Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Adaptive Combination of Local Motion, Appearance, and Shape for Video Segmentation

Full metadata record
DC Field Value Language
dc.contributor.authorShim, Woo-sung-
dc.contributor.authorKim, Se-hoon-
dc.contributor.authorLee, Soochahn-
dc.date.accessioned2021-08-11T16:44:40Z-
dc.date.available2021-08-11T16:44:40Z-
dc.date.issued2016-11-
dc.identifier.issn1062-3701-
dc.identifier.issn1943-3522-
dc.identifier.urihttps://scholarworks.bwise.kr/sch/handle/2021.sw.sch/8623-
dc.description.abstractIn this paper, we propose an accurate and robust video segmentation method. The main contributions are threefold: (1) multiple cues (appearance and shape) are explicitly used and adaptively combined to determine segment probability; (2) motion is implicitly used to compute the shape cue; and (3) the segment labeling is improved by utilizing geodesic graph cuts. Experimental results show the effectiveness of the proposed method. (C) 2016 Society for Imaging Science and Technology.-
dc.language영어-
dc.language.isoENG-
dc.publisherSociety for Imaging Science and Technology-
dc.titleAdaptive Combination of Local Motion, Appearance, and Shape for Video Segmentation-
dc.typeArticle-
dc.publisher.location미국-
dc.identifier.doi10.2352/J.ImagingSci.Technol.2016.60.6.060409-
dc.identifier.scopusid2-s2.0-85041544343-
dc.identifier.wosid000393112000011-
dc.identifier.bibliographicCitationJournal of Imaging Science and Technology, v.60, no.6-
dc.citation.titleJournal of Imaging Science and Technology-
dc.citation.volume60-
dc.citation.number6-
dc.type.docTypeArticle-
dc.description.isOpenAccessN-
dc.description.journalRegisteredClasssci-
dc.description.journalRegisteredClassscie-
dc.description.journalRegisteredClassscopus-
dc.relation.journalResearchAreaImaging Science & Photographic Technology-
dc.relation.journalWebOfScienceCategoryImaging Science & Photographic Technology-
dc.subject.keywordAuthorVideo Segmentation-
dc.subject.keywordAuthorAdaptive Combination-
dc.subject.keywordAuthorLocal Motion-
dc.subject.keywordAuthorLocal Shape-
dc.subject.keywordAuthorLocal Appearance-
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Engineering > Department of Electronic Engineering > 1. Journal Articles

qrcode

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

Altmetrics

Total Views & Downloads

BROWSE