Fitting boxes to Manhattan scenes using linear integer programming

Handle URI:
http://hdl.handle.net/10754/600705
Title:
Fitting boxes to Manhattan scenes using linear integer programming
Authors:
Li, Minglei; Nan, Liangliang ( 0000-0002-5629-9975 ) ; Liu, Shaochuang
Abstract:
We propose an approach for automatic generation of building models by assembling a set of boxes using a Manhattan-world assumption. The method first aligns the point cloud with a per-building local coordinate system, and then fits axis-aligned planes to the point cloud through an iterative regularization process. The refined planes partition the space of the data into a series of compact cubic cells (candidate boxes) spanning the entire 3D space of the input data. We then choose to approximate the target building by the assembly of a subset of these candidate boxes using a binary linear programming formulation. The objective function is designed to maximize the point cloud coverage and the compactness of the final model. Finally, all selected boxes are merged into a lightweight polygonal mesh model, which is suitable for interactive visualization of large scale urban scenes. Experimental results and a comparison with state-of-the-art methods demonstrate the effectiveness of the proposed framework.
KAUST Department:
Visual Computing Center (VCC)
Citation:
Fitting boxes to Manhattan scenes using linear integer programming 2016:1 International Journal of Digital Earth
Publisher:
Informa UK Limited
Journal:
International Journal of Digital Earth
Issue Date:
19-Feb-2016
DOI:
10.1080/17538947.2016.1143982
Type:
Article
ISSN:
1753-8947; 1753-8955
Additional Links:
http://www.tandfonline.com/doi/full/10.1080/17538947.2016.1143982
Appears in Collections:
Articles; Visual Computing Center (VCC)

Full metadata record

DC FieldValue Language
dc.contributor.authorLi, Mingleien
dc.contributor.authorNan, Liangliangen
dc.contributor.authorLiu, Shaochuangen
dc.date.accessioned2016-03-07T12:58:40Zen
dc.date.available2016-03-07T12:58:40Zen
dc.date.issued2016-02-19en
dc.identifier.citationFitting boxes to Manhattan scenes using linear integer programming 2016:1 International Journal of Digital Earthen
dc.identifier.issn1753-8947en
dc.identifier.issn1753-8955en
dc.identifier.doi10.1080/17538947.2016.1143982en
dc.identifier.urihttp://hdl.handle.net/10754/600705en
dc.description.abstractWe propose an approach for automatic generation of building models by assembling a set of boxes using a Manhattan-world assumption. The method first aligns the point cloud with a per-building local coordinate system, and then fits axis-aligned planes to the point cloud through an iterative regularization process. The refined planes partition the space of the data into a series of compact cubic cells (candidate boxes) spanning the entire 3D space of the input data. We then choose to approximate the target building by the assembly of a subset of these candidate boxes using a binary linear programming formulation. The objective function is designed to maximize the point cloud coverage and the compactness of the final model. Finally, all selected boxes are merged into a lightweight polygonal mesh model, which is suitable for interactive visualization of large scale urban scenes. Experimental results and a comparison with state-of-the-art methods demonstrate the effectiveness of the proposed framework.en
dc.language.isoenen
dc.publisherInforma UK Limiteden
dc.relation.urlhttp://www.tandfonline.com/doi/full/10.1080/17538947.2016.1143982en
dc.rightsThis is an Accepted Manuscript of an article published by Taylor & Francis in International Journal of Digital Earth on 19 Feb 2016, available online: http://www.tandfonline.com/doi/full/10.1080/17538947.2016.1143982.en
dc.subjectUrban building modelsen
dc.subjectaerial point clouden
dc.subjectManhattan scenesen
dc.subjectlinear integer programmingen
dc.titleFitting boxes to Manhattan scenes using linear integer programmingen
dc.typeArticleen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.identifier.journalInternational Journal of Digital Earthen
dc.eprint.versionPost-printen
dc.contributor.institutionIntegrated Spatial Information Lab, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing, People's Republic of Chinaen
dc.contributor.affiliationKing Abdullah University of Science and Technology (KAUST)en
kaust.authorNan, Liangliangen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.