Filtering airborne LIDAR data by using fully convolutional networks

dc.contributor.authorVarlik, Abdullah
dc.contributor.authorUray, Firat
dc.date.accessioned2024-02-23T14:17:12Z
dc.date.available2024-02-23T14:17:12Z
dc.date.issued2023
dc.departmentNEÜen_US
dc.description.abstractThe classification of LIDAR point clouds has always been a challenging task. Classification refers to label each point in different categories, such as ground, vegetation or building. The success of deep learning techniques in image processing tasks have encouraged researchers to use deep neural networks for classification of LIDAR point clouds. In this paper, we proposed a U-Net based architecture capable of classifying LIDAR data. The results indicated that our network model achieved an average F1 score of 91% over all three classes (ground, vegetation and building) for our best model.en_US
dc.identifier.doi10.1080/00396265.2021.1996798
dc.identifier.endpage31en_US
dc.identifier.issn0039-6265
dc.identifier.issn1752-2706
dc.identifier.issue388en_US
dc.identifier.scopus2-s2.0-85119301168en_US
dc.identifier.scopusqualityQ2en_US
dc.identifier.startpage21en_US
dc.identifier.urihttps://doi.org/10.1080/00396265.2021.1996798
dc.identifier.urihttps://hdl.handle.net/20.500.12452/12984
dc.identifier.volume55en_US
dc.identifier.wosWOS:000717878100001en_US
dc.identifier.wosqualityQ4en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherTaylor & Francis Ltden_US
dc.relation.ispartofSurvey Reviewen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectLidaren_US
dc.subjectDeep Learningen_US
dc.subjectPoint Cloudsen_US
dc.subjectPoint Cloud Classificationen_US
dc.subjectPoint Cloud Segmentationen_US
dc.subjectRemote Sensingen_US
dc.titleFiltering airborne LIDAR data by using fully convolutional networksen_US
dc.typeArticleen_US

Dosyalar