File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Three-dimensional model-based human detection in crowded scenes

TitleThree-dimensional model-based human detection in crowded scenes
Authors
KeywordsBayesian Method
Crowd Segmentation
Human Detection
Model-Based Method
Video Surveillance
Issue Date2012
PublisherI E E E. The Journal's web site is located at http://www.ewh.ieee.org/tc/its/trans.html
Citation
Ieee Transactions On Intelligent Transportation Systems, 2012, v. 13 n. 2, p. 691-703 How to Cite?
AbstractIn this paper, the problem of human detection in crowded scenes is formulated as a maximum a posteriori problem, in which, given a set of candidates, predefined 3-D human shape models are matched with image evidence, provided by foreground extraction and probability of boundary, to estimate the human configuration. The optimal solution is obtained by decomposing the mutually related candidates into unoccluded and occluded ones in each iteration according to a graph description of the candidate relations and then only matching models for the unoccluded candidates. A candidate validation and rejection process based on minimum description length and local occlusion reasoning is carried out after each iteration of model matching. The advantage of the proposed optimization procedure is that its computational cost is much smaller than that of global optimization methods, while its performance is comparable to them. The proposed method achieves a detection rate of about 2% higher on a subset of images of the Caviar data set than the best result reported by previous works. We also demonstrate the performance of the proposed method using another challenging data set. © 2011 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/155766
ISSN
2015 Impact Factor: 2.534
2015 SCImago Journal Rankings: 1.300
ISI Accession Number ID
Funding AgencyGrant Number
Research Grant Council of the Hong Kong Special Administrative Region, ChinaHKU719608E
University of Hong Kong
Funding Information:

Manuscript received November 29, 2010; revised August 13, 2011 and November 4, 2011; accepted November 13, 2011. Date of publication January 14, 2012; date of current version May 30, 2012. This work was supported in part by a Grant from the Research Grant Council of the Hong Kong Special Administrative Region, China, under Project HKU719608E and in part by the Postgraduate Studentship of the University of Hong Kong. The Associate Editor for this paper was J. Zhang.

References

 

DC FieldValueLanguage
dc.contributor.authorWang, Len_US
dc.contributor.authorYung, NHCen_US
dc.date.accessioned2012-08-08T08:35:14Z-
dc.date.available2012-08-08T08:35:14Z-
dc.date.issued2012en_US
dc.identifier.citationIeee Transactions On Intelligent Transportation Systems, 2012, v. 13 n. 2, p. 691-703en_US
dc.identifier.issn1524-9050en_US
dc.identifier.urihttp://hdl.handle.net/10722/155766-
dc.description.abstractIn this paper, the problem of human detection in crowded scenes is formulated as a maximum a posteriori problem, in which, given a set of candidates, predefined 3-D human shape models are matched with image evidence, provided by foreground extraction and probability of boundary, to estimate the human configuration. The optimal solution is obtained by decomposing the mutually related candidates into unoccluded and occluded ones in each iteration according to a graph description of the candidate relations and then only matching models for the unoccluded candidates. A candidate validation and rejection process based on minimum description length and local occlusion reasoning is carried out after each iteration of model matching. The advantage of the proposed optimization procedure is that its computational cost is much smaller than that of global optimization methods, while its performance is comparable to them. The proposed method achieves a detection rate of about 2% higher on a subset of images of the Caviar data set than the best result reported by previous works. We also demonstrate the performance of the proposed method using another challenging data set. © 2011 IEEE.en_US
dc.languageengen_US
dc.publisherI E E E. The Journal's web site is located at http://www.ewh.ieee.org/tc/its/trans.htmlen_US
dc.relation.ispartofIEEE Transactions on Intelligent Transportation Systemsen_US
dc.rightsIEEE Transactions on Intelligent Transportation Systems. Copyright © IEEE.-
dc.rights©20xx 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.subjectBayesian Methoden_US
dc.subjectCrowd Segmentationen_US
dc.subjectHuman Detectionen_US
dc.subjectModel-Based Methoden_US
dc.subjectVideo Surveillanceen_US
dc.titleThree-dimensional model-based human detection in crowded scenesen_US
dc.typeArticleen_US
dc.identifier.emailYung, NHC:nyung@eee.hku.hken_US
dc.identifier.authorityYung, NHC=rp00226en_US
dc.description.naturepublished_or_final_versionen_US
dc.identifier.doi10.1109/TITS.2011.2179536en_US
dc.identifier.scopuseid_2-s2.0-84862784934-
dc.identifier.hkuros201092-
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-84861856233&selection=ref&src=s&origin=recordpageen_US
dc.identifier.volume13en_US
dc.identifier.issue2en_US
dc.identifier.spage691en_US
dc.identifier.epage703en_US
dc.identifier.isiWOS:000304907000024-
dc.publisher.placeUnited Statesen_US
dc.identifier.scopusauthoridWang, L=54904062500en_US
dc.identifier.scopusauthoridYung, NHC=7003473369en_US

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats