File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Crowd segmentation based on fusion of appearance and motion features

TitleCrowd segmentation based on fusion of appearance and motion features
Authors
KeywordsCrowd segmentation
Human detection
Implicit shape model (ISM)
Coherent motion
Issue Date2011
PublisherIEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1800906
Citation
The 3rd Chinese Conference on Intelligent Visual Surveillance (IVS 2011), Beijing, Chinese, 1-2 December 2011. In Chinese Conference on Intelligent Visual Surveillance Proceedings, 2012, p. 105-108. How to Cite?
第三届全国智能视觉监控学术会议, 中国北京, 2011年12月1-2日. How to Cite?
AbstractCrowd segmentation is an important topic in a visual surveillance system. In this paper, crowd segmentation is formulated as a problem to cluster the feature points inside the foreground region with a set of rectangles. Coherent motion of feature points in an individual are fused with appearance cues around the feature points for crowd segmentation, which has improved the segmentation performance. Furthermore, three descriptors are proposed to extract the points with a non-articulated movement. Some results on the CAVIAR dataset have been shown. The results show that coherent motion cue can be used more reliably by considering the points with rigid motion only. © 2011 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/165268
ISBN

 

DC FieldValueLanguage
dc.contributor.authorHou, Yen_US
dc.contributor.authorPang, GKHen_US
dc.date.accessioned2012-09-20T08:16:35Z-
dc.date.available2012-09-20T08:16:35Z-
dc.date.issued2011en_US
dc.identifier.citationThe 3rd Chinese Conference on Intelligent Visual Surveillance (IVS 2011), Beijing, Chinese, 1-2 December 2011. In Chinese Conference on Intelligent Visual Surveillance Proceedings, 2012, p. 105-108.en_US
dc.identifier.citation第三届全国智能视觉监控学术会议, 中国北京, 2011年12月1-2日.-
dc.identifier.isbn978-1-4577-1833-5-
dc.identifier.urihttp://hdl.handle.net/10722/165268-
dc.description.abstractCrowd segmentation is an important topic in a visual surveillance system. In this paper, crowd segmentation is formulated as a problem to cluster the feature points inside the foreground region with a set of rectangles. Coherent motion of feature points in an individual are fused with appearance cues around the feature points for crowd segmentation, which has improved the segmentation performance. Furthermore, three descriptors are proposed to extract the points with a non-articulated movement. Some results on the CAVIAR dataset have been shown. The results show that coherent motion cue can be used more reliably by considering the points with rigid motion only. © 2011 IEEE.-
dc.languagechien_US
dc.publisherIEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1800906-
dc.relation.ispartofChinese Conference on Intelligent Visual Surveillance Proceedingsen_US
dc.rightsChinese Conference on Intelligent Visual Surveillance Proceedings. Copyright © IEEE.-
dc.rights©2011 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.subjectCrowd segmentation-
dc.subjectHuman detection-
dc.subjectImplicit shape model (ISM)-
dc.subjectCoherent motion-
dc.titleCrowd segmentation based on fusion of appearance and motion featuresen_US
dc.typeConference_Paperen_US
dc.identifier.emailHou, Y: h0795498@hku.hken_US
dc.identifier.emailPang, GKH: gpang@eee.hku.hk-
dc.identifier.authorityPang, GKH=rp00162en_US
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1109/IVSurv.2011.6157036-
dc.identifier.scopuseid_2-s2.0-84858176159-
dc.identifier.hkuros209044en_US
dc.identifier.hkuros210686-
dc.identifier.spage105-
dc.identifier.epage108-
dc.publisher.placeUnited States-
dc.customcontrol.immutablesml 130408-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats