File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Bayesian 3D model based human detection in crowded scenes using efficient optimization

TitleBayesian 3D model based human detection in crowded scenes using efficient optimization
Authors
Keywords3D models
Bayesian
Computational costs
Data sets
Edge information
Issue Date2011
PublisherIEEE.
Citation
The 2011 IEEE Workshop on Applications of Computer Vision (WACV 2011), Kona, HI., 5-7 January 2011. In Proceedings of WACV2011, 2011, p. 557-563 How to Cite?
AbstractIn this paper, we solve the problem of human detection in crowded scenes using a Bayesian 3D model based method. Human candidates are first nominated by a head detector and a foot detector, then optimization is performed to find the best configuration of the candidates and their corresponding shape models. The solution is obtained by decomposing the mutually related candidates into un-occluded ones and occluded ones in each iteration, and then performing model matching for the un-occluded candidates. To this end, in addition to some obvious clues, we also derive a graph that depicts the inter-object relation so that unreasonable decomposition is avoided. The merit of the proposed optimization procedure is that its computational cost is similar to the greedy optimization methods while its performance is comparable to the global optimization approaches. For model matching, it is performed by employing both prior knowledge and image likelihood, where the priors include the distribution of individual shape models and the restriction on the inter-object distance in real world, and image likelihood is provided by foreground extraction and the edge information. After the model matching, a validation and rejection strategy based on minimum description length is applied to confirm the candidates that have reliable matching results. The proposed method is tested on both the publicly available Caviar dataset and a challenging dataset constructed by ourselves. The experimental results demonstrate the effectiveness of our approach. © 2010 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/137725
ISSN
References

 

DC FieldValueLanguage
dc.contributor.authorWang, Len_HK
dc.contributor.authorYung, NHCen_HK
dc.date.accessioned2011-08-26T14:32:27Z-
dc.date.available2011-08-26T14:32:27Z-
dc.date.issued2011en_HK
dc.identifier.citationThe 2011 IEEE Workshop on Applications of Computer Vision (WACV 2011), Kona, HI., 5-7 January 2011. In Proceedings of WACV2011, 2011, p. 557-563en_HK
dc.identifier.issn1550-5790en_US
dc.identifier.urihttp://hdl.handle.net/10722/137725-
dc.description.abstractIn this paper, we solve the problem of human detection in crowded scenes using a Bayesian 3D model based method. Human candidates are first nominated by a head detector and a foot detector, then optimization is performed to find the best configuration of the candidates and their corresponding shape models. The solution is obtained by decomposing the mutually related candidates into un-occluded ones and occluded ones in each iteration, and then performing model matching for the un-occluded candidates. To this end, in addition to some obvious clues, we also derive a graph that depicts the inter-object relation so that unreasonable decomposition is avoided. The merit of the proposed optimization procedure is that its computational cost is similar to the greedy optimization methods while its performance is comparable to the global optimization approaches. For model matching, it is performed by employing both prior knowledge and image likelihood, where the priors include the distribution of individual shape models and the restriction on the inter-object distance in real world, and image likelihood is provided by foreground extraction and the edge information. After the model matching, a validation and rejection strategy based on minimum description length is applied to confirm the candidates that have reliable matching results. The proposed method is tested on both the publicly available Caviar dataset and a challenging dataset constructed by ourselves. The experimental results demonstrate the effectiveness of our approach. © 2010 IEEE.en_HK
dc.languageengen_US
dc.publisherIEEE.en_US
dc.relation.ispartofProceedings of the IEEE Workshop on Applications of Computer Vision, WACV2011en_HK
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.rightsIEEE Workshop on Applications of Computer Vision 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.subject3D models-
dc.subjectBayesian-
dc.subjectComputational costs-
dc.subjectData sets-
dc.subjectEdge information-
dc.titleBayesian 3D model based human detection in crowded scenes using efficient optimizationen_HK
dc.typeConference_Paperen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=1550-5790&volume=&spage=557&epage=563&date=2011&atitle=Bayesian+3D+model+based+human+detection+in+crowded+scenes+using+efficient+optimizationen_US
dc.identifier.emailYung, NHC:nyung@eee.hku.hken_HK
dc.identifier.authorityYung, NHC=rp00226en_HK
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1109/WACV.2011.5711553en_HK
dc.identifier.scopuseid_2-s2.0-79952492530en_HK
dc.identifier.hkuros191019en_US
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-79952492530&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.spage557en_HK
dc.identifier.epage563en_HK
dc.description.otherThe 2011 IEEE Workshop on Applications of Computer Vision (WACV 2011), Kona, HI., 5-7 January 2011. In Proceedings of WACV2011, 2011, p. 557-563-
dc.identifier.scopusauthoridWang, L=35728037200en_HK
dc.identifier.scopusauthoridYung, NHC=7003473369en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats