Recursive On-Line (2D)(2)PCA and Its Application to Long-Term Background Subtraction

Cited 9 time in webofscience Cited 0 time in scopus
  • Hit : 304
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorSeo, Ja Wonko
dc.contributor.authorKim, Seong-Daeko
dc.date.accessioned2015-04-07T02:45:28Z-
dc.date.available2015-04-07T02:45:28Z-
dc.date.created2014-12-29-
dc.date.created2014-12-29-
dc.date.issued2014-12-
dc.identifier.citationIEEE TRANSACTIONS ON MULTIMEDIA, v.16, no.8, pp.2333 - 2344-
dc.identifier.issn1520-9210-
dc.identifier.urihttp://hdl.handle.net/10203/195133-
dc.description.abstractIn this paper, we propose a novel background subtraction method which enables reliable detection of foreground objects in a long surveillance video stream. Recently, although much progress has been made in the field of background subtraction, there are still challenging scenarios (e. g., high frequency motion of dynamic texture, non-stationary motion of camera, abrupt changes of illumination, etc.) in the long surveillance videos in which even state-of-the-art methods are often prone to fail. To cope with these challenging scenarios effectively, in the proposed method, a background model is initialized in a low-dimensional subspace and then updated periodically based on a novel recursive on-line (2D)(2)PCA algorithm developed in this paper. Moreover, a threshold map is also updated in a scene-adaptive manner for labeling each pixel in a scene either foreground or background independently. Based on this on-line framework, the background of a surveillance video stream is reconstructed over time, thereby facilitating the detection of foreground objects reliably. In extensive experiments, we demonstrate that the proposed background subtraction method can cope with the aforementioned challenging scenarios more favorably than the state-of-the-art methods.-
dc.languageEnglish-
dc.publisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC-
dc.subjectOBJECT DETECTION-
dc.subjectFACE REPRESENTATION-
dc.subject2-DIMENSIONAL PCA-
dc.subjectDYNAMIC SCENES-
dc.subjectCODEBOOK MODEL-
dc.subjectRECOGNITION-
dc.subjectFRAMEWORK-
dc.titleRecursive On-Line (2D)(2)PCA and Its Application to Long-Term Background Subtraction-
dc.typeArticle-
dc.identifier.wosid000345571300021-
dc.identifier.scopusid2-s2.0-84912107755-
dc.type.rimsART-
dc.citation.volume16-
dc.citation.issue8-
dc.citation.beginningpage2333-
dc.citation.endingpage2344-
dc.citation.publicationnameIEEE TRANSACTIONS ON MULTIMEDIA-
dc.identifier.doi10.1109/TMM.2014.2353772-
dc.contributor.localauthorKim, Seong-Dae-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorBackground model-
dc.subject.keywordAuthorlong-term background subtraction-
dc.subject.keywordAuthorobject detection-
dc.subject.keywordAuthorrecursive on-line (2D)(2)PCA (two-directional two-dimensional principal component analysis)-
dc.subject.keywordPlusOBJECT DETECTION-
dc.subject.keywordPlusFACE REPRESENTATION-
dc.subject.keywordPlus2-DIMENSIONAL PCA-
dc.subject.keywordPlusDYNAMIC SCENES-
dc.subject.keywordPlusCODEBOOK MODEL-
dc.subject.keywordPlusRECOGNITION-
dc.subject.keywordPlusFRAMEWORK-
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 9 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0