Please use this identifier to cite or link to this item: https://hdl.handle.net/2440/77210
Citations
Scopus Web of Science® Altmetric
?
?
Full metadata record
DC FieldValueLanguage
dc.contributor.authorZhou, X.-
dc.contributor.authorLi, X.-
dc.contributor.authorChin, T.-
dc.contributor.authorSuter, D.-
dc.date.issued2012-
dc.identifier.citationProceedings of the 19th IEEE International Conference on Image Processing, held in Orlando, Florida, 30 September-3 October, 2012: pp.409-412-
dc.identifier.isbn9781467325325-
dc.identifier.issn1522-4880-
dc.identifier.urihttp://hdl.handle.net/2440/77210-
dc.description.abstractIn this paper, we propose a superpixel-driven method for level set tracking. In particular, by taking a superpixel-based speed function, the level set evolution is accelerated greatly. We define a mutual information based speed function using a superpixel-unit as the underlying representation, which captures the correlation of a superpixel with object/background. In order to enhance the robustness of our method, a shape prior is incorporated to constrain the contour evolution. Experimental results on a number of challenging sequences demonstrate the effectiveness and robustness of our method.-
dc.description.statementofresponsibilityXue Zhou, Xi Li, Tat-Jun Chin and D. Suter-
dc.language.isoen-
dc.publisherIEEE-
dc.relation.ispartofseriesIEEE International Conference on Image Processing ICIP-
dc.rights© Copyright 2012 IEEE - All rights reserved.-
dc.source.urihttp://dx.doi.org/10.1109/icip.2012.6466882-
dc.subjectTracking-
dc.subjectlevel set-
dc.subjectmutual information-
dc.subjectsuperpixel-
dc.titleSuperpixel-driven level set tracking-
dc.typeConference paper-
dc.contributor.conferenceIEEE International Conference on Image Processing (19th : 2012 : Orlando, Florida)-
dc.identifier.doi10.1109/ICIP.2012.6466882-
dc.publisher.placeUSA-
pubs.publication-statusPublished-
dc.identifier.orcidSuter, D. [0000-0001-6306-3023]-
Appears in Collections:Aurora harvest
Computer Science publications

Files in This Item:
There are no files associated with this item.


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