Characterization and recognition of gestures in videos using Markovian models
Identifieur interne : 000248 ( France/Analysis ); précédent : 000247; suivant : 000249Characterization and recognition of gestures in videos using Markovian models
Auteurs : Selma Belgacem [France]Source :
Descripteurs français
- mix :
English descriptors
- mix :
Abstract
This PHD thesis concerns the analysis of gestures, especially the characteri-zation and the recognition of gestures. The analysis of gestural data is a research field which involves Human-Machine communication, video management and signal processing fields. The main contribution of this PHD thesis is the design and implementation of a hybrid Markov system for sequential data recognition. The recognition task typically combines two tasks : segmentation and classification. Therefore, the proposed hybrid model combines the ability of modeling and segmentation of HiddenMarkov Models and the ability of local discrimination of Conditional Random Fields. We applied this hybrid system to the recognition of gesture sequences in videos in the context of one-shot-learning. The interesting recognition performance achieved in the context of the competition of ChaLearn show the advantage of the proposed approach for the context of learning with few examples. The recognition task requires a step of data characterization. In the context of gesture characterization, we propose two contributions. The first contribution is an improvement of local tracking of the dominant hand in a gesture with particle filters. This improvement is mainly based on a penalisation, computed with optical flow method, of the estimator and an automatic vocabulary reference generation. The second contribution is a method of global characterization of a gesture that we call the "gesture signature". The gesture signature describes the location, velocity and orientation of the global movement in a gesture combining velocity information calculated with optical flow method.
Url:
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Hal, to step Corpus: 000059
- to stream Hal, to step Curation: 000059
- to stream Hal, to step Checkpoint: 000135
- to stream Main, to step Merge: 000260
- to stream Main, to step Curation: 000259
- to stream Main, to step Exploration: 000259
- to stream France, to step Extraction: 000248
Links to Exploration step
Hal:tel-01137866Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Characterization and recognition of gestures in videos using Markovian models</title><title xml:lang="fr">Caractérisation et Reconnaissance de Gestes dans des vidéos à l'aide de Modèles Markoviens</title><author><name sortKey="Belgacem, Selma" sort="Belgacem, Selma" uniqKey="Belgacem S" first="Selma" last="Belgacem">Selma Belgacem</name><affiliation wicri:level="1"><hal:affiliation type="researchteam" xml:id="struct-389520" status="INCOMING"> <orgName>DOCAPP</orgName> <desc> <address> <country key="FR"></country> </address> </desc> <listRelation> <relation active="#struct-23832" type="direct"></relation> <relation active="#struct-300317" type="indirect"></relation> <relation name="EA4108" active="#struct-300318" type="indirect"></relation> <relation active="#struct-301288" type="indirect"></relation> <relation active="#struct-301232" type="indirect"></relation> </listRelation><tutelles><tutelle active="#struct-23832" type="direct"><org type="laboratory" xml:id="struct-23832" status="VALID"><orgName>Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes</orgName><orgName type="acronym">LITIS</orgName><desc><address><addrLine>Avenue de l'Université UFR des Sciences et Techniques 76800 Saint-Etienne du Rouvray</addrLine><country key="FR"></country></address><ref type="url">http://www.litislab.eu</ref></desc><listRelation><relation active="#struct-300317" type="direct"></relation><relation name="EA4108" active="#struct-300318" type="direct"></relation><relation active="#struct-301288" type="direct"></relation><relation active="#struct-301232" type="indirect"></relation></listRelation></org></tutelle><tutelle active="#struct-300317" type="indirect"><org type="institution" xml:id="struct-300317" status="VALID"><orgName>Université du Havre</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle><tutelle name="EA4108" active="#struct-300318" type="indirect"><org type="institution" xml:id="struct-300318" status="VALID"><orgName>Université de Rouen</orgName><desc><address><addrLine> 1 rue Thomas Becket - 76821 Mont-Saint-Aignan</addrLine><country key="FR"></country></address><ref type="url">http://www.univ-rouen.fr/</ref></desc></org></tutelle><tutelle active="#struct-301288" type="indirect"><org type="department" xml:id="struct-301288" status="VALID"><orgName>Institut National des Sciences Appliquées - Rouen</orgName><orgName type="acronym">INSA Rouen</orgName><desc><address><country key="FR"></country></address></desc><listRelation><relation active="#struct-301232" type="direct"></relation></listRelation></org></tutelle><tutelle active="#struct-301232" type="indirect"><org type="institution" xml:id="struct-301232" status="VALID"><orgName>Institut National des Sciences Appliquées</orgName><orgName type="acronym">INSA</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle></tutelles></hal:affiliation><country>France</country><placeName><settlement type="city">Le Havre</settlement><region type="region" nuts="2">Région Normandie</region><region type="old region" nuts="2">Haute-Normandie</region></placeName><orgName type="university">Université du Havre</orgName><placeName><settlement type="city">Rouen</settlement><region type="region" nuts="2">Région Normandie</region><region type="old region" nuts="2">Haute-Normandie</region></placeName><orgName type="university">Université de Rouen</orgName></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">HAL</idno><idno type="RBID">Hal:tel-01137866</idno><idno type="halId">tel-01137866</idno><idno type="halUri">https://tel.archives-ouvertes.fr/tel-01137866</idno><idno type="url">https://tel.archives-ouvertes.fr/tel-01137866</idno><date when="2014-06-25">2014-06-25</date><idno type="wicri:Area/Hal/Corpus">000059</idno><idno type="wicri:Area/Hal/Curation">000059</idno><idno type="wicri:Area/Hal/Checkpoint">000135</idno><idno type="wicri:Area/Main/Merge">000260</idno><idno type="wicri:Area/Main/Curation">000259</idno><idno type="wicri:Area/Main/Exploration">000259</idno><idno type="wicri:Area/France/Extraction">000248</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Characterization and recognition of gestures in videos using Markovian models</title><title xml:lang="fr">Caractérisation et Reconnaissance de Gestes dans des vidéos à l'aide de Modèles Markoviens</title><author><name sortKey="Belgacem, Selma" sort="Belgacem, Selma" uniqKey="Belgacem S" first="Selma" last="Belgacem">Selma Belgacem</name><affiliation wicri:level="1"><hal:affiliation type="researchteam" xml:id="struct-389520" status="INCOMING"> <orgName>DOCAPP</orgName> <desc> <address> <country key="FR"></country> </address> </desc> <listRelation> <relation active="#struct-23832" type="direct"></relation> <relation active="#struct-300317" type="indirect"></relation> <relation name="EA4108" active="#struct-300318" type="indirect"></relation> <relation active="#struct-301288" type="indirect"></relation> <relation active="#struct-301232" type="indirect"></relation> </listRelation><tutelles><tutelle active="#struct-23832" type="direct"><org type="laboratory" xml:id="struct-23832" status="VALID"><orgName>Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes</orgName><orgName type="acronym">LITIS</orgName><desc><address><addrLine>Avenue de l'Université UFR des Sciences et Techniques 76800 Saint-Etienne du Rouvray</addrLine><country key="FR"></country></address><ref type="url">http://www.litislab.eu</ref></desc><listRelation><relation active="#struct-300317" type="direct"></relation><relation name="EA4108" active="#struct-300318" type="direct"></relation><relation active="#struct-301288" type="direct"></relation><relation active="#struct-301232" type="indirect"></relation></listRelation></org></tutelle><tutelle active="#struct-300317" type="indirect"><org type="institution" xml:id="struct-300317" status="VALID"><orgName>Université du Havre</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle><tutelle name="EA4108" active="#struct-300318" type="indirect"><org type="institution" xml:id="struct-300318" status="VALID"><orgName>Université de Rouen</orgName><desc><address><addrLine> 1 rue Thomas Becket - 76821 Mont-Saint-Aignan</addrLine><country key="FR"></country></address><ref type="url">http://www.univ-rouen.fr/</ref></desc></org></tutelle><tutelle active="#struct-301288" type="indirect"><org