occultation, Probabilistic approach, Process dynamics, Real time, Reliability, Robustness, Shadow, Surveillance, Updating, Video signal.
Abstract
Computer vision has been a widely developed research area in the last years, and it has been used for a broad range of applications, including surveillance systems. In the pursuit of an autonomous and smart motion detection system, a reliable segmentation algorithm is required. The main problems of present segmentation solutions are their high execution time and the lack of robustness against changes in the environment due to variations in lighting, shadows, occlusions or the movement of secondary objects. This paper proposes a new algorithm named Mixture of Merged Gaussian Algorithm (MMGA) that aims to achieve a substantial improvement in execution speed to enable real-time implementation, without compromising the reliability and accuracy of the segmentation. The MMGA is based on the combination of a probabilistic model for the background, similar to the Mixture of Gaussian Model (MGM), with the learning processes of Real-Time Dynamic Ellipsoidal Neural Networks (RTDENN) for the update of the model. The proposed algorithm has been tested for different videos and compared to the MGM and SDGM algorithms. Results show a reduction of 30 to 50 % in execution times. Furthermore, the segmentation is more robust against the effect of noise and adapts faster to lighting changes.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000364
- to stream PascalFrancis, to step Curation: 005A98
- to stream PascalFrancis, to step Checkpoint: 000194
- to stream Main, to step Merge: 004118
- to stream Main, to step Curation: 004057
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Mixture of Merged Gaussian Algorithm using RTDENN</title><author><name sortKey="Alvar, Manuel" sort="Alvar, Manuel" uniqKey="Alvar M" first="Manuel" last="Alvar">Manuel Alvar</name><affiliation wicri:level="2"><inist:fA14 i1="01"><s1>Institute for Research in Technology, Comillas Pontifical University, Alberto Aguilera 23</s1><s2>Madrid 28015</s2><s3>ESP</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ><sZ>4 aut.</sZ></inist:fA14><country>Espagne</country><placeName><region nuts="2" type="communauté">Communauté de Madrid</region></placeName></affiliation></author><author><name sortKey="Rodriguez Calvo, Andrea" sort="Rodriguez Calvo, Andrea" uniqKey="Rodriguez Calvo A" first="Andrea" last="Rodriguez-Calvo">Andrea Rodriguez-Calvo</name><affiliation wicri:level="2"><inist:fA14 i1="01"><s1>Institute for Research in Technology, Comillas Pontifical University, Alberto Aguilera 23</s1><s2>Madrid 28015</s2><s3>ESP</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ><sZ>4 aut.</sZ></inist:fA14><country>Espagne</country><placeName><region nuts="2" type="communauté">Communauté de Madrid</region></placeName></affiliation></author><author><name sortKey="Sanchez Miralles, Alvaro" sort="Sanchez Miralles, Alvaro" uniqKey="Sanchez Miralles A" first="Alvaro" last="Sanchez-Miralles">Alvaro Sanchez-Miralles</name><affiliation wicri:level="2"><inist:fA14 i1="01"><s1>Institute for Research in Technology, Comillas Pontifical University, Alberto Aguilera 23</s1><s2>Madrid 28015</s2><s3>ESP</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ><sZ>4 aut.</sZ></inist:fA14><country>Espagne</country><placeName><region nuts="2" type="communauté">Communauté de Madrid</region></placeName></affiliation></author><author><name sortKey="Arranz, Alvaro" sort="Arranz, Alvaro" uniqKey="Arranz A" first="Alvaro" last="Arranz">Alvaro Arranz</name><affiliation wicri:level="2"><inist:fA14 i1="01"><s1>Institute for Research in Technology, Comillas Pontifical University, Alberto Aguilera 23</s1><s2>Madrid 28015</s2><s3>ESP</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ><sZ>4 aut.</sZ></inist:fA14><country>Espagne</country><placeName><region nuts="2" type="communauté">Communauté de Madrid</region></placeName></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">INIST</idno><idno type="inist">14-0172012</idno><date when="2014">2014</date><idno type="stanalyst">PASCAL 14-0172012 INIST</idno><idno type="RBID">Pascal:14-0172012</idno><idno type="wicri:Area/PascalFrancis/Corpus">000364</idno><idno type="wicri:Area/PascalFrancis/Curation">005A98</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">000194</idno><idno type="wicri:explorRef" wicri:stream="PascalFrancis" wicri:step="Checkpoint">000194</idno><idno type="wicri:doubleKey">0932-8092:2014:Alvar M:mixture:of:merged</idno><idno type="wicri:Area/Main/Merge">004118</idno><idno type="wicri:Area/Main/Curation">004057</idno><idno type="wicri:Area/Main/Exploration">004057</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Mixture of Merged Gaussian Algorithm using RTDENN</title><author><name sortKey="Alvar, Manuel" sort="Alvar, Manuel" uniqKey="Alvar M" first="Manuel" last="Alvar">Manuel Alvar</name><affiliation wicri:level="2"><inist:fA14 i1="01"><s1>Institute for Research in Technology, Comillas Pontifical University, Alberto Aguilera 23</s1><s2>Madrid 28015</s2><s3>ESP</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ><sZ>4 aut.</sZ></inist:fA14><country>Espagne</country><placeName><region nuts="2" type="communauté">Communauté de Madrid</region></placeName></affiliation></author><author><name sortKey="Rodriguez Calvo, Andrea" sort="Rodriguez Calvo, Andrea" uniqKey="Rodriguez Calvo A" first="Andrea" last="Rodriguez-Calvo">Andrea Rodriguez-Calvo</name><affiliation wicri:level="2"><inist:fA14 i1="01"><s1>Institute for Research in Technology, Comillas Pontifical University, Alberto Aguilera 23</s1><s2>Madrid 28015</s2><s3>ESP</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ><sZ>4 aut.</sZ></inist:fA14><country>Espagne</country><placeName><region nuts="2" type="communauté">Communauté de Madrid</region></placeName></affiliation></author><author><name sortKey="Sanchez Miralles, Alvaro" sort="Sanchez Miralles, Alvaro" uniqKey="Sanchez Miralles A" first="Alvaro" last="Sanchez-Miralles">Alvaro Sanchez-Miralles</name><affiliation wicri:level="2"><inist:fA14 i1="01"><s1>Institute for Research in Technology, Comillas Pontifical University, Alberto Aguilera 23</s1><s2>Madrid 28015</s2><s3>ESP</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ><sZ>4 aut.</sZ></inist:fA14><country>Espagne</country><placeName><region nuts="2" type="communauté">Communauté de Madrid</region></placeName></affiliation></author><author><name sortKey="Arranz, Alvaro" sort="Arranz, Alvaro" uniqKey="Arranz A" first="Alvaro" last="Arranz">Alvaro Arranz</name><affiliation wicri:level="2"><inist:fA14 i1="01"><s1>Institute for Research in Technology, Comillas Pontifical University, Alberto Aguilera 23</s1><s2>Madrid 28015</s2><s3>ESP</s3><sZ>1 aut.</sZ><sZ>2 aut.</sZ><sZ>3 aut.</sZ><sZ>4 aut.</sZ></inist:fA14><country>Espagne</country><placeName><region nuts="2" type="communauté">Communauté de Madrid</region></placeName></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>Artificial intelligence</term><term>Computer vision</term><term>Dynamic model</term><term>Ellipsoid</term><term>Execution time</term><term>Gaussian process</term><term>Image analysis</term><term>Image processing</term><term>Image segmentation</term><term>Lighting</term><term>Mixture theory</term><term>Modeling</term><term>Monitoring</term><term>Motion detection</term><term>Motion estimation</term><term>Neural network</term><term>Object detection</term><term>Occlusion</term><term>Occultation</term><term>Probabilistic approach</term><term>Process dynamics</term><term>Real time</term><term>Reliability</term><term>Robustness</term><term>Shadow</term><term>Surveillance</term><term>Updating</term><term>Video signal</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Vision ordinateur</term><term>Monitorage</term><term>Surveillance</term><term>Estimation mouvement</term><term>Temps exécution</term><term>Temps réel</term><term>Fiabilité</term><term>Intelligence artificielle</term><term>Mise à jour</term><term>Signal vidéo</term><term>Analyse image</term><term>Traitement image</term><term>Détection mouvement</term><term>Eclairage</term><term>Ombre</term><term>Occlusion</term><term>Occultation</term><term>Processus Gauss</term><term>Robustesse</term><term>Approche probabiliste</term><term>Modélisation</term><term>Théorie mélange</term><term>Réseau neuronal</term><term>Modèle dynamique</term><term>Ellipsoïde</term><term>Dynamique processus</term><term>Segmentation image</term><term>Détection objet</term></keywords><keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Intelligence artificielle</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Computer vision has been a widely developed research area in the last years, and it has been used for a broad range of applications, including surveillance systems. In the pursuit of an autonomous and smart motion detection system, a reliable segmentation algorithm is required. The main problems of present segmentation solutions are their high execution time and the lack of robustness against changes in the environment due to variations in lighting, shadows, occlusions or the movement of secondary objects. This paper proposes a new algorithm named Mixture of Merged Gaussian Algorithm (MMGA) that aims to achieve a substantial improvement in execution speed to enable real-time implementation, without compromising the reliability and accuracy of the segmentation. The MMGA is based on the combination of a probabilistic model for the background, similar to the Mixture of Gaussian Model (MGM), with the learning processes of Real-Time Dynamic Ellipsoidal Neural Networks (RTDENN) for the update of the model. The proposed algorithm has been tested for different videos and compared to the MGM and SDGM algorithms. Results show a reduction of 30 to 50 % in execution times. Furthermore, the segmentation is more robust against the effect of noise and adapts faster to lighting changes.</div></front></TEI><affiliations><list><country><li>Espagne</li></country><region><li>Communauté de Madrid</li></region></list><tree><country name="Espagne"><region name="Communauté de Madrid"><name sortKey="Alvar, Manuel" sort="Alvar, Manuel" uniqKey="Alvar M" first="Manuel" last="Alvar">Manuel Alvar</name></region><name sortKey="Arranz, Alvaro" sort="Arranz, Alvaro" uniqKey="Arranz A" first="Alvaro" last="Arranz">Alvaro Arranz</name><name sortKey="Rodriguez Calvo, Andrea" sort="Rodriguez Calvo, Andrea" uniqKey="Rodriguez Calvo A" first="Andrea" last="Rodriguez-Calvo">Andrea Rodriguez-Calvo</name><name sortKey="Sanchez Miralles, Alvaro" sort="Sanchez Miralles, Alvaro" uniqKey="Sanchez Miralles A" first="Alvaro" last="Sanchez-Miralles">Alvaro Sanchez-Miralles</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 004057 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 004057 | 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:14-0172012
|texte= Mixture of Merged Gaussian Algorithm using RTDENN
}}
| This area was generated with Dilib version V0.6.33. |  |