Multi-hypothesis contextual modeling for semantic segmentation

Basit Öğe Kaydı
dc.authorid0000-0002-6842-1528
dc.contributor.authorAteş, Hasan Fehmien_US
dc.contributor.authorSünetci, Sercanen_US
dc.date.accessioned2019-03-19T01:42:37Z
dc.date.available2019-03-19T01:42:37Z
dc.date.issued2019-01-01
dc.departmentIşık Üniversitesi, Mühendislik Fakültesi, Elektrik-Elektronik Mühendisliği Bölümüen_US
dc.departmentIşık University, Faculty of Engineering, Department of Electrical-Electronics Engineeringen_US
dc.description.abstractSemantic segmentation (i.e. image parsing) aims to annotate each image pixel with its corresponding semantic class label. Spatially consistent labeling of the image requires an accurate description and modeling of the local contextual information. Segmentation result is typically improved by Markov Random Field (MRF) optimization on the initial labels. However this improvement is limited by the accuracy of initial result and how the contextual neighborhood is defined. In this paper, we develop generalized and flexible contextual models for segmentation neighborhoods in order to improve parsing accuracy. Instead of using a fixed segmentation and neighborhood definition, we explore various contextual models for fusion of complementary information available in alternative segmentations of the same image. In other words, we propose a novel MRF framework that describes and optimizes the contextual dependencies between multiple segmentations. Simulation results on two common datasets demonstrate significant improvement in parsing accuracy over the baseline approaches.en_US
dc.description.sponsorshipThis work is supported in part by TUBITAK project no: 115E307 and by Isik University BAP project no: 14A205en_US
dc.description.versionPublisher's Versionen_US
dc.identifier.citationAteş, H. F. & Sünetci, S. (2019). Multi-hypothesis contextual modeling for semantic segmentation. Pattern Recognition Letters, 117, 104-110. doi:10.1016/j.patrec.2018.12.011en_US
dc.identifier.doi10.1016/j.patrec.2018.12.011
dc.identifier.endpage110
dc.identifier.issn0167-8655
dc.identifier.issn1872-7344
dc.identifier.scopus2-s2.0-85058782768
dc.identifier.scopusqualityQ1
dc.identifier.startpage104
dc.identifier.urihttps://hdl.handle.net/11729/1482
dc.identifier.urihttp://dx.doi.org/10.1016/j.patrec.2018.12.011
dc.identifier.volume117
dc.identifier.wosWOS:000455196900015
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.indekslendigikaynakScience Citation Index Expanded (SCI-EXPANDED)en_US
dc.institutionauthorSünetci, Sercanen_US
dc.language.isoenen_US
dc.peerreviewedYesen_US
dc.publicationstatusPublisheden_US
dc.publisherElsevier Science BVen_US
dc.relation.ispartofPattern Recognition Lettersen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectImage parsingen_US
dc.subjectSegmentationen_US
dc.subjectSuperpixelen_US
dc.subjectMRFen_US
dc.subjectSceneen_US
dc.titleMulti-hypothesis contextual modeling for semantic segmentationen_US
dc.typeArticleen_US
dspace.entity.typePublication

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
1482.pdf
Boyut:
1.08 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Publisher's Version
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.71 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Makale Koleksiyonu | Elektrik-Elektronik Mühendisliği Bölümü
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu