Open Access System for Information Sharing

Login Library

 

Article
Cited 1 time in webofscience Cited 3 time in scopus
Metadata Downloads
Full metadata record
Files in This Item:
There are no files associated with this item.
DC FieldValueLanguage
dc.contributor.authorCho, SH-
dc.contributor.authorKim, T-
dc.contributor.authorKim, D-
dc.date.accessioned2016-04-01T02:42:52Z-
dc.date.available2016-04-01T02:42:52Z-
dc.date.created2011-04-05-
dc.date.issued2010-08-
dc.identifier.issn0218-0014-
dc.identifier.other2010-OAK-0000021893-
dc.identifier.urihttps://oasis.postech.ac.kr/handle/2014.oak/25636-
dc.description.abstractThis paper proposes a pose robust human detection and identification method for sequences of stereo images using multiply-oriented 2D elliptical filters (MO2DEFs), which can detect and identify humans regardless of scale and pose. Four 2D elliptical filters with specific orientations are applied to a 2D spatial-depth histogram, and threshold values are used to detect humans. The human pose is then determined by finding the filter whose convolution result was maximal. Candidates are verified by either detecting the face or matching head-shoulder shapes. Human identification employs the human detection method for a sequence of input stereo images and identifies them as a registered human or a new human using the Bhattacharyya distance of the color histogram. Experimental results show that (1) the accuracy of pose angle estimation is about 88%, (2) human detection using the proposed method outperforms that of using the existing Object Oriented Scale Adaptive Filter (OOSAF) by 15-20%, especially in the case of posed humans, and (3) the human identification method has a nearly perfect accuracy.-
dc.description.statementofresponsibilityX-
dc.languageEnglish-
dc.publisherWORLD SCIENTIFIC PUBL CO PTE LTD-
dc.relation.isPartOfINTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE-
dc.subjectStereo image-
dc.subjecthuman detection-
dc.subjectmultiply-oriented 2D elliptical filter-
dc.subjectpose angle estimation-
dc.subjecthuman verification-
dc.subjectface detection-
dc.subjectshape matching-
dc.subjecthuman identification-
dc.subjectBhattacharyya distance-
dc.subjectPEDESTRIAN DETECTION-
dc.subjectTRACKING-
dc.titlePOSE ROBUST HUMAN DETECTION IN DEPTH IMAGES USING MULTIPLY-ORIENTED 2D ELLIPTICAL FILTERS-
dc.typeArticle-
dc.contributor.college컴퓨터공학과-
dc.identifier.doi10.1142/S0218001410008135-
dc.author.googleCho, SH-
dc.author.googleKim, T-
dc.author.googleKim, D-
dc.relation.volume24-
dc.relation.issue5-
dc.relation.startpage691-
dc.relation.lastpage717-
dc.contributor.id10054411-
dc.relation.journalINTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE-
dc.relation.indexSCI급, SCOPUS 등재논문-
dc.relation.sciSCIE-
dc.collections.nameJournal Papers-
dc.type.rimsART-
dc.identifier.bibliographicCitationINTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, v.24, no.5, pp.691 - 717-
dc.identifier.wosid000281194300002-
dc.date.tcdate2019-02-01-
dc.citation.endPage717-
dc.citation.number5-
dc.citation.startPage691-
dc.citation.titleINTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE-
dc.citation.volume24-
dc.contributor.affiliatedAuthorKim, D-
dc.identifier.scopusid2-s2.0-77956049620-
dc.description.journalClass1-
dc.description.journalClass1-
dc.description.wostc1-
dc.description.scptc2*
dc.date.scptcdate2018-05-121*
dc.type.docTypeArticle-
dc.subject.keywordAuthorStereo image-
dc.subject.keywordAuthorhuman detection-
dc.subject.keywordAuthormultiply-oriented 2D elliptical filter-
dc.subject.keywordAuthorpose angle estimation-
dc.subject.keywordAuthorhuman verification-
dc.subject.keywordAuthorface detection-
dc.subject.keywordAuthorshape matching-
dc.subject.keywordAuthorhuman identification-
dc.subject.keywordAuthorBhattacharyya distance-
dc.relation.journalWebOfScienceCategoryComputer Science, Artificial Intelligence-
dc.description.journalRegisteredClassscie-
dc.description.journalRegisteredClassscopus-
dc.relation.journalResearchAreaComputer Science-

qr_code

  • mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher

김대진KIM, DAI JIN
Dept of Computer Science & Enginrg
Read more

Views & Downloads

Browse