File Download
Supplementary

Conference Paper: Automated people counting using template matching and head search

TitleAutomated people counting using template matching and head search
Authors
Pang, GKHNg, CK
KeywordsAutomated people counting
Real-time image processing
Template matching
Issue Date2002
PublisherIEEE.
Citation
The 9th IEEE Conference on Mechatronics and Machine Vision in Practice, Chiang Mai, Thailand, 10-12 September 2002, p. 323-331 How to Cite?
AbstractPeople counting using image processing has been carried out for years. Conventional methods can count people accurately when only a few isolated people pass through a counting region in a non-crowded situation. In this paper, the emphasis is on people counting in a crowded environment and a method using head search and model matching is described. A camera is mounted vertically downwards viewing the people heads from the top. People head search can be used to locate some passengers. In addition, templates obtained from the perspective projection of the human model are used to locate and isolate individual person. Our approach cams at dealing with a congested situation where occlusion is a major problem. This paper describes a real-time, high-accuracy, automated people counting system that has been developed. Experimental results are illustrated and the effectiveness of the developed method for real-time application is verified.
Persistent Identifierhttp://hdl.handle.net/10722/48463

 

DC FieldValueLanguage
dc.contributor.authorPang, GKHen_HK
dc.contributor.authorNg, CKen_HK
dc.date.accessioned2008-05-22T04:13:50Z-
dc.date.available2008-05-22T04:13:50Z-
dc.date.issued2002en_HK
dc.identifier.citationThe 9th IEEE Conference on Mechatronics and Machine Vision in Practice, Chiang Mai, Thailand, 10-12 September 2002, p. 323-331en_HK
dc.identifier.urihttp://hdl.handle.net/10722/48463-
dc.description.abstractPeople counting using image processing has been carried out for years. Conventional methods can count people accurately when only a few isolated people pass through a counting region in a non-crowded situation. In this paper, the emphasis is on people counting in a crowded environment and a method using head search and model matching is described. A camera is mounted vertically downwards viewing the people heads from the top. People head search can be used to locate some passengers. In addition, templates obtained from the perspective projection of the human model are used to locate and isolate individual person. Our approach cams at dealing with a congested situation where occlusion is a major problem. This paper describes a real-time, high-accuracy, automated people counting system that has been developed. Experimental results are illustrated and the effectiveness of the developed method for real-time application is verified.en_HK
dc.format.extent4564403 bytes-
dc.format.extent4353 bytes-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypetext/plain-
dc.languageengen_HK
dc.publisherIEEE.en_HK
dc.relation.ispartofIEEE Conference on Mechatronics and Machine Vision in Practice-
dc.rights©2002 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.en_HK
dc.subjectAutomated people countingen_HK
dc.subjectReal-time image processingen_HK
dc.subjectTemplate matchingen_HK
dc.titleAutomated people counting using template matching and head searchen_HK
dc.typeConference_Paperen_HK
dc.identifier.emailPang, GKH: gpang@eee.hku.hken_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.hkuros82760-

Export via OAI-PMH Interface in XML Formats

OR

Export to Other Non-XML Formats