type="department" xml:id="struct-301288" status="VALID"><orgName>Institut National des Sciences Appliquées - Rouen</orgName><orgName type="acronym">INSA Rouen</orgName><desc><address><country key="FR"></country></address></desc><listRelation><relation active="#struct-301232" type="direct"></relation></listRelation></org></tutelle><tutelle active="#struct-301232" type="indirect"><org type="institution" xml:id="struct-301232" status="VALID"><orgName>Institut National des Sciences Appliquées</orgName><orgName type="acronym">INSA</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle></tutelles></hal:affiliation><country>France</country><placeName><settlement type="city">Le Havre</settlement><region type="region" nuts="2">Région Normandie</region><region type="old region" nuts="2">Haute-Normandie</region></placeName><orgName type="university">Université du Havre</orgName><placeName><settlement type="city">Rouen</settlement><region type="region" nuts="2">Région Normandie</region><region type="old region" nuts="2">Haute-Normandie</region></placeName><orgName type="university">Université de Rouen</orgName></affiliation></author></analytic></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="mix" xml:lang="en"><term>conditional random fields</term><term>gesture recognition</term><term>hidden markov models</term><term>optical flow</term><term>particle filter</term></keywords><keywords scheme="mix" xml:lang="fr"><term>caractérisation de gestes</term><term>champ aléatoire conditionnel</term><term>filtres particulaires</term><term>flots optiques.</term><term>modèle de Markov cachés</term><term>reconnaissance de gestes</term><term>système hybride</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">This PHD thesis concerns the analysis of gestures, especially the characteri-zation and the recognition of gestures. The analysis of gestural data is a research field which involves Human-Machine communication, video management and signal processing fields. The main contribution of this PHD thesis is the design and implementation of a hybrid Markov system for sequential data recognition. The recognition task typically combines two tasks : segmentation and classification. Therefore, the proposed hybrid model combines the ability of modeling and segmentation of HiddenMarkov Models and the ability of local discrimination of Conditional Random Fields. We applied this hybrid system to the recognition of gesture sequences in videos in the context of one-shot-learning. The interesting recognition performance achieved in the context of the competition of ChaLearn show the advantage of the proposed approach for the context of learning with few examples. The recognition task requires a step of data characterization. In the context of gesture characterization, we propose two contributions. The first contribution is an improvement of local tracking of the dominant hand in a gesture with particle filters. This improvement is mainly based on a penalisation, computed with optical flow method, of the estimator and an automatic vocabulary reference generation. The second contribution is a method of global characterization of a gesture that we call the "gesture signature". The gesture signature describes the location, velocity and orientation of the global movement in a gesture combining velocity information calculated with optical flow method.</div></front></TEI><affiliations><list><country><li>France</li></country><region><li>Haute-Normandie</li><li>Région Normandie</li></region><settlement><li>Le Havre</li><li>Rouen</li></settlement><orgName><li>Université de Rouen</li><li>Université du Havre</li></orgName></list><tree><country name="France"><region name="Région Normandie"><name sortKey="Belgacem, Selma" sort="Belgacem, Selma" uniqKey="Belgacem S" first="Selma" last="Belgacem">Selma Belgacem</name></region></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/France/explor/LeHavreV1/Data/France/Analysis
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000248 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/France/Analysis/biblio.hfd -nk 000248 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/France
|area= LeHavreV1
|flux= France
|étape= Analysis
|type= RBID
|clé= Hal:tel-01137866
|texte= Characterization and recognition of gestures in videos using Markovian models
}}
| This area was generated with Dilib version V0.6.25. |  |