File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Human gait recognition with matrix representation

TitleHuman gait recognition with matrix representation
Authors
KeywordsCoupled subspaces analysis (CSA)
Dimensionality reduction
Discriminant analysis with tensor representation (DATER)
Human gait recognition
Object representation
Issue Date2006
Citation
IEEE Transactions on Circuits and Systems for Video Technology, 2006, v. 16, n. 7, p. 896-903 How to Cite?
AbstractHuman gait is an important biometric feature. It can be perceived from a great distance and has recently attracted greater attention in video-surveillance-related applications, such as closed-circuit television. We explore gait recognition based on a matrix representation in this paper. First, binary silhouettes over one gait cycle are averaged. As a result, each gait video sequence, containing a number of gait cycles, is represented by a series of gray-level averaged images. Then, a matrix-based unsupervised algorithm, namely coupled subspace analysis (CSA), is employed as a preprocessing step to remove noise and retain the most representative information. Finally, a supervised algorithm, namely discriminant analysis with tensor representation, is applied to further improve classification ability. This matrix-based scheme demonstrates a much better gait recognition performance than state-of-the-art algorithms on the standard USF HumanID Gait database. © 2006 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/321309
ISSN
2023 Impact Factor: 8.3
2023 SCImago Journal Rankings: 2.299
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorXu, Dong-
dc.contributor.authorYan, Shuicheng-
dc.contributor.authorTao, Dacheng-
dc.contributor.authorZhang, Lei-
dc.contributor.authorLi, Xuelong-
dc.contributor.authorZhang, Hong Jiang-
dc.date.accessioned2022-11-03T02:18:03Z-
dc.date.available2022-11-03T02:18:03Z-
dc.date.issued2006-
dc.identifier.citationIEEE Transactions on Circuits and Systems for Video Technology, 2006, v. 16, n. 7, p. 896-903-
dc.identifier.issn1051-8215-
dc.identifier.urihttp://hdl.handle.net/10722/321309-
dc.description.abstractHuman gait is an important biometric feature. It can be perceived from a great distance and has recently attracted greater attention in video-surveillance-related applications, such as closed-circuit television. We explore gait recognition based on a matrix representation in this paper. First, binary silhouettes over one gait cycle are averaged. As a result, each gait video sequence, containing a number of gait cycles, is represented by a series of gray-level averaged images. Then, a matrix-based unsupervised algorithm, namely coupled subspace analysis (CSA), is employed as a preprocessing step to remove noise and retain the most representative information. Finally, a supervised algorithm, namely discriminant analysis with tensor representation, is applied to further improve classification ability. This matrix-based scheme demonstrates a much better gait recognition performance than state-of-the-art algorithms on the standard USF HumanID Gait database. © 2006 IEEE.-
dc.languageeng-
dc.relation.ispartofIEEE Transactions on Circuits and Systems for Video Technology-
dc.subjectCoupled subspaces analysis (CSA)-
dc.subjectDimensionality reduction-
dc.subjectDiscriminant analysis with tensor representation (DATER)-
dc.subjectHuman gait recognition-
dc.subjectObject representation-
dc.titleHuman gait recognition with matrix representation-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TCSVT.2006.877418-
dc.identifier.scopuseid_2-s2.0-33746893801-
dc.identifier.volume16-
dc.identifier.issue7-
dc.identifier.spage896-
dc.identifier.epage903-
dc.identifier.isiWOS:000239440900011-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats