Automatic extraction of building roof contours by laser scanning data and markov random field
Autor(a) principal: | |
---|---|
Data de Publicação: | 2008 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Boletim de Ciências Geodésicas |
Texto Completo: | https://revistas.ufpr.br/bcg/article/view/11817 |
Resumo: | This paper proposes a methodology for automatic extraction of building roofcontours from a Digital Elevation Model (DEM), which is generated through theregularization of an available laser point cloud. The methodology is based on twosteps. First, in order to detect high objects (buildings, trees etc.), the DEM issegmented through a recursive splitting technique and a Bayesian mergingtechnique. The recursive splitting technique uses the quadtree structure forsubdividing the DEM into homogeneous regions. In order to minimize thefragmentation, which is commonly observed in the results of the recursive splittingsegmentation, a region merging technique based on the Bayesian framework isapplied to the previously segmented data. The high object polygons are extracted byusing vectorization and polygonization techniques. Second, the building roofcontours are identified among all high objects extracted previously. Taking intoaccount some roof properties and some feature measurements (e. g., area,rectangularity, and angles between principal axes of the roofs), an energy functionwas developed based on the Markov Random Field (MRF) model. The solution ofthis function is a polygon set corresponding to building roof contours and is foundby using a minimization technique, like the Simulated Annealing (SA) algorithm. Experiments carried out with laser scanning DEM´s showed that the methodologyworks properly, as it delivered roof contours with approximately 90% shapeaccuracy and no false positive was verified. |
id |
UFPR-2_3a2e837b795a7e9f590d01fdac182c25 |
---|---|
oai_identifier_str |
oai:revistas.ufpr.br:article/11817 |
network_acronym_str |
UFPR-2 |
network_name_str |
Boletim de Ciências Geodésicas |
repository_id_str |
|
spelling |
Automatic extraction of building roof contours by laser scanning data and markov random fieldEXTRAÇÃO AUTOMÁTICA DE CONTORNOS DE TELHADOS USANDO DADOS DE VARREDURA A LASER E CAMPOS RANDÔMICOS DE MARKOVAutomatic Extraction; Building Roof Contours; Digital Elevation Model; Laser Scanning Data; Markov Random Field; Extração Automática; Contornos de Telhados de Edifícios; Modelo Digital de Elevação; Dados de Varredura a Laser; Campos Randômicos de MarkovThis paper proposes a methodology for automatic extraction of building roofcontours from a Digital Elevation Model (DEM), which is generated through theregularization of an available laser point cloud. The methodology is based on twosteps. First, in order to detect high objects (buildings, trees etc.), the DEM issegmented through a recursive splitting technique and a Bayesian mergingtechnique. The recursive splitting technique uses the quadtree structure forsubdividing the DEM into homogeneous regions. In order to minimize thefragmentation, which is commonly observed in the results of the recursive splittingsegmentation, a region merging technique based on the Bayesian framework isapplied to the previously segmented data. The high object polygons are extracted byusing vectorization and polygonization techniques. Second, the building roofcontours are identified among all high objects extracted previously. Taking intoaccount some roof properties and some feature measurements (e. g., area,rectangularity, and angles between principal axes of the roofs), an energy functionwas developed based on the Markov Random Field (MRF) model. The solution ofthis function is a polygon set corresponding to building roof contours and is foundby using a minimization technique, like the Simulated Annealing (SA) algorithm. Experiments carried out with laser scanning DEM´s showed that the methodologyworks properly, as it delivered roof contours with approximately 90% shapeaccuracy and no false positive was verified.Este artigo propõe uma metodologia para a extração automática de contornos detelhados de edifícios a partir de um MDE (Modelo Digital de Elevação), gerado apartir da regularização de uma malha irregular de dados laser preexistentes. Ametodologia baseia-se em duas etapas. Primeiramente, a fim de detectar objetosaltos (edifícios altos, árvores etc.), o MDE é segmentado através de uma técnica dedivisão recursiva e de uma técnica de fusão bayesiana. A técnica de divisãorecursiva usa a estrutura quadtree para subdividir o MDE em regiões homogêneas.A fim de minimizar a fragmentação que freqüentemente é observada nos resultadosda segmentação por divisão recursiva, uma técnica de fusão baseada em InferênciaBayesiana é aplicada aos dados previamente segmentados. Os contornos dos objetos altos são obtidos através de técnicas de vetorização e poligonização. Na segundaetapa, os contornos de telhados de edifícios são identificados entre todos os objetosaltos extraídos previamente. Levando em conta algumas propriedades de telhado ealguns atributos (por exemplo, área, retangularidade e ângulos entre os eixosprincipais dos telhados), uma função de energia foi desenvolvida com base nomodelo Markov Random Field (MRF). A solução desta função é um conjunto depolígonos representando contornos de telhados de edifícios e é encontrada atravésde técnicas de minimização, como o algoritmo Simulated Annealing (SA). Váriosexperimentos foram realizados com base em DEM´s obtidos a partir de dados devarredura a laser, os quais demonstraram que a metodologia proposta funcionaadequadamente, visto que foram extraídos contornos de telhados comaproximadamente 90% de completeza de área e nenhum falso positivo foiverificado.Boletim de Ciências GeodésicasBulletin of Geodetic Sciences2008-07-18info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://revistas.ufpr.br/bcg/article/view/11817Boletim de Ciências Geodésicas; Vol 14, No 2 (2008)Bulletin of Geodetic Sciences; Vol 14, No 2 (2008)1982-21701413-4853reponame:Boletim de Ciências Geodésicasinstname:Universidade Federal do Paraná (UFPR)instacron:UFPRporhttps://revistas.ufpr.br/bcg/article/view/11817/8328Galvanin, Edinéia Aparecida dos SantosDal Poz, Aluir PorfírioSouza, Aparecida Doniseti Pires deinfo:eu-repo/semantics/openAccess2008-10-08T14:15:31Zoai:revistas.ufpr.br:article/11817Revistahttps://revistas.ufpr.br/bcgPUBhttps://revistas.ufpr.br/bcg/oaiqdalmolin@ufpr.br|| danielsantos@ufpr.br||qdalmolin@ufpr.br|| danielsantos@ufpr.br1982-21701413-4853opendoar:2008-10-08T14:15:31Boletim de Ciências Geodésicas - Universidade Federal do Paraná (UFPR)false |
