Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/44636
Citations
Scopus Web of Science® Altmetric
?
?
Full metadata record
DC FieldValueLanguage
dc.contributor.authorZhao, A.en
dc.contributor.authorBrooks, M.en
dc.contributor.authorDick, A.en
dc.date.issued2007en
dc.identifier.citationProceedings of the Fourth International Conference on Image and Graphics, 2007;. pp.513-518en
dc.identifier.isbn0769529291en
dc.identifier.isbn9780769529295en
dc.identifier.urihttp://hdl.handle.net/2440/44636-
dc.description©2007 IEEE.en
dc.description.abstractThis paper is concerned with improving target appearance models to realize robust object tracking. We explore the use of feature space other than the commonly used color space for object tracking. Specifically, we employ gradient information to be used separately as well as in conjunction with color information. Our target appearance model is then represented in the form of a histogram using its gradient and color feature spaces, and frame-to-frame tracking is performed using mean shift or local exhaustive search. By combining gradients with color, we build new appearance models with combined feature spaces. Based on our extensive testing of these models, we find that they can be used to track complex objects, such as full 360-degree rotating objects, appearance-changing objects, occluding objects and zooming objects.en
dc.description.statementofresponsibilityAn Zhao, Brooks, M.J. and Dick, A.R.en
dc.language.isoenen
dc.publisherIEEEen
dc.titleEnhanced appearance models for object trackingen
dc.typeConference paperen
dc.identifier.rmid0020076747en
dc.contributor.conferenceInternational Conference on Image and Graphics (4th : 2007 : Sichuan, China)en
dc.identifier.doi10.1109/ICIG.2007.64en
dc.publisher.placeUSAen
dc.identifier.pubid44746-
pubs.library.collectionComputer Science publicationsen
pubs.verification-statusVerifieden
pubs.publication-statusPublisheden
dc.identifier.orcidDick, A. [0000-0001-9049-7345]en
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
hdl_44636.pdf1.3 MBPublisher's PDFView/Open


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