Show simple item record

dc.contributor.authorSmolic, Aljosa
dc.contributor.authorZolanvari, S.M. Iman
dc.contributor.authorRuano, Susana
dc.contributor.authorRana, Aakanksha
dc.contributor.authorCumins, Alan
dc.contributor.authorda Silva, Rogerio Eduardo
dc.contributor.authorRahbar, Morteza
dc.date.accessioned2020-02-18T17:11:36Z
dc.date.available2020-02-18T17:11:36Z
dc.date.issued2019
dc.date.submitted2019en
dc.identifier.citationZolanvari, S.M.I., Ruano, S., Rana, A., Cummins, A., da Silva, R.E., Rahbar, M. & Smolic, A., DublinCity: Annotated LiDAR Point Cloud and its Applications, BMVC 30th British Machine Vision Conference, Forthcoming, 2019en
dc.identifier.otherY
dc.identifier.urihttps://v-sense.scss.tcd.ie/wp-content/uploads/2019/08/BMVC_2019_PointCloud__Copy_-2.pdf
dc.identifier.urihttp://hdl.handle.net/2262/91577
dc.descriptionPUBLISHEDen
dc.description.abstractScene understanding of full-scale 3D models of an urban area remains a challenging task. While advanced computer vision techniques offer cost-effective approaches to analyse 3D urban elements, a precise and densely labelled dataset is quintessential. The paper presents the first-ever labelled dataset for a highly dense Aerial Laser Scanning (ALS) point cloud at city-scale. This work introduces a novel benchmark dataset that includes a manually annotated point cloud for over 260 million laser scanning points into 100’000 (approx.) assets from Dublin LiDAR point cloud [12] in 2015. Objects are labelled into 13 classes using hierarchical levels of detail from large (i.e. building, vegetation and ground) to refined (i.e. window, door and tree) elements. To validate the performance of our dataset, two different applications are showcased. Firstly, the labelled point cloud is employed for training Convolutional Neural Networks (CNNs) to classify urban elements. The dataset is tested on the well-known state-of-the-art CNNs (i.e. PointNet, PointNet++ and So-Net). Secondly, the complete ALS dataset is applied as detailed ground truth for city-scale image-based 3D reconstruction.en
dc.language.isoenen
dc.rightsYen
dc.subject3D modelsen
dc.subjectAerial Laser Scanningen
dc.subjectLiDAR Point Clouden
dc.subjectUrban areasen
dc.titleDublinCity: Annotated LiDAR Point Cloud and its Applicationsen
dc.title.alternativeBMVC 30th British Machine Vision Conference, Forthcoming.en
dc.typeConference Paperen
dc.contributor.sponsorSFI stipenden
dc.type.supercollectionscholarly_publicationsen
dc.type.supercollectionrefereed_publicationsen
dc.identifier.peoplefinderurlhttp://people.tcd.ie/smolica
dc.identifier.rssinternalid212576
dc.rights.ecaccessrightsopenAccess
dc.contributor.sponsorGrantNumber15/RP/2776en
dc.subject.TCDThemeCreative Technologiesen
dc.subject.TCDTagMultimedia & Creativityen
dc.subject.darat_impairmentOtheren
dc.status.accessibleNen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record