Extração automática de contornos de telhados usando dados de varredura a laser e campos randômicos de Markov
Autor(a) principal: | |
---|---|
Data de Publicação: | 2008 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://hdl.handle.net/11449/231125 |
Resumo: | This paper proposes a methodology for automatic extraction of building roof contours from a Digital Elevation Model (DEM), which is generated through the regularization of an available laser point cloud. The methodology is based on two steps. First, in order to detect high objects (buildings, trees etc.), the DEM is segmented through a recursive splitting technique and a Bayesian merging technique. The recursive splitting technique uses the quadtree structure for subdividing the DEM into homogeneous regions. In order to minimize the fragmentation, which is commonly observed in the results of the recursive splitting segmentation, a region merging technique based on the Bayesian framework is applied to the previously segmented data. The high object polygons are extracted by using vectorization and polygonization techniques. Second, the building roof contours are identified among all high objects extracted previously. Taking into account some roof properties and some feature measurements (e. g., area, rectangularity, and angles between principal axes of the roofs), an energy function was developed based on the Markov Random Field (MRF) model. The solution of this function is a polygon set corresponding to building roof contours and is found by using a minimization technique, like the Simulated Annealing (SA) algorithm. Experiments carried out with laser scanning DEM's showed that the methodology works properly, as it delivered roofs with approximately 90% shape accuracy and no false positive was verified. |
id |
UNSP_5140fb3b4ad8cf07260189bb9d1ddc68 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/231125 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Extração automática de contornos de telhados usando dados de varredura a laser e campos randômicos de MarkovAutomatic extraction of building roof contours by laser scanning data and Markov Random FieldAutomatic extractionBuilding roof contoursDigital elevation modelLaser scanning dataMarkov Random FieldThis paper proposes a methodology for automatic extraction of building roof contours from a Digital Elevation Model (DEM), which is generated through the regularization of an available laser point cloud. The methodology is based on two steps. First, in order to detect high objects (buildings, trees etc.), the DEM is segmented through a recursive splitting technique and a Bayesian merging technique. The recursive splitting technique uses the quadtree structure for subdividing the DEM into homogeneous regions. In order to minimize the fragmentation, which is commonly observed in the results of the recursive splitting segmentation, a region merging technique based on the Bayesian framework is applied to the previously segmented data. The high object polygons are extracted by using vectorization and polygonization techniques. Second, the building roof contours are identified among all high objects extracted previously. Taking into account some roof properties and some feature measurements (e. g., area, rectangularity, and angles between principal axes of the roofs), an energy function was developed based on the Markov Random Field (MRF) model. The solution of this function is a polygon set corresponding to building roof contours and is found by using a minimization technique, like the Simulated Annealing (SA) algorithm. Experiments carried out with laser scanning DEM's showed that the methodology works properly, as it delivered roofs with approximately 90% shape accuracy and no false positive was verified.Universidade do Estado de Mato Grosso - UNEMAT Departmento de Matemática, Rus A, s/n, 78390-000 Barra do Bugres, MTUniversidade Estadual Paulista (UNESP) Faculdade de Ciências e Tecnologia, Rua Roberto Simonsen, 305, 19060 - 900 Presidente Prudente, SPPrograma de Pós-Graduação em Ciências Cartográficas, Rua Roberto Simonsen, 305, 19060 - 900 Presidente Prudente, SPUniversidade Estadual Paulista (UNESP) Faculdade de Ciências e Tecnologia, Rua Roberto Simonsen, 305, 19060 - 900 Presidente Prudente, SPUniversidade do Estado de Mato Grosso - UNEMATUniversidade Estadual Paulista (UNESP)Programa de Pós-Graduação em Ciências CartográficasGalvanin, Edineia Aparecida dos SantosDal Poz, Aluir Porfírio [UNESP]De Souza, Aparecida Doniseti Pires2022-04-29T08:43:45Z2022-04-29T08:43:45Z2008-04-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article221-241Boletim de Ciencias Geodesicas, v. 14, n. 2, p. 221-241, 2008.1413-4853http://hdl.handle.net/11449/2311252-s2.0-49649112733Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPporBoletim de Ciencias Geodesicas6525info:eu-repo/semantics/openAccess2024-06-18T15:01:26Zoai:repositorio.unesp.br:11449/231125Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T16:30:41.769182Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Extração automática de contornos de telhados usando dados de varredura a laser e campos randômicos de Markov Automatic extraction of building roof contours by laser scanning data and Markov Random Field |
title |
Extração automática de contornos de telhados usando dados de varredura a laser e campos randômicos de Markov |
spellingShingle |
Extração automática de contornos de telhados usando dados de varredura a laser e campos randômicos de Markov Galvanin, Edineia Aparecida dos Santos Automatic extraction Building roof contours Digital elevation model Laser scanning data Markov Random Field |
title_short |
Extração automática de contornos de telhados usando dados de varredura a laser e campos randômicos de Markov |
title_full |
Extração automática de contornos de telhados usando dados de varredura a laser e campos randômicos de Markov |
title_fullStr |
Extração automática de contornos de telhados usando dados de varredura a laser e campos randômicos de Markov |
title_full_unstemmed |
Extração automática de contornos de telhados usando dados de varredura a laser e campos randômicos de Markov |
title_sort |
Extração automática de contornos de telhados usando dados de varredura a laser e campos randômicos de Markov |
author |
Galvanin, Edineia Aparecida dos Santos |
author_facet |
Galvanin, Edineia Aparecida dos Santos Dal Poz, Aluir Porfírio [UNESP] De Souza, Aparecida Doniseti Pires |
author_role |
author |
author2 |
Dal Poz, Aluir Porfírio [UNESP] De Souza, Aparecida Doniseti Pires |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Universidade do Estado de Mato Grosso - UNEMAT Universidade Estadual Paulista (UNESP) Programa de Pós-Graduação em Ciências Cartográficas |
dc.contributor.author.fl_str_mv |
Galvanin, Edineia Aparecida dos Santos Dal Poz, Aluir Porfírio [UNESP] De Souza, Aparecida Doniseti Pires |
dc.subject.por.fl_str_mv |
Automatic extraction Building roof contours Digital elevation model Laser scanning data Markov Random Field |
topic |
Automatic extraction Building roof contours Digital elevation model Laser scanning data Markov Random Field |
description |
This paper proposes a methodology for automatic extraction of building roof contours from a Digital Elevation Model (DEM), which is generated through the regularization of an available laser point cloud. The methodology is based on two steps. First, in order to detect high objects (buildings, trees etc.), the DEM is segmented through a recursive splitting technique and a Bayesian merging technique. The recursive splitting technique uses the quadtree structure for subdividing the DEM into homogeneous regions. In order to minimize the fragmentation, which is commonly observed in the results of the recursive splitting segmentation, a region merging technique based on the Bayesian framework is applied to the previously segmented data. The high object polygons are extracted by using vectorization and polygonization techniques. Second, the building roof contours are identified among all high objects extracted previously. Taking into account some roof properties and some feature measurements (e. g., area, rectangularity, and angles between principal axes of the roofs), an energy function was developed based on the Markov Random Field (MRF) model. The solution of this function is a polygon set corresponding to building roof contours and is found by using a minimization technique, like the Simulated Annealing (SA) algorithm. Experiments carried out with laser scanning DEM's showed that the methodology works properly, as it delivered roofs with approximately 90% shape accuracy and no false positive was verified. |
publishDate |
2008 |
dc.date.none.fl_str_mv |
2008-04-01 2022-04-29T08:43:45Z 2022-04-29T08:43:45Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
Boletim de Ciencias Geodesicas, v. 14, n. 2, p. 221-241, 2008. 1413-4853 http://hdl.handle.net/11449/231125 2-s2.0-49649112733 |
identifier_str_mv |
Boletim de Ciencias Geodesicas, v. 14, n. 2, p. 221-241, 2008. 1413-4853 2-s2.0-49649112733 |
url |
http://hdl.handle.net/11449/231125 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.none.fl_str_mv |
Boletim de Ciencias Geodesicas 6525 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
221-241 |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808128663794745344 |