Show simple item record

dc.contributor.authorTrulls Fortuny, Eduard
dc.contributor.authorKokkinos, Iasonas
dc.contributor.authorSanfeliu Cortés, Alberto
dc.contributor.authorMoreno-Noguer, Francesc
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament d'Enginyeria de Sistemes, Automàtica i Informàtica Industrial
dc.contributor.otherInstitut de Robòtica i Informàtica Industrial
dc.date.accessioned2016-04-05T08:27:39Z
dc.date.issued2016
dc.identifier.citationTrulls, E., Kokkinos, I., Sanfeliu, A., Moreno-Noguer, F. Dense segmentation-aware descriptors. A: "Dense Image Correspondences for Computer Vision". Springer, 2016, p. 83-107.
dc.identifier.isbn978-3-319-23048-1
dc.identifier.urihttp://hdl.handle.net/2117/85171
dc.description.abstractDense descriptors are becoming increasingly popular in a host of tasks, such as dense image correspondence, bag-of-words image classification, and label transfer. However, the extraction of descriptors on generic image points, rather than selecting geometric features, requires rethinking how to achieve invariance to nuisance parameters. In this work we pursue invariance to occlusions and background changes by introducing segmentation information within dense feature construction. The core idea is to use the segmentation cues to downplay the features coming from image areas that are unlikely to belong to the same region as the feature point. We show how to integrate this idea with dense SIFT, as well as with the dense scale- and rotation-invariant descriptor (SID). We thereby deliver dense descriptors that are invariant to background changes, rotation, and/or scaling. We explore the merit of our technique in conjunction with large displacement motion estimation and wide-baseline stereo, and demonstrate that exploiting segmentation information yields clear improvements.
dc.format.extent25 p.
dc.language.isoeng
dc.publisherSpringer
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
dc.subject.lcshComputer vision
dc.subject.othercomputer vision
dc.subject.otherfeature extraction.
dc.titleDense segmentation-aware descriptors
dc.typePart of book or chapter of book
dc.subject.lemacVisió per ordinador
dc.contributor.groupUniversitat Politècnica de Catalunya. VIS - Visió Artificial i Sistemes Intel.ligents
dc.contributor.groupUniversitat Politècnica de Catalunya. ROBiri - Grup de Robòtica de l'IRI
dc.identifier.doi10.1007/978-3-319-23048-1_5
dc.rights.accessRestricted access - publisher's policy
drac.iddocument17648018
dc.description.versionPostprint (published version)
dc.relation.projectidinfo:eu-repo/grantAgreement/EC/FP7/600796/EU/Intelligent Active MObility Aid RoBOT integrating Multimodal Communication/MOBOT
dc.relation.projectidinfo:eu-repo/grantAgreement/EC/FP7/600825/EU/Cognitive, Decentralized Coordination of Heterogeneous Multi-Robot Systems via Reconfigurable Task Planning/RECONFIG
dc.relation.projectidinfo:eu-repo/grantAgreement/EC/FP7/287617/EU/Aerial Robotics Cooperative Assembly System/ARCAS
dc.date.lift10000-01-01
upcommons.citation.authorTrulls, E.; Kokkinos, I.; Sanfeliu, A.; Moreno-Noguer, F.
upcommons.citation.publishedtrue
upcommons.citation.publicationNameDense Image Correspondences for Computer Vision
upcommons.citation.startingPage83
upcommons.citation.endingPage107


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder