Reconstructing building mass models from UAV images

Handle URI:
http://hdl.handle.net/10754/567059
Title:
Reconstructing building mass models from UAV images
Authors:
Li, Minglei; Nan, Liangliang ( 0000-0002-5629-9975 ) ; Smith, Neil; Wonka, Peter ( 0000-0003-0627-9746 )
Abstract:
We present an automatic reconstruction pipeline for large scale urban scenes from aerial images captured by a camera mounted on an unmanned aerial vehicle. Using state-of-the-art Structure from Motion and Multi-View Stereo algorithms, we first generate a dense point cloud from the aerial images. Based on the statistical analysis of the footprint grid of the buildings, the point cloud is classified into different categories (i.e., buildings, ground, trees, and others). Roof structures are extracted for each individual building using Markov random field optimization. Then, a contour refinement algorithm based on pivot point detection is utilized to refine the contour of patches. Finally, polygonal mesh models are extracted from the refined contours. Experiments on various scenes as well as comparisons with state-of-the-art reconstruction methods demonstrate the effectiveness and robustness of the proposed method.
KAUST Department:
Visual Computing Center (VCC)
Citation:
Reconstructing building mass models from UAV images 2016, 54:84 Computers & Graphics
Publisher:
Elsevier BV
Journal:
Computers & Graphics
Issue Date:
26-Jul-2015
DOI:
10.1016/j.cag.2015.07.004
Type:
Article
ISSN:
00978493
Additional Links:
http://linkinghub.elsevier.com/retrieve/pii/S0097849315001077
Appears in Collections:
Articles; Visual Computing Center (VCC)

Full metadata record

DC FieldValue Language
dc.contributor.authorLi, Mingleien
dc.contributor.authorNan, Liangliangen
dc.contributor.authorSmith, Neilen
dc.contributor.authorWonka, Peteren
dc.date.accessioned2015-08-17T07:38:03Zen
dc.date.available2015-08-17T07:38:03Zen
dc.date.issued2015-07-26en
dc.identifier.citationReconstructing building mass models from UAV images 2016, 54:84 Computers & Graphicsen
dc.identifier.issn00978493en
dc.identifier.doi10.1016/j.cag.2015.07.004en
dc.identifier.urihttp://hdl.handle.net/10754/567059en
dc.description.abstractWe present an automatic reconstruction pipeline for large scale urban scenes from aerial images captured by a camera mounted on an unmanned aerial vehicle. Using state-of-the-art Structure from Motion and Multi-View Stereo algorithms, we first generate a dense point cloud from the aerial images. Based on the statistical analysis of the footprint grid of the buildings, the point cloud is classified into different categories (i.e., buildings, ground, trees, and others). Roof structures are extracted for each individual building using Markov random field optimization. Then, a contour refinement algorithm based on pivot point detection is utilized to refine the contour of patches. Finally, polygonal mesh models are extracted from the refined contours. Experiments on various scenes as well as comparisons with state-of-the-art reconstruction methods demonstrate the effectiveness and robustness of the proposed method.en
dc.language.isoenen
dc.publisherElsevier BVen
dc.relation.urlhttp://linkinghub.elsevier.com/retrieve/pii/S0097849315001077en
dc.rightsNOTICE: this is the author’s version of a work that was accepted for publication in Computers & Graphics. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Computers & Graphics, 26 July 2015. DOI: 10.1016/j.cag.2015.07.004en
dc.subjectUrban reconstructionen
dc.subjectAerial imagesen
dc.subjectPoint clouden
dc.subjectMarkov random fielden
dc.subjectGraph cuten
dc.titleReconstructing building mass models from UAV imagesen
dc.typeArticleen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.identifier.journalComputers & Graphicsen
dc.eprint.versionPost-printen
dc.contributor.institutionInstitute of Remote Sensing and Digital Earth, CAS, Datun Road No. 20, Chaoyang District, Beijing 100101, P.R. Chinaen
dc.contributor.affiliationKing Abdullah University of Science and Technology (KAUST)en
kaust.authorSmith, Neilen
kaust.authorWonka, Peteren
kaust.authorLi, Mingleien
kaust.authorNan, Liangliangen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.