3D ROAD EXTRACTION USING A STEREO PAIR OF AERIAL IMAGES

Detalhes bibliográficos
Autor(a) principal: Dal Poz, A. P. [UNESP]
Data de Publicação: 2010
Outros Autores: Silva, J. F. C. [UNESP], Gallis, R. A. B. [UNESP], ISPRS
Tipo de documento: Artigo de conferência
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://hdl.handle.net/11449/196082
Resumo: Road extraction from aerial and satellite imagery is of fundamental importance in the context of spatial data capturing and updating for GIS (Geographic Information System) applications. This article proposes a semiautomatic methodology for 3D road extraction from digital images. The dynamic programming (DP) algorithm is used to carry out the optimisation process in the object-space, instead of doing it in the image-space such as the DP traditional methodologies. This means that road centrelines are directly traced in the object-space, implying that a mathematical relationship is necessary to connect road points in object-and image-space. This allows the integration of radiometric information from images into the associate energy function. Although the methodology can operate in different modes (mono-plotting or stereo-plotting), and with several image types, including multisensor images, this paper presents details of our stereo-based approach involving a stereo pair of aerial images. In order to initialise the extraction procedure, a few seed points are necessary to be supplied in the object-space to sparsely and coarsely describe the roads. We visually identify these points on the stereo images and project them onto the object-space. Each road is extracted separately by an iterative scheme based on the DP optimisation algorithm. Each iteration cycle is carried out by means of a polyline densification followed by a DP optimisation. The polyline densification is carried out by linearly interpolating middle points between every adjacent vertices of the current polyline. Preliminary results have shown that the proposed methodology works properly.
id UNSP_c459445d8ec1fa74beb01a793c52a021
oai_identifier_str oai:repositorio.unesp.br:11449/196082
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling 3D ROAD EXTRACTION USING A STEREO PAIR OF AERIAL IMAGESDynamic ProgrammingRoad ModelFeature ExtractionRoad ExtractionAerial ImagesRoad extraction from aerial and satellite imagery is of fundamental importance in the context of spatial data capturing and updating for GIS (Geographic Information System) applications. This article proposes a semiautomatic methodology for 3D road extraction from digital images. The dynamic programming (DP) algorithm is used to carry out the optimisation process in the object-space, instead of doing it in the image-space such as the DP traditional methodologies. This means that road centrelines are directly traced in the object-space, implying that a mathematical relationship is necessary to connect road points in object-and image-space. This allows the integration of radiometric information from images into the associate energy function. Although the methodology can operate in different modes (mono-plotting or stereo-plotting), and with several image types, including multisensor images, this paper presents details of our stereo-based approach involving a stereo pair of aerial images. In order to initialise the extraction procedure, a few seed points are necessary to be supplied in the object-space to sparsely and coarsely describe the roads. We visually identify these points on the stereo images and project them onto the object-space. Each road is extracted separately by an iterative scheme based on the DP optimisation algorithm. Each iteration cycle is carried out by means of a polyline densification followed by a DP optimisation. The polyline densification is carried out by linearly interpolating middle points between every adjacent vertices of the current polyline. Preliminary results have shown that the proposed methodology works properly.Sao Paulo State Univ, Dept Cartog, Presidente Prudente, SP, BrazilSao Paulo State Univ, Dept Cartog, Presidente Prudente, SP, BrazilCopernicus Gesellschaft MbhUniversidade Estadual Paulista (Unesp)Dal Poz, A. P. [UNESP]Silva, J. F. C. [UNESP]Gallis, R. A. B. [UNESP]ISPRS2020-12-10T19:32:45Z2020-12-10T19:32:45Z2010-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject42010 Canadian Geomatics Conference And Symposium Of Commission I, Isprs Convergence In Geomatics - Shaping Canada's Competitive Landscape. Gottingen: Copernicus Gesellschaft Mbh, v. 38, 4 p., 2010.2194-9034http://hdl.handle.net/11449/196082WOS:000358301700060Web of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPeng2010 Canadian Geomatics Conference And Symposium Of Commission I, Isprs Convergence In Geomatics - Shaping Canada's Competitive Landscapeinfo:eu-repo/semantics/openAccess2024-06-18T15:02:38Zoai:repositorio.unesp.br:11449/196082Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T17:22:41.113782Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv 3D ROAD EXTRACTION USING A STEREO PAIR OF AERIAL IMAGES
title 3D ROAD EXTRACTION USING A STEREO PAIR OF AERIAL IMAGES
spellingShingle 3D ROAD EXTRACTION USING A STEREO PAIR OF AERIAL IMAGES
Dal Poz, A. P. [UNESP]
Dynamic Programming
Road Model
Feature Extraction
Road Extraction
Aerial Images
title_short 3D ROAD EXTRACTION USING A STEREO PAIR OF AERIAL IMAGES
title_full 3D ROAD EXTRACTION USING A STEREO PAIR OF AERIAL IMAGES
title_fullStr 3D ROAD EXTRACTION USING A STEREO PAIR OF AERIAL IMAGES
title_full_unstemmed 3D ROAD EXTRACTION USING A STEREO PAIR OF AERIAL IMAGES
title_sort 3D ROAD EXTRACTION USING A STEREO PAIR OF AERIAL IMAGES
author Dal Poz, A. P. [UNESP]
author_facet Dal Poz, A. P. [UNESP]
Silva, J. F. C. [UNESP]
Gallis, R. A. B. [UNESP]
ISPRS
author_role author
author2 Silva, J. F. C. [UNESP]
Gallis, R. A. B. [UNESP]
ISPRS
author2_role author
author
author
dc.contributor.none.fl_str_mv Universidade Estadual Paulista (Unesp)
dc.contributor.author.fl_str_mv Dal Poz, A. P. [UNESP]
Silva, J. F. C. [UNESP]
Gallis, R. A. B. [UNESP]
ISPRS
dc.subject.por.fl_str_mv Dynamic Programming
Road Model
Feature Extraction
Road Extraction
Aerial Images
topic Dynamic Programming
Road Model
Feature Extraction
Road Extraction
Aerial Images
description Road extraction from aerial and satellite imagery is of fundamental importance in the context of spatial data capturing and updating for GIS (Geographic Information System) applications. This article proposes a semiautomatic methodology for 3D road extraction from digital images. The dynamic programming (DP) algorithm is used to carry out the optimisation process in the object-space, instead of doing it in the image-space such as the DP traditional methodologies. This means that road centrelines are directly traced in the object-space, implying that a mathematical relationship is necessary to connect road points in object-and image-space. This allows the integration of radiometric information from images into the associate energy function. Although the methodology can operate in different modes (mono-plotting or stereo-plotting), and with several image types, including multisensor images, this paper presents details of our stereo-based approach involving a stereo pair of aerial images. In order to initialise the extraction procedure, a few seed points are necessary to be supplied in the object-space to sparsely and coarsely describe the roads. We visually identify these points on the stereo images and project them onto the object-space. Each road is extracted separately by an iterative scheme based on the DP optimisation algorithm. Each iteration cycle is carried out by means of a polyline densification followed by a DP optimisation. The polyline densification is carried out by linearly interpolating middle points between every adjacent vertices of the current polyline. Preliminary results have shown that the proposed methodology works properly.
publishDate 2010
dc.date.none.fl_str_mv 2010-01-01
2020-12-10T19:32:45Z
2020-12-10T19:32:45Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/conferenceObject
format conferenceObject
status_str publishedVersion
dc.identifier.uri.fl_str_mv 2010 Canadian Geomatics Conference And Symposium Of Commission I, Isprs Convergence In Geomatics - Shaping Canada's Competitive Landscape. Gottingen: Copernicus Gesellschaft Mbh, v. 38, 4 p., 2010.
2194-9034
http://hdl.handle.net/11449/196082
WOS:000358301700060
identifier_str_mv 2010 Canadian Geomatics Conference And Symposium Of Commission I, Isprs Convergence In Geomatics - Shaping Canada's Competitive Landscape. Gottingen: Copernicus Gesellschaft Mbh, v. 38, 4 p., 2010.
2194-9034
WOS:000358301700060
url http://hdl.handle.net/11449/196082
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 2010 Canadian Geomatics Conference And Symposium Of Commission I, Isprs Convergence In Geomatics - Shaping Canada's Competitive Landscape
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 4
dc.publisher.none.fl_str_mv Copernicus Gesellschaft Mbh
publisher.none.fl_str_mv Copernicus Gesellschaft Mbh
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_ 1808128801911078912