Robust rooftop extraction from visible band images using higher order CRF

Handle URI:
http://hdl.handle.net/10754/564195
Title:
Robust rooftop extraction from visible band images using higher order CRF
Authors:
Li, Er; Femiani, John; Xu, Shibiao; Zhang, Xiaopeng; Wonka, Peter ( 0000-0003-0627-9746 )
Abstract:
In this paper, we propose a robust framework for building extraction in visible band images. We first get an initial classification of the pixels based on an unsupervised presegmentation. Then, we develop a novel conditional random field (CRF) formulation to achieve accurate rooftops extraction, which incorporates pixel-level information and segment-level information for the identification of rooftops. Comparing with the commonly used CRF model, a higher order potential defined on segment is added in our model, by exploiting region consistency and shape feature at segment level. Our experiments show that the proposed higher order CRF model outperforms the state-of-the-art methods both at pixel and object levels on rooftops with complex structures and sizes in challenging environments. © 1980-2012 IEEE.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Computer Science Program; Visual Computing Center (VCC)
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
IEEE Transactions on Geoscience and Remote Sensing
Issue Date:
Aug-2015
DOI:
10.1109/TGRS.2015.2400462
Type:
Article
ISSN:
01962892
Sponsors:
This work was supported by the National Natural Science Foundation of China under Grant 61331018, Grant 91338202, and Grant 61100132.
Appears in Collections:
Articles; Computer Science Program; Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorLi, Eren
dc.contributor.authorFemiani, Johnen
dc.contributor.authorXu, Shibiaoen
dc.contributor.authorZhang, Xiaopengen
dc.contributor.authorWonka, Peteren
dc.date.accessioned2015-08-03T12:36:00Zen
dc.date.available2015-08-03T12:36:00Zen
dc.date.issued2015-08en
dc.identifier.issn01962892en
dc.identifier.doi10.1109/TGRS.2015.2400462en
dc.identifier.urihttp://hdl.handle.net/10754/564195en
dc.description.abstractIn this paper, we propose a robust framework for building extraction in visible band images. We first get an initial classification of the pixels based on an unsupervised presegmentation. Then, we develop a novel conditional random field (CRF) formulation to achieve accurate rooftops extraction, which incorporates pixel-level information and segment-level information for the identification of rooftops. Comparing with the commonly used CRF model, a higher order potential defined on segment is added in our model, by exploiting region consistency and shape feature at segment level. Our experiments show that the proposed higher order CRF model outperforms the state-of-the-art methods both at pixel and object levels on rooftops with complex structures and sizes in challenging environments. © 1980-2012 IEEE.en
dc.description.sponsorshipThis work was supported by the National Natural Science Foundation of China under Grant 61331018, Grant 91338202, and Grant 61100132.en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.subjectBuildingsen
dc.subjectrooftops conditional random field (CRF)en
dc.subjectshadowsen
dc.titleRobust rooftop extraction from visible band images using higher order CRFen
dc.typeArticleen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentComputer Science Programen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.identifier.journalIEEE Transactions on Geoscience and Remote Sensingen
dc.contributor.institutionDepartment of Engineering and Computing Systems, Arizona State UniversityMesa, AZ, United Statesen
dc.contributor.institutionNational Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of SciencesBeijing, Chinaen
dc.contributor.institutionDepartment of Computer Science and Engineering, Arizona State UniversityTempe, AZ, United Statesen
kaust.authorWonka, Peteren
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.