A Low-Complexity Pedestrian Detection Framework for Smart Video Surveillance Systems

Cited 7 time in webofscience Cited 0 time in scopus
  • Hit : 339
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorBilal, Muhammadko
dc.contributor.authorKhan, Asimko
dc.contributor.authorKhan, Muhammad Umar Karimko
dc.contributor.authorKyung, Chong-Minko
dc.date.accessioned2017-11-08T02:22:21Z-
dc.date.available2017-11-08T02:22:21Z-
dc.date.created2017-10-23-
dc.date.created2017-10-23-
dc.date.created2017-10-23-
dc.date.issued2017-10-
dc.identifier.citationIEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, v.27, no.10, pp.2260 - 2273-
dc.identifier.issn1051-8215-
dc.identifier.urihttp://hdl.handle.net/10203/226717-
dc.description.abstractPedestrian detection is a key problem in computer vision and is currently addressed with increasingly complex solutions involving compute-intensive features and classification schemes. In this scope, histogram of oriented gradients (HOG) in conjunction with linear support vector machine (SVM) classifier is considered to be the single most discriminative feature that has been adopted as a stand-alone detector as well as a key instrument in advance systems involving hybrid features and cascaded detectors. In this paper, we propose a pedestrian detection framework that is computationally less expensive as well as more accurate than HOG-linear SVM. The proposed scheme exploits the discriminating power of the locally significant gradients in building orientation histograms without involving complex floating point operations while computing the feature. The integer-only feature allows the use of powerful histogram inter-section kernel SVM classifier in a fast lookup-table-based implementation. Resultantly, the proposed framework achieves at least 3% more accurate detection results than HOG on standard data sets while being 1.8 and 2.6 times faster on conventional desktop PC and embedded ARM platforms, respectively, for a single scale pedestrian detection on VGA resolution video. In addition, hardware implementation on Altera Cyclone IV field-programmable gate array results in more than 40% savings in logic resources compared with its HOG-linear SVM competitor. Hence, the proposed feature and classification setup is shown to be a better candidate as the single most discriminative pedestrian detector than the currently accepted HOG-linear SVM.-
dc.languageEnglish-
dc.publisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC-
dc.subjectHOG FEATURE-EXTRACTION-
dc.subjectTIME OBJECT DETECTION-
dc.subjectORIENTED GRADIENTS-
dc.subjectPERFORMANCE EVALUATION-
dc.subjectCLASSIFICATION-
dc.subjectHISTOGRAMS-
dc.subjectANALYTICS-
dc.subjectFEATURES-
dc.subjectSINGLE-
dc.titleA Low-Complexity Pedestrian Detection Framework for Smart Video Surveillance Systems-
dc.typeArticle-
dc.identifier.wosid000412466700016-
dc.identifier.scopusid2-s2.0-85032278004-
dc.type.rimsART-
dc.citation.volume27-
dc.citation.issue10-
dc.citation.beginningpage2260-
dc.citation.endingpage2273-
dc.citation.publicationnameIEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY-
dc.identifier.doi10.1109/TCSVT.2016.2581660-
dc.contributor.localauthorKyung, Chong-Min-
dc.contributor.nonIdAuthorBilal, Muhammad-
dc.description.isOpenAccessN-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorField-programmable gate array (FPGA)-
dc.subject.keywordAuthorhistogram intersection kernel (HIK) support vector machine (SVM)-
dc.subject.keywordAuthorhistogram of gradients-
dc.subject.keywordAuthorlinear SVM-
dc.subject.keywordAuthorpedestrian detection-
dc.subject.keywordPlusHOG FEATURE-EXTRACTION-
dc.subject.keywordPlusTIME OBJECT DETECTION-
dc.subject.keywordPlusORIENTED GRADIENTS-
dc.subject.keywordPlusPERFORMANCE EVALUATION-
dc.subject.keywordPlusCLASSIFICATION-
dc.subject.keywordPlusHISTOGRAMS-
dc.subject.keywordPlusANALYTICS-
dc.subject.keywordPlusFEATURES-
dc.subject.keywordPlusSINGLE-
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 7 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0