Recognizing gestures by learning local motion signatures of HOG descriptors.
Identifieur interne : 000172 ( Main/Exploration ); précédent : 000171; suivant : 000173Recognizing gestures by learning local motion signatures of HOG descriptors.
Auteurs : Mohamed-Bécha Kaâniche [Tunisie] ; François BrémondSource :
- IEEE transactions on pattern analysis and machine intelligence [ 1939-3539 ] ; 2012.
Descripteurs français
- KwdFr :
- Algorithmes (MeSH), Amélioration d'image (méthodes), Enregistrement sur magnétoscope (méthodes), Gestes (MeSH), Humains (MeSH), Imagerie du corps entier (méthodes), Intelligence artificielle (MeSH), Interprétation d'images assistée par ordinateur (méthodes), Mouvement (physiologie), Reconnaissance automatique des formes (méthodes), Reproductibilité des résultats (MeSH), Sensibilité et spécificité (MeSH).
- MESH :
- méthodes : Amélioration d'image, Enregistrement sur magnétoscope, Imagerie du corps entier, Interprétation d'images assistée par ordinateur, Reconnaissance automatique des formes.
- physiologie : Mouvement.
- Algorithmes, Gestes, Humains, Intelligence artificielle, Reproductibilité des résultats, Sensibilité et spécificité.
English descriptors
- KwdEn :
- Algorithms (MeSH), Artificial Intelligence (MeSH), Gestures (MeSH), Humans (MeSH), Image Enhancement (methods), Image Interpretation, Computer-Assisted (methods), Movement (physiology), Pattern Recognition, Automated (methods), Reproducibility of Results (MeSH), Sensitivity and Specificity (MeSH), Video Recording (methods), Whole Body Imaging (methods).
- MESH :
Abstract
We introduce a new gesture recognition framework based on learning local motion signatures (LMSs) of HOG descriptors introduced by [1]. Our main contribution is to propose a new probabilistic learning-classification scheme based on a reliable tracking of local features. After the generation of these LMSs computed on one individual by tracking Histograms of Oriented Gradient (HOG) [2] descriptor, we learn a codebook of video-words (i.e., clusters of LMSs) using k-means algorithm on a learning gesture video database. Then, the video-words are compacted to a code-book of codewords by the Maximization of Mutual Information (MMI) algorithm. At the final step, we compare the LMSs generated for a new gesture w.r.t. the learned code-book via the k-nearest neighbors (k-NN) algorithm and a novel voting strategy. Our main contribution is the handling of the N to N mapping between codewords and gesture labels within the proposed voting strategy. Experiments have been carried out on two public gesture databases: KTH [3] and IXMAS [4]. Results show that the proposed method outperforms recent state-of-the-art methods.
DOI: 10.1109/TPAMI.2012.19
PubMed: 22997128
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PubMed, to step Corpus: 000648
- to stream PubMed, to step Curation: 000644
- to stream PubMed, to step Checkpoint: 000648
- to stream Main, to step Merge: 000172
- to stream Main, to step Curation: 000172
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Recognizing gestures by learning local motion signatures of HOG descriptors.</title><author><name sortKey="Kaaniche, Mohamed Becha" sort="Kaaniche, Mohamed Becha" uniqKey="Kaaniche M" first="Mohamed-Bécha" last="Kaâniche">Mohamed-Bécha Kaâniche</name><affiliation wicri:level="1"><nlm:affiliation>Higher School of Communications of Tunis (Sup’Com), University of Carthage, Ariana, Tunisia.</nlm:affiliation><country xml:lang="fr">Tunisie</country><wicri:regionArea>Higher School of Communications of Tunis (Sup’Com), University of Carthage, Ariana</wicri:regionArea><wicri:noRegion>Ariana</wicri:noRegion></affiliation></author><author><name sortKey="Bremond, Francois" sort="Bremond, Francois" uniqKey="Bremond F" first="François" last="Brémond">François Brémond</name></author></titleStmt><publicationStmt><idno type="wicri:source">PubMed</idno><date when="2012">2012</date><idno type="RBID">pubmed:22997128</idno><idno type="pmid">22997128</idno><idno type="doi">10.1109/TPAMI.2012.19</idno><idno type="wicri:Area/PubMed/Corpus">000648</idno><idno type="wicri:explorRef" wicri:stream="PubMed" wicri:step="Corpus" wicri:corpus="PubMed">000648</idno><idno type="wicri:Area/PubMed/Curation">000644</idno><idno type="wicri:explorRef" wicri:stream="PubMed" wicri:step="Curation">000644</idno><idno type="wicri:Area/PubMed/Checkpoint">000648</idno><idno type="wicri:explorRef" wicri:stream="Checkpoint" wicri:step="PubMed">000648</idno><idno type="wicri:Area/Main/Merge">000172</idno><idno type="wicri:Area/Main/Curation">000172</idno><idno type="wicri:Area/Main/Exploration">000172</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Recognizing gestures by learning local motion signatures of HOG descriptors.</title><author><name sortKey="Kaaniche, Mohamed Becha" sort="Kaaniche, Mohamed Becha" uniqKey="Kaaniche M" first="Mohamed-Bécha" last="Kaâniche">Mohamed-Bécha Kaâniche</name><affiliation wicri:level="1"><nlm:affiliation>Higher School of Communications of Tunis (Sup’Com), University of Carthage, Ariana, Tunisia.</nlm:affiliation><country xml:lang="fr">Tunisie</country><wicri:regionArea>Higher School of Communications of Tunis (Sup’Com), University of Carthage, Ariana</wicri:regionArea><wicri:noRegion>Ariana</wicri:noRegion></affiliation></author><author><name sortKey="Bremond, Francois" sort="Bremond, Francois" uniqKey="Bremond F" first="François" last="Brémond">François Brémond</name></author></analytic><series><title level="j">IEEE transactions on pattern analysis and machine intelligence</title><idno type="eISSN">1939-3539</idno><imprint><date when="2012" type="published">2012</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithms (MeSH)</term><term>Artificial Intelligence (MeSH)</term><term>Gestures (MeSH)</term><term>Humans (MeSH)</term><term>Image Enhancement (methods)</term><term>Image Interpretation, Computer-Assisted (methods)</term><term>Movement (physiology)</term><term>Pattern Recognition, Automated (methods)</term><term>Reproducibility of Results (MeSH)</term><term>Sensitivity and Specificity (MeSH)</term><term>Video Recording (methods)</term><term>Whole Body Imaging (methods)</term></keywords><keywords scheme="KwdFr" xml:lang="fr"><term>Algorithmes (MeSH)</term><term>Amélioration d'image (méthodes)</term><term>Enregistrement sur magnétoscope (méthodes)</term><term>Gestes (MeSH)</term><term>Humains (MeSH)</term><term>Imagerie du corps entier (méthodes)</term><term>Intelligence artificielle (MeSH)</term><term>Interprétation d'images assistée par ordinateur (méthodes)</term><term>Mouvement (physiologie)</term><term>Reconnaissance automatique des formes (méthodes)</term><term>Reproductibilité des résultats (MeSH)</term><term>Sensibilité et spécificité (MeSH)</term></keywords><keywords scheme="MESH" qualifier="methods" xml:lang="en"><term>Image Enhancement</term><term>Image Interpretation, Computer-Assisted</term><term>Pattern Recognition, Automated</term><term>Video Recording</term><term>Whole Body Imaging</term></keywords><keywords scheme="MESH" qualifier="méthodes" xml:lang="fr"><term>Amélioration d'image</term><term>Enregistrement sur magnétoscope</term><term>Imagerie du corps entier</term><term>Interprétation d'images assistée par ordinateur</term><term>Reconnaissance automatique des formes</term></keywords><keywords scheme="MESH" qualifier="physiologie" xml:lang="fr"><term>Mouvement</term></keywords><keywords scheme="MESH" qualifier="physiology" xml:lang="en"><term>Movement</term></keywords><keywords scheme="MESH" xml:lang="en"><term>Algorithms</term><term>Artificial Intelligence</term><term>Gestures</term><term>Humans</term><term>Reproducibility of Results</term><term>Sensitivity and Specificity</term></keywords><keywords scheme="MESH" xml:lang="fr"><term>Algorithmes</term><term>Gestes</term><term>Humains</term><term>Intelligence artificielle</term><term>Reproductibilité des résultats</term><term>Sensibilité et spécificité</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">We introduce a new gesture recognition framework based on learning local motion signatures (LMSs) of HOG descriptors introduced by [1]. Our main contribution is to propose a new probabilistic learning-classification scheme based on a reliable tracking of local features. After the generation of these LMSs computed on one individual by tracking Histograms of Oriented Gradient (HOG) [2] descriptor, we learn a codebook of video-words (i.e., clusters of LMSs) using k-means algorithm on a learning gesture video database. Then, the video-words are compacted to a code-book of codewords by the Maximization of Mutual Information (MMI) algorithm. At the final step, we compare the LMSs generated for a new gesture w.r.t. the learned code-book via the k-nearest neighbors (k-NN) algorithm and a novel voting strategy. Our main contribution is the handling of the N to N mapping between codewords and gesture labels within the proposed voting strategy. Experiments have been carried out on two public gesture databases: KTH [3] and IXMAS [4]. Results show that the proposed method outperforms recent state-of-the-art methods.</div></front></TEI><affiliations><list><country><li>Tunisie</li></country></list><tree><noCountry><name sortKey="Bremond, Francois" sort="Bremond, Francois" uniqKey="Bremond F" first="François" last="Brémond">François Brémond</name></noCountry><country name="Tunisie"><noRegion><name sortKey="Kaaniche, Mohamed Becha" sort="Kaaniche, Mohamed Becha" uniqKey="Kaaniche M" first="Mohamed-Bécha" last="Kaâniche">Mohamed-Bécha Kaâniche</name></noRegion></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Sante/explor/MaghrebDataLibMedV2/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000172 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000172 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Sante
|area= MaghrebDataLibMedV2
|flux= Main
|étape= Exploration
|type= RBID
|clé= pubmed:22997128
|texte= Recognizing gestures by learning local motion signatures of HOG descriptors.
}}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Exploration/RBID.i -Sk "pubmed:22997128" \
| HfdSelect -Kh $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd \
| NlmPubMed2Wicri -a MaghrebDataLibMedV2
| This area was generated with Dilib version V0.6.38. |  |