dc.title.none.fl_str_mv |
Automatic extraction of building roof contours by laser scanning data and markov random field EXTRAÇÃO AUTOMÁTICA DE CONTORNOS DE TELHADOS USANDO DADOS DE VARREDURA A LASER E CAMPOS RANDÔMICOS DE MARKOV |
title |
Automatic extraction of building roof contours by laser scanning data and markov random field |
spellingShingle |
Automatic extraction of building roof contours by laser scanning data and markov random field Galvanin, Edinéia Aparecida dos Santos Automatic Extraction; Building Roof Contours; Digital Elevation Model; Laser Scanning Data; Markov Random Field; Extração Automática; Contornos de Telhados de Edifícios; Modelo Digital de Elevação; Dados de Varredura a Laser; Campos Randômicos de Markov |
title_short |
Automatic extraction of building roof contours by laser scanning data and markov random field |
title_full |
Automatic extraction of building roof contours by laser scanning data and markov random field |
title_fullStr |
Automatic extraction of building roof contours by laser scanning data and markov random field |
title_full_unstemmed |
Automatic extraction of building roof contours by laser scanning data and markov random field |
title_sort |
Automatic extraction of building roof contours by laser scanning data and markov random field |
author |
Galvanin, Edinéia Aparecida dos Santos |
author_facet |
Galvanin, Edinéia Aparecida dos Santos Dal Poz, Aluir Porfírio Souza, Aparecida Doniseti Pires de |
author_role |
author |
author2 |
Dal Poz, Aluir Porfírio Souza, Aparecida Doniseti Pires de |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Galvanin, Edinéia Aparecida dos Santos Dal Poz, Aluir Porfírio Souza, Aparecida Doniseti Pires de |
dc.subject.por.fl_str_mv |
Automatic Extraction; Building Roof Contours; Digital Elevation Model; Laser Scanning Data; Markov Random Field; Extração Automática; Contornos de Telhados de Edifícios; Modelo Digital de Elevação; Dados de Varredura a Laser; Campos Randômicos de Markov |
topic |
Automatic Extraction; Building Roof Contours; Digital Elevation Model; Laser Scanning Data; Markov Random Field; Extração Automática; Contornos de Telhados de Edifícios; Modelo Digital de Elevação; Dados de Varredura a Laser; Campos Randômicos de Markov |
description |
This paper proposes a methodology for automatic extraction of building roofcontours from a Digital Elevation Model (DEM), which is generated through theregularization of an available laser point cloud. The methodology is based on twosteps. First, in order to detect high objects (buildings, trees etc.), the DEM issegmented through a recursive splitting technique and a Bayesian mergingtechnique. The recursive splitting technique uses the quadtree structure forsubdividing the DEM into homogeneous regions. In order to minimize thefragmentation, which is commonly observed in the results of the recursive splittingsegmentation, a region merging technique based on the Bayesian framework isapplied to the previously segmented data. The high object polygons are extracted byusing vectorization and polygonization techniques. Second, the building roofcontours are identified among all high objects extracted previously. Taking intoaccount some roof properties and some feature measurements (e. g., area,rectangularity, and angles between principal axes of the roofs), an energy functionwas developed based on the Markov Random Field (MRF) model. The solution ofthis function is a polygon set corresponding to building roof contours and is foundby using a minimization technique, like the Simulated Annealing (SA) algorithm. Experiments carried out with laser scanning DEM´s showed that the methodologyworks properly, as it delivered roof contours with approximately 90% shapeaccuracy and no false positive was verified. |
publishDate |
2008 |
dc.date.none.fl_str_mv |
2008-07-18 |
dc.type.none.fl_str_mv |
|
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://revistas.ufpr.br/bcg/article/view/11817 |
url |
https://revistas.ufpr.br/bcg/article/view/11817 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
https://revistas.ufpr.br/bcg/article/view/11817/8328 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Boletim de Ciências Geodésicas Bulletin of Geodetic Sciences |
publisher.none.fl_str_mv |
Boletim de Ciências Geodésicas Bulletin of Geodetic Sciences |
dc.source.none.fl_str_mv |
Boletim de Ciências Geodésicas; Vol 14, No 2 (2008) Bulletin of Geodetic Sciences; Vol 14, No 2 (2008) 1982-2170 1413-4853 reponame:Boletim de Ciências Geodésicas instname:Universidade Federal do Paraná (UFPR) instacron:UFPR |
instname_str |
Universidade Federal do Paraná (UFPR) |
instacron_str |
UFPR |
institution |
UFPR |
reponame_str |
Boletim de Ciências Geodésicas |
collection |
Boletim de Ciências Geodésicas |
repository.name.fl_str_mv |
Boletim de Ciências Geodésicas - Universidade Federal do Paraná (UFPR) |
repository.mail.fl_str_mv |
qdalmolin@ufpr.br|| danielsantos@ufpr.br||qdalmolin@ufpr.br|| danielsantos@ufpr.br |
_version_ |
1799771721678454784 |