A Markov-Random-Field Approach for Extracting Straight-Line Segments of Roofs From High-Resolution Aerial Images
Autor(a) principal: | |
---|---|
Data de Publicação: | 2016 |
Outros Autores: | |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1109/JSTARS.2016.2601068 http://hdl.handle.net/11449/162325 |
Resumo: | This paper proposes a method for extracting groups of straight lines that represent roof boundary sides and roof ridgelines from high-resolution aerial images using corresponding airborne laser scanner (ALS) roof polyhedrons as initial approximations. Our motivation for this research is the possibility of future use of resulting image-space straight lines in several applications. For example, straight lines that represent roof boundary sides and precisely extracted from a high-resolution image can be back-projected onto the ALS-derived building polyhedron for refining the accuracy of its boundary. The proposed method is based on two main steps. First, straight lines that are candidates to represent roof ridgelines and roof boundary sides of a building are extracted from the aerial image. The ALS-derived roof boundary sides and roof ridgelines are projected onto the image space, and bolding boxes are constructed around the projected straight lines while considering the projection errors. This allows the extraction of straight lines within the bounding boxes. Second, a group of straight lines that represent roof boundary sides and roof ridgelines of a selected building is obtained through the optimization of a Markov random field-based energy function using the genetic algorithm optimization method. The formulation of this energy function considers several attributes, such as the proximity of the extracted straight lines to the corresponding projected ALS-derived roof polyhedron and the rectangularity (extracted straight lines that intersect at nearly 90 degrees). In order to validate the proposed method, four experiments were accomplished using high-resolution aerial images, along with interior and exterior orientation parameters, and available ALS-derived building roof polyhedrons. The obtained results have shown that the method works properly and this will be qualitatively and quantitatively demonstrated in this research. |
id |
UNSP_31643aafa81fdde1a466df050487e900 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/162325 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
A Markov-Random-Field Approach for Extracting Straight-Line Segments of Roofs From High-Resolution Aerial ImagesAirborne laser scanner (ALS)Markov random field (MRF)straight lineThis paper proposes a method for extracting groups of straight lines that represent roof boundary sides and roof ridgelines from high-resolution aerial images using corresponding airborne laser scanner (ALS) roof polyhedrons as initial approximations. Our motivation for this research is the possibility of future use of resulting image-space straight lines in several applications. For example, straight lines that represent roof boundary sides and precisely extracted from a high-resolution image can be back-projected onto the ALS-derived building polyhedron for refining the accuracy of its boundary. The proposed method is based on two main steps. First, straight lines that are candidates to represent roof ridgelines and roof boundary sides of a building are extracted from the aerial image. The ALS-derived roof boundary sides and roof ridgelines are projected onto the image space, and bolding boxes are constructed around the projected straight lines while considering the projection errors. This allows the extraction of straight lines within the bounding boxes. Second, a group of straight lines that represent roof boundary sides and roof ridgelines of a selected building is obtained through the optimization of a Markov random field-based energy function using the genetic algorithm optimization method. The formulation of this energy function considers several attributes, such as the proximity of the extracted straight lines to the corresponding projected ALS-derived roof polyhedron and the rectangularity (extracted straight lines that intersect at nearly 90 degrees). In order to validate the proposed method, four experiments were accomplished using high-resolution aerial images, along with interior and exterior orientation parameters, and available ALS-derived building roof polyhedrons. The obtained results have shown that the method works properly and this will be qualitatively and quantitatively demonstrated in this research.Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Sao Paulo State Univ, BR-19060900 Presidente Prudente, BrazilSao Paulo State Univ, Dept Cartog, BR-19060900 Presidente Prudente, BrazilSao Paulo State Univ, BR-19060900 Presidente Prudente, BrazilSao Paulo State Univ, Dept Cartog, BR-19060900 Presidente Prudente, BrazilFAPESP: 2013/13138-0FAPESP: 2012/22332-2CNPq: 304879/2009-6Ieee-inst Electrical Electronics Engineers IncUniversidade Estadual Paulista (Unesp)Marcato Fernandes, Vanessa Jordao [UNESP]Dal Poz, Aluir Porfirio [UNESP]2018-11-26T17:15:38Z2018-11-26T17:15:38Z2016-12-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article5493-5505application/pdfhttp://dx.doi.org/10.1109/JSTARS.2016.2601068Ieee Journal Of Selected Topics In Applied Earth Observations And Remote Sensing. Piscataway: Ieee-inst Electrical Electronics Engineers Inc, v. 9, n. 12, p. 5493-5505, 2016.1939-1404http://hdl.handle.net/11449/16232510.1109/JSTARS.2016.2601068WOS:000391468100020WOS000391468100020.pdfWeb of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengIeee Journal Of Selected Topics In Applied Earth Observations And Remote Sensing1,547info:eu-repo/semantics/openAccess2024-06-18T18:18:24Zoai:repositorio.unesp.br:11449/162325Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T23:16:43.350686Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
A Markov-Random-Field Approach for Extracting Straight-Line Segments of Roofs From High-Resolution Aerial Images |
title |
A Markov-Random-Field Approach for Extracting Straight-Line Segments of Roofs From High-Resolution Aerial Images |
spellingShingle |
A Markov-Random-Field Approach for Extracting Straight-Line Segments of Roofs From High-Resolution Aerial Images Marcato Fernandes, Vanessa Jordao [UNESP] Airborne laser scanner (ALS) Markov random field (MRF) straight line |
title_short |
A Markov-Random-Field Approach for Extracting Straight-Line Segments of Roofs From High-Resolution Aerial Images |
title_full |
A Markov-Random-Field Approach for Extracting Straight-Line Segments of Roofs From High-Resolution Aerial Images |
title_fullStr |
A Markov-Random-Field Approach for Extracting Straight-Line Segments of Roofs From High-Resolution Aerial Images |
title_full_unstemmed |
A Markov-Random-Field Approach for Extracting Straight-Line Segments of Roofs From High-Resolution Aerial Images |
title_sort |
A Markov-Random-Field Approach for Extracting Straight-Line Segments of Roofs From High-Resolution Aerial Images |
author |
Marcato Fernandes, Vanessa Jordao [UNESP] |
author_facet |
Marcato Fernandes, Vanessa Jordao [UNESP] Dal Poz, Aluir Porfirio [UNESP] |
author_role |
author |
author2 |
Dal Poz, Aluir Porfirio [UNESP] |
author2_role |
author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) |
dc.contributor.author.fl_str_mv |
Marcato Fernandes, Vanessa Jordao [UNESP] Dal Poz, Aluir Porfirio [UNESP] |
dc.subject.por.fl_str_mv |
Airborne laser scanner (ALS) Markov random field (MRF) straight line |
topic |
Airborne laser scanner (ALS) Markov random field (MRF) straight line |
description |
This paper proposes a method for extracting groups of straight lines that represent roof boundary sides and roof ridgelines from high-resolution aerial images using corresponding airborne laser scanner (ALS) roof polyhedrons as initial approximations. Our motivation for this research is the possibility of future use of resulting image-space straight lines in several applications. For example, straight lines that represent roof boundary sides and precisely extracted from a high-resolution image can be back-projected onto the ALS-derived building polyhedron for refining the accuracy of its boundary. The proposed method is based on two main steps. First, straight lines that are candidates to represent roof ridgelines and roof boundary sides of a building are extracted from the aerial image. The ALS-derived roof boundary sides and roof ridgelines are projected onto the image space, and bolding boxes are constructed around the projected straight lines while considering the projection errors. This allows the extraction of straight lines within the bounding boxes. Second, a group of straight lines that represent roof boundary sides and roof ridgelines of a selected building is obtained through the optimization of a Markov random field-based energy function using the genetic algorithm optimization method. The formulation of this energy function considers several attributes, such as the proximity of the extracted straight lines to the corresponding projected ALS-derived roof polyhedron and the rectangularity (extracted straight lines that intersect at nearly 90 degrees). In order to validate the proposed method, four experiments were accomplished using high-resolution aerial images, along with interior and exterior orientation parameters, and available ALS-derived building roof polyhedrons. The obtained results have shown that the method works properly and this will be qualitatively and quantitatively demonstrated in this research. |
publishDate |
2016 |
dc.date.none.fl_str_mv |
2016-12-01 2018-11-26T17:15:38Z 2018-11-26T17:15:38Z |
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 |
http://dx.doi.org/10.1109/JSTARS.2016.2601068 Ieee Journal Of Selected Topics In Applied Earth Observations And Remote Sensing. Piscataway: Ieee-inst Electrical Electronics Engineers Inc, v. 9, n. 12, p. 5493-5505, 2016. 1939-1404 http://hdl.handle.net/11449/162325 10.1109/JSTARS.2016.2601068 WOS:000391468100020 WOS000391468100020.pdf |
url |
http://dx.doi.org/10.1109/JSTARS.2016.2601068 http://hdl.handle.net/11449/162325 |
identifier_str_mv |
Ieee Journal Of Selected Topics In Applied Earth Observations And Remote Sensing. Piscataway: Ieee-inst Electrical Electronics Engineers Inc, v. 9, n. 12, p. 5493-5505, 2016. 1939-1404 10.1109/JSTARS.2016.2601068 WOS:000391468100020 WOS000391468100020.pdf |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Ieee Journal Of Selected Topics In Applied Earth Observations And Remote Sensing 1,547 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
5493-5505 application/pdf |
dc.publisher.none.fl_str_mv |
Ieee-inst Electrical Electronics Engineers Inc |
publisher.none.fl_str_mv |
Ieee-inst Electrical Electronics Engineers Inc |
dc.source.none.fl_str_mv |
Web of Science 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_ |
1808129503739772928 |