File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Human face tracking system with multiple non-overlapping cameras

TitleHuman face tracking system with multiple non-overlapping cameras
Authors
Issue Date2011
Citation
Proceedings - 3Rd International Conference On Data Mining And Intelligent Information Technology Applications, Icmia 2011, 2011, p. 176-179 How to Cite?
Abstract
A novel human face tracking system with multiple cameras is proposed in this article. Unlike most surveillance approaches requiring overlapping field of views (FOVs) for tracking targets across multiple cameras, our proposed system utilizes face recognition as cue to build correspondence between cameras, and is therefore compatible with application with non-overlapping FOVs. Face recognition achieves great success in recent years, however it has an intrinsic limitation of low tolerance to face pose changes. In the proposed system, face reconstruction technology is adopted to transform non-frontal human face to a frontal one to substantially enhance the usability of face recognition, so that correspondence of humans across multiple trajectories can be reliably established. © 2011 AICIT.
Persistent Identifierhttp://hdl.handle.net/10722/152030
ISBN
References

 

DC FieldValueLanguage
dc.contributor.authorHe, XCen_US
dc.contributor.authorYuk, SCen_US
dc.contributor.authorLuo, Ten_US
dc.contributor.authorChow, KPen_US
dc.contributor.authorWong, KYKen_US
dc.contributor.authorChung, RHYen_US
dc.date.accessioned2012-06-26T06:32:39Z-
dc.date.available2012-06-26T06:32:39Z-
dc.date.issued2011en_US
dc.identifier.citationProceedings - 3Rd International Conference On Data Mining And Intelligent Information Technology Applications, Icmia 2011, 2011, p. 176-179en_US
dc.identifier.isbn978-898867848-0-
dc.identifier.urihttp://hdl.handle.net/10722/152030-
dc.description.abstractA novel human face tracking system with multiple cameras is proposed in this article. Unlike most surveillance approaches requiring overlapping field of views (FOVs) for tracking targets across multiple cameras, our proposed system utilizes face recognition as cue to build correspondence between cameras, and is therefore compatible with application with non-overlapping FOVs. Face recognition achieves great success in recent years, however it has an intrinsic limitation of low tolerance to face pose changes. In the proposed system, face reconstruction technology is adopted to transform non-frontal human face to a frontal one to substantially enhance the usability of face recognition, so that correspondence of humans across multiple trajectories can be reliably established. © 2011 AICIT.en_US
dc.languageengen_US
dc.relation.ispartofProceedings - 3rd International Conference on Data Mining and Intelligent Information Technology Applications, ICMIA 2011en_US
dc.titleHuman face tracking system with multiple non-overlapping camerasen_US
dc.typeConference_Paperen_US
dc.identifier.emailChow, KP:chow@cs.hku.hken_US
dc.identifier.emailWong, KYK:kykwong@cs.hku.hken_US
dc.identifier.emailChung, RHY:hychung@cs.hku.hken_US
dc.identifier.authorityChow, KP=rp00111en_US
dc.identifier.authorityWong, KYK=rp01393en_US
dc.identifier.authorityChung, RHY=rp00219en_US
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.scopuseid_2-s2.0-84863395052en_US
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-84855839214&selection=ref&src=s&origin=recordpageen_US
dc.identifier.spage176en_US
dc.identifier.epage179en_US
dc.identifier.scopusauthoridHe, XC=25645571900en_US
dc.identifier.scopusauthoridYuk, SC=12764865300en_US
dc.identifier.scopusauthoridLuo, T=16064613200en_US
dc.identifier.scopusauthoridChow, KP=7202180751en_US
dc.identifier.scopusauthoridWong, KYK=24402187900en_US
dc.identifier.scopusauthoridChung, RHY=14059962600en_US

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats