Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/120066
Citations
Scopus Web of Science® Altmetric
?
?
Full metadata record
DC FieldValueLanguage
dc.contributor.authorPham, T.en
dc.contributor.authorDo, T.en
dc.contributor.authorSunderhauf, N.en
dc.contributor.authorReid, I.en
dc.date.issued2018en
dc.identifier.citation2018 IEEE International Conference on Robotics and Automation (ICRA), 2018 / pp.3213-3220en
dc.identifier.isbn1538630818en
dc.identifier.isbn9781538630815en
dc.identifier.issn1050-4729en
dc.identifier.issn2577-087Xen
dc.identifier.urihttp://hdl.handle.net/2440/120066-
dc.description.abstractThis paper presents SceneCut, a novel approach to jointly discover previously unseen objects and non-object surfaces using a single RGB-D image. SceneCut's joint reasoning over scene semantics and geometry allows a robot to detect and segment object instances in complex scenes where modern deep learning-based methods either fail to separate object instances, or fail to detect objects that were not seen during training. SceneCut automatically decomposes a scene into meaningful regions which either represent objects or scene surfaces. The decomposition is qualified by an unified energy function over objectness and geometric fitting. We show how this energy function can be optimized efficiently by utilizing hierarchical segmentation trees. Moreover, we leverage a pre-trained convolutional oriented boundary network to predict accurate boundaries from images, which are used to construct high-quality region hierarchies. We evaluate SceneCut on several different indoor environments, and the results show that SceneCut significantly outperforms all the existing methods.en
dc.description.statementofresponsibilityTrung T. Pham, Thanh-Toan Do, Niko Sünderhauf, Ian Reiden
dc.language.isoenen
dc.publisherIEEEen
dc.relation.ispartofseriesPiscataway, NJ.en
dc.rights©2018 IEEEen
dc.titleSceneCut: joint geometric and object segmentation for indoor scenesen
dc.typeConference paperen
dc.identifier.rmid0030111876en
dc.contributor.conferenceIEEE International Conference on Robotics and Automation (ICRA) (21 May 2018 - 25 May 2018 : Brisbane, Australia)en
dc.identifier.doi10.1109/ICRA.2018.8461108en
dc.relation.granthttp://purl.org/au-research/grants/arc/CE140100016en
dc.relation.granthttp://purl.org/au-research/grants/arc/FL130100102en
dc.identifier.pubid443657-
pubs.library.collectionComputer Science publicationsen
pubs.library.teamDS05en
pubs.verification-statusVerifieden
pubs.publication-statusPublisheden
dc.identifier.orcidReid, I. [0000-0001-7790-6423]en
Appears in Collections: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.