File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Gait recognition based on multiple views fusion of wavelet descriptor and human skeleton model

TitleGait recognition based on multiple views fusion of wavelet descriptor and human skeleton model
Authors
KeywordsGait Recognition
Human Skeleton Model
Multiple Feature Fusion
Multiple Views Fusion
Svm
Wavelet Descriptor
Issue Date2009
PublisherIEEE
Citation
2009 Ieee International Conference On Virtual Environments, Human-Computer Interfaces, And Measurements Systems, Vecims 2009 - Proceedings, 2009, p. 246-249 How to Cite?
AbstractGait recognition is a relatively new subfield in biometric recognition, which attempts to recognize people from the way they walk or run. This paper discusses silhouette-based feature descriptor. Human silhouette geometry is generated by boundary tracking approach and resampled to a normalized format. Boundary-centroid distance is proposed to describe gait modality. Then, we apply wavelet transform to boundarycentroid distance, and extract wavelet descriptor. At the same time, we obtain the human skeleton model and extract body's dynamic parameters to express gait modality. We carry out human identification based on SVM using the two kinds of gait feature. The performances based on the two features are compared. Multiple feature fusion and multiple views fusion are carried out and the recognition results demonstrate that the performance of multiple features and multiple views recognition is better than any single feature and single view recognition. ©2009 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/173411
ISBN
ISSN
References

 

DC FieldValueLanguage
dc.contributor.authorMing, Den_US
dc.contributor.authorZhang, Cen_US
dc.contributor.authorBai, Yen_US
dc.contributor.authorWan, Ben_US
dc.contributor.authorHu, Yen_US
dc.contributor.authorLuk, KDKen_US
dc.date.accessioned2012-10-30T06:30:55Z-
dc.date.available2012-10-30T06:30:55Z-
dc.date.issued2009en_US
dc.identifier.citation2009 Ieee International Conference On Virtual Environments, Human-Computer Interfaces, And Measurements Systems, Vecims 2009 - Proceedings, 2009, p. 246-249en_US
dc.identifier.isbn978-1-4244-3808-2-
dc.identifier.issn1944-9410-
dc.identifier.urihttp://hdl.handle.net/10722/173411-
dc.description.abstractGait recognition is a relatively new subfield in biometric recognition, which attempts to recognize people from the way they walk or run. This paper discusses silhouette-based feature descriptor. Human silhouette geometry is generated by boundary tracking approach and resampled to a normalized format. Boundary-centroid distance is proposed to describe gait modality. Then, we apply wavelet transform to boundarycentroid distance, and extract wavelet descriptor. At the same time, we obtain the human skeleton model and extract body's dynamic parameters to express gait modality. We carry out human identification based on SVM using the two kinds of gait feature. The performances based on the two features are compared. Multiple feature fusion and multiple views fusion are carried out and the recognition results demonstrate that the performance of multiple features and multiple views recognition is better than any single feature and single view recognition. ©2009 IEEE.en_US
dc.languageengen_US
dc.publisherIEEE-
dc.relation.ispartof2009 IEEE International Conference on Virtual Environments, Human-Computer Interfaces, and Measurements Systems, VECIMS 2009 - Proceedingsen_US
dc.subjectGait Recognitionen_US
dc.subjectHuman Skeleton Modelen_US
dc.subjectMultiple Feature Fusionen_US
dc.subjectMultiple Views Fusionen_US
dc.subjectSvmen_US
dc.subjectWavelet Descriptoren_US
dc.titleGait recognition based on multiple views fusion of wavelet descriptor and human skeleton modelen_US
dc.typeConference_Paperen_US
dc.identifier.emailHu, Y:yhud@hku.hken_US
dc.identifier.emailLuk, KDK:hcm21000@hku.hken_US
dc.identifier.authorityHu, Y=rp00432en_US
dc.identifier.authorityLuk, KDK=rp00333en_US
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.doi10.1109/VECIMS.2009.5068902en_US
dc.identifier.scopuseid_2-s2.0-70349899113en_US
dc.identifier.hkuros159886-
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-70349899113&selection=ref&src=s&origin=recordpageen_US
dc.identifier.spage246en_US
dc.identifier.epage249en_US
dc.identifier.scopusauthoridMing, D=9745824400en_US
dc.identifier.scopusauthoridZhang, C=35110047100en_US
dc.identifier.scopusauthoridBai, Y=35108689200en_US
dc.identifier.scopusauthoridWan, B=7102316798en_US
dc.identifier.scopusauthoridHu, Y=7407116091en_US
dc.identifier.scopusauthoridLuk, KDK=7201921573en_US

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats