Extração de vias combinando métodos de detecção de regiões e linhas em imagens de intensidade de pulso laser

Detalhes bibliográficos
Autor(a) principal: Mendes, Tatiana Sussel Gonçalves [UNESP]
Data de Publicação: 2011
Outros Autores: Dal Poz, Aluir Porfírio [UNESP]
Tipo de documento: Artigo
Idioma: eng
por
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://www.ufrgs.br/igeo/pesquisas/38-3.html
http://hdl.handle.net/11449/73028
Resumo: This paper aims at extracting street centerlines from previously isolated street regions by using the image of laser scanning intensity. In this image, streets are easily identified, since they manifest as dark, elongate ribbons contrasting with background objects. The intensity image is segmented by using the region growing technique, which generates regions representing the streets. From these regions, the street centerlines are extracted in two manners. The first one is through the Steger lines detection method combined with a line length thresholding by which lines being shorter than a minimum length are removed. The other manner is by combining the skeletonization method of regions based on the Medial Axis Transform and with a pruning process to eliminate as much as possible the ramifications. Experiments showed that the Steger-based method provided results better than the method based on skeletonization.
id UNSP_0a3544fda9772ba22a7e1809520d0219
oai_identifier_str oai:repositorio.unesp.br:11449/73028
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Extração de vias combinando métodos de detecção de regiões e linhas em imagens de intensidade de pulso laserTreet extraction combining methods for region and line detection from laser scanning intensity imagesDetection of linesSegmentationSkeletonizationStreet extractionThis paper aims at extracting street centerlines from previously isolated street regions by using the image of laser scanning intensity. In this image, streets are easily identified, since they manifest as dark, elongate ribbons contrasting with background objects. The intensity image is segmented by using the region growing technique, which generates regions representing the streets. From these regions, the street centerlines are extracted in two manners. The first one is through the Steger lines detection method combined with a line length thresholding by which lines being shorter than a minimum length are removed. The other manner is by combining the skeletonization method of regions based on the Medial Axis Transform and with a pruning process to eliminate as much as possible the ramifications. Experiments showed that the Steger-based method provided results better than the method based on skeletonization.Universidade Estadual Paulista, Rua Roberto Simonsen, 305, CEP 19060-900. Presidente Prudente, SPDepartamento de Cartografia Universidade Estadual Paulista, Rua Roberto Simonsen, 305, CEP 19060-900, Presidente Prudente, SPUniversidade Estadual Paulista, Rua Roberto Simonsen, 305, CEP 19060-900. Presidente Prudente, SPDepartamento de Cartografia Universidade Estadual Paulista, Rua Roberto Simonsen, 305, CEP 19060-900, Presidente Prudente, SPUniversidade Estadual Paulista (Unesp)Mendes, Tatiana Sussel Gonçalves [UNESP]Dal Poz, Aluir Porfírio [UNESP]2014-05-27T11:26:19Z2014-05-27T11:26:19Z2011-12-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article235-249application/pdfhttp://www.ufrgs.br/igeo/pesquisas/38-3.htmlPesquisas em Geociencias, v. 38, n. 3, p. 235-249, 2011.1518-23981807-9806http://hdl.handle.net/11449/730282-s2.0-848694440062-s2.0-84869444006.pdfScopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengporPesquisas em Geociencias0,152info:eu-repo/semantics/openAccess2024-06-18T15:01:26Zoai:repositorio.unesp.br:11449/73028Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-06-18T15:01:26Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Extração de vias combinando métodos de detecção de regiões e linhas em imagens de intensidade de pulso laser
Treet extraction combining methods for region and line detection from laser scanning intensity images
title Extração de vias combinando métodos de detecção de regiões e linhas em imagens de intensidade de pulso laser
spellingShingle Extração de vias combinando métodos de detecção de regiões e linhas em imagens de intensidade de pulso laser
Mendes, Tatiana Sussel Gonçalves [UNESP]
Detection of lines
Segmentation
Skeletonization
Street extraction
title_short Extração de vias combinando métodos de detecção de regiões e linhas em imagens de intensidade de pulso laser
title_full Extração de vias combinando métodos de detecção de regiões e linhas em imagens de intensidade de pulso laser
title_fullStr Extração de vias combinando métodos de detecção de regiões e linhas em imagens de intensidade de pulso laser
title_full_unstemmed Extração de vias combinando métodos de detecção de regiões e linhas em imagens de intensidade de pulso laser
title_sort Extração de vias combinando métodos de detecção de regiões e linhas em imagens de intensidade de pulso laser
author Mendes, Tatiana Sussel Gonçalves [UNESP]
author_facet Mendes, Tatiana Sussel Gonçalves [UNESP]
Dal Poz, Aluir Porfírio [UNESP]
author_role author
author2 Dal Poz, Aluir Porfírio [UNESP]
author2_role author
dc.contributor.none.fl_str_mv Universidade Estadual Paulista (Unesp)
dc.contributor.author.fl_str_mv Mendes, Tatiana Sussel Gonçalves [UNESP]
Dal Poz, Aluir Porfírio [UNESP]
dc.subject.por.fl_str_mv Detection of lines
Segmentation
Skeletonization
Street extraction
topic Detection of lines
Segmentation
Skeletonization
Street extraction
description This paper aims at extracting street centerlines from previously isolated street regions by using the image of laser scanning intensity. In this image, streets are easily identified, since they manifest as dark, elongate ribbons contrasting with background objects. The intensity image is segmented by using the region growing technique, which generates regions representing the streets. From these regions, the street centerlines are extracted in two manners. The first one is through the Steger lines detection method combined with a line length thresholding by which lines being shorter than a minimum length are removed. The other manner is by combining the skeletonization method of regions based on the Medial Axis Transform and with a pruning process to eliminate as much as possible the ramifications. Experiments showed that the Steger-based method provided results better than the method based on skeletonization.
publishDate 2011
dc.date.none.fl_str_mv 2011-12-01
2014-05-27T11:26:19Z
2014-05-27T11:26:19Z
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://www.ufrgs.br/igeo/pesquisas/38-3.html
Pesquisas em Geociencias, v. 38, n. 3, p. 235-249, 2011.
1518-2398
1807-9806
http://hdl.handle.net/11449/73028
2-s2.0-84869444006
2-s2.0-84869444006.pdf
url http://www.ufrgs.br/igeo/pesquisas/38-3.html
http://hdl.handle.net/11449/73028
identifier_str_mv Pesquisas em Geociencias, v. 38, n. 3, p. 235-249, 2011.
1518-2398
1807-9806
2-s2.0-84869444006
2-s2.0-84869444006.pdf
dc.language.iso.fl_str_mv eng
por
language eng
por
dc.relation.none.fl_str_mv Pesquisas em Geociencias
0,152
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 235-249
application/pdf
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_ 1803045292948324352