Semantic Segmentation of High-Resolution Airborne Images with Dual-Stream DeepLabV3+

Basit Öğe Kaydı
dc.authoridAYDAR, Umut/0000-0002-3987-6435
dc.authoridAkcay, Ozgun/0000-0003-0474-7518
dc.authoridAvsar, Emin Ozgur/0000-0002-3804-1209
dc.authoridKINACI, AHMET CUMHUR/0000-0002-8832-5453
dc.contributor.authorAkcay, Ozgun
dc.contributor.authorKinaci, Ahmet Cumhur
dc.contributor.authorAvsar, Emin Ozgur
dc.contributor.authorAydar, Umut
dc.date.accessioned2025-01-27T20:20:46Z
dc.date.available2025-01-27T20:20:46Z
dc.date.issued2022
dc.departmentÇanakkale Onsekiz Mart Üniversitesi
dc.description.abstractIn geospatial applications such as urban planning and land use management, automatic detection and classification of earth objects are essential and primary subjects. When the significant semantic segmentation algorithms are considered, DeepLabV3+ stands out as a state-of-the-art CNN. Although the DeepLabV3+ model is capable of extracting multi-scale contextual information, there is still a need for multi-stream architectural approaches and different training approaches of the model that can leverage multi-modal geographic datasets. In this study, a new end-to-end dual-stream architecture that considers geospatial imagery was developed based on the DeepLabV3+ architecture. As a result, the spectral datasets other than RGB provided increments in semantic segmentation accuracies when they were used as additional channels to height information. Furthermore, both the given data augmentation and Tversky loss function which is sensitive to imbalanced data accomplished better overall accuracies. Also, it has been shown that the new dual-stream architecture using Potsdam and Vaihingen datasets produced 88.87% and 87.39% overall semantic segmentation accuracies, respectively. Eventually, it was seen that enhancement of the traditional significant semantic segmentation networks has a great potential to provide higher model performances, whereas the contribution of geospatial data as the second stream to RGB to segmentation was explicitly shown.
dc.description.sponsorshipScientific and Technological Research Council of Turkey (TUEBITAK) [119Y363]
dc.description.sponsorshipThis research was funded by The Scientific and Technological Research Council of Turkey (TUEBITAK), Project No: 119Y363.
dc.identifier.doi10.3390/ijgi11010023
dc.identifier.issn2220-9964
dc.identifier.issue1
dc.identifier.scopus2-s2.0-85123266413
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.3390/ijgi11010023
dc.identifier.urihttps://hdl.handle.net/20.500.12428/21810
dc.identifier.volume11
dc.identifier.wosWOS:000748827400001
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherMdpi
dc.relation.ispartofIsprs International Journal of Geo-Information
dc.relation.publicationcategoryinfo:eu-repo/semantics/openAccess
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_WoS_20250125
dc.subjectdeep learning
dc.subjectsemantic segmentation
dc.subjectphotogrammetry
dc.subjectmulti-spectral aerial imagery
dc.subjectdigital surface model
dc.subjectvegetation index
dc.subjectland cover classification
dc.titleSemantic Segmentation of High-Resolution Airborne Images with Dual-Stream DeepLabV3+
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu