Large-scale building reconstruction through information fusion and 3-D priors

Karantzalos, K; Paragios, N

dc.contributor.author	Karantzalos, K	en
dc.contributor.author	Paragios, N	en
dc.date.accessioned	2014-03-01T01:33:41Z
dc.date.available	2014-03-01T01:33:41Z
dc.date.issued	2010	en
dc.identifier.issn	0196-2892	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/20538
dc.subject	Level sets	en
dc.subject	Modeling	en
dc.subject	Object detection	en
dc.subject	Recognition	en
dc.subject	Registration	en
dc.subject	Segmentation	en
dc.subject	Variational methods	en
dc.subject.classification	Geochemistry & Geophysics	en
dc.subject.classification	Engineering, Electrical & Electronic	en
dc.subject.classification	Remote Sensing	en
dc.subject.other	Building model	en
dc.subject.other	Building reconstruction	en
dc.subject.other	Digital Elevation Map	en
dc.subject.other	Hierarchical representation	en
dc.subject.other	Integrated approach	en
dc.subject.other	Level Set	en
dc.subject.other	Object Detection	en
dc.subject.other	Observed data	en
dc.subject.other	Optical image	en
dc.subject.other	Quantitative evaluation	en
dc.subject.other	Sensing data	en
dc.subject.other	Variational framework	en
dc.subject.other	Variational methods	en
dc.subject.other	Geometrical optics	en
dc.subject.other	Level measurement	en
dc.subject.other	Remote sensing	en
dc.subject.other	Three dimensional	en
dc.subject.other	building	en
dc.subject.other	digital elevation model	en
dc.subject.other	experimental study	en
dc.subject.other	geometry	en
dc.subject.other	reconstruction	en
dc.subject.other	remote sensing	en
dc.subject.other	satellite data	en
dc.subject.other	satellite imagery	en
dc.subject.other	three-dimensional modeling	en
dc.title	Large-scale building reconstruction through information fusion and 3-D priors	en
heal.type	journalArticle	en
heal.identifier.primary	10.1109/TGRS.2009.2039220	en
heal.identifier.secondary	http://dx.doi.org/10.1109/TGRS.2009.2039220	en
heal.identifier.secondary	5433051	en
heal.language	English	en
heal.publicationDate	2010	en
heal.abstract	In this paper, a novel variational framework is introduced toward automatic 3-D building reconstruction from remote-sensing data. We consider a subset of building models that involve the footprint, their elevation, and the roof type. These models, under a certain hierarchical representation, describe the space of solutions and, under a fruitful synergy with an inferential procedure, recover the observed scene's geometry. Such an integrated approach is defined in a variational context, solves segmentation both in optical images and digital elevation maps, and allows multiple competing priors to determine their pose and 3-D geometry from the observed data. The very promising experimental results and the performed quantitative evaluation demonstrate the potentials of our approach. © 2010 IEEE.	en
heal.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC	en
heal.journalName	IEEE Transactions on Geoscience and Remote Sensing	en
dc.identifier.doi	10.1109/TGRS.2009.2039220	en
dc.identifier.isi	ISI:000276814300010	en
dc.identifier.volume	48	en
dc.identifier.issue	5	en
dc.identifier.spage	2283	en
dc.identifier.epage	2296	en