Classification of LiDAR data over building roofs using k-means and principal component analysis
Autor(a) principal: | |
---|---|
Data de Publicação: | 2018 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1590/S1982-21702018000100006 http://hdl.handle.net/11449/176161 |
Resumo: | The classification is an important step in the extraction of geometric primitives from LiDAR data. Normally, it is applied for the identification of points sampled on geometric primitives of interest. In the literature there are several studies that have explored the use of eigenvalues to classify LiDAR points into different classes or structures, such as corner, edge, and plane. However, in some works the classes are defined considering an ideal geometry, which can be affected by the inadequate sampling and/or by the presence of noise when using real data. To overcome this limitation, in this paper is proposed the use of metrics based on eigenvalues and the k-means method to carry out the classification. So, the concept of principal component analysis is used to obtain the eigenvalues and the derived metrics, while the k-means is applied to cluster the roof points in two classes: edge and non-edge. To evaluate the proposed method four test areas with different levels of complexity were selected. From the qualitative and quantitative analyses, it could be concluded that the proposed classification procedure gave satisfactory results, resulting in completeness and correctness above 92% for the non-edge class, and between 61% to 98% for the edge class. |
id |
UNSP_d356fef9b4bdb24aa10a3aab4afd5a0e |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/176161 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Classification of LiDAR data over building roofs using k-means and principal component analysisClassificação de dados LiDAR sobre telhados de edificações usando k-médias e análise de componentes principaisClassification of LiDAR pointsEdge pointsEigenvaluesK-means methodPrincipal component analysisThe classification is an important step in the extraction of geometric primitives from LiDAR data. Normally, it is applied for the identification of points sampled on geometric primitives of interest. In the literature there are several studies that have explored the use of eigenvalues to classify LiDAR points into different classes or structures, such as corner, edge, and plane. However, in some works the classes are defined considering an ideal geometry, which can be affected by the inadequate sampling and/or by the presence of noise when using real data. To overcome this limitation, in this paper is proposed the use of metrics based on eigenvalues and the k-means method to carry out the classification. So, the concept of principal component analysis is used to obtain the eigenvalues and the derived metrics, while the k-means is applied to cluster the roof points in two classes: edge and non-edge. To evaluate the proposed method four test areas with different levels of complexity were selected. From the qualitative and quantitative analyses, it could be concluded that the proposed classification procedure gave satisfactory results, resulting in completeness and correctness above 92% for the non-edge class, and between 61% to 98% for the edge class.Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Universidade Estadual Paulista Júlio de Mesquita Filho - UNESPUniversidade Estadual Paulista Júlio de Mesquita Filho – UNESP Departamento de CartografiaUniversidade Estadual Paulista Júlio de Mesquita Filho – UNESP Departamento de EstatísticaUniversidade Estadual Paulista Júlio de Mesquita Filho - UNESPUniversidade Estadual Paulista Júlio de Mesquita Filho – UNESP Departamento de CartografiaUniversidade Estadual Paulista Júlio de Mesquita Filho – UNESP Departamento de EstatísticaFAPESP: 2016/12167-5CNPq: 304189/2016-2Universidade Estadual Paulista (Unesp)dos Santos, Renato César [UNESP]Galo, Mauricio [UNESP]Tachibana, Vilma Mayumi [UNESP]2018-12-11T17:19:20Z2018-12-11T17:19:20Z2018-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article69-84application/pdfhttp://dx.doi.org/10.1590/S1982-21702018000100006Boletim de Ciencias Geodesicas, v. 24, n. 1, p. 69-84, 2018.1982-21701413-4853http://hdl.handle.net/11449/17616110.1590/S1982-21702018000100006S1982-217020180001000692-s2.0-85045150395S1982-21702018000100069.pdfScopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengBoletim de Ciencias Geodesicas0,188info:eu-repo/semantics/openAccess2024-06-18T15:02:07Zoai:repositorio.unesp.br:11449/176161Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-06T00:11:27.090664Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Classification of LiDAR data over building roofs using k-means and principal component analysis Classificação de dados LiDAR sobre telhados de edificações usando k-médias e análise de componentes principais |
title |
Classification of LiDAR data over building roofs using k-means and principal component analysis |
spellingShingle |
Classification of LiDAR data over building roofs using k-means and principal component analysis dos Santos, Renato César [UNESP] Classification of LiDAR points Edge points Eigenvalues K-means method Principal component analysis |
title_short |
Classification of LiDAR data over building roofs using k-means and principal component analysis |
title_full |
Classification of LiDAR data over building roofs using k-means and principal component analysis |
title_fullStr |
Classification of LiDAR data over building roofs using k-means and principal component analysis |
title_full_unstemmed |
Classification of LiDAR data over building roofs using k-means and principal component analysis |
title_sort |
Classification of LiDAR data over building roofs using k-means and principal component analysis |
author |
dos Santos, Renato César [UNESP] |
author_facet |
dos Santos, Renato César [UNESP] Galo, Mauricio [UNESP] Tachibana, Vilma Mayumi [UNESP] |
author_role |
author |
author2 |
Galo, Mauricio [UNESP] Tachibana, Vilma Mayumi [UNESP] |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (Unesp) |
dc.contributor.author.fl_str_mv |
dos Santos, Renato César [UNESP] Galo, Mauricio [UNESP] Tachibana, Vilma Mayumi [UNESP] |
dc.subject.por.fl_str_mv |
Classification of LiDAR points Edge points Eigenvalues K-means method Principal component analysis |
topic |
Classification of LiDAR points Edge points Eigenvalues K-means method Principal component analysis |
description |
The classification is an important step in the extraction of geometric primitives from LiDAR data. Normally, it is applied for the identification of points sampled on geometric primitives of interest. In the literature there are several studies that have explored the use of eigenvalues to classify LiDAR points into different classes or structures, such as corner, edge, and plane. However, in some works the classes are defined considering an ideal geometry, which can be affected by the inadequate sampling and/or by the presence of noise when using real data. To overcome this limitation, in this paper is proposed the use of metrics based on eigenvalues and the k-means method to carry out the classification. So, the concept of principal component analysis is used to obtain the eigenvalues and the derived metrics, while the k-means is applied to cluster the roof points in two classes: edge and non-edge. To evaluate the proposed method four test areas with different levels of complexity were selected. From the qualitative and quantitative analyses, it could be concluded that the proposed classification procedure gave satisfactory results, resulting in completeness and correctness above 92% for the non-edge class, and between 61% to 98% for the edge class. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018-12-11T17:19:20Z 2018-12-11T17:19:20Z 2018-01-01 |
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/10.1590/S1982-21702018000100006 Boletim de Ciencias Geodesicas, v. 24, n. 1, p. 69-84, 2018. 1982-2170 1413-4853 http://hdl.handle.net/11449/176161 10.1590/S1982-21702018000100006 S1982-21702018000100069 2-s2.0-85045150395 S1982-21702018000100069.pdf |
url |
http://dx.doi.org/10.1590/S1982-21702018000100006 http://hdl.handle.net/11449/176161 |
identifier_str_mv |
Boletim de Ciencias Geodesicas, v. 24, n. 1, p. 69-84, 2018. 1982-2170 1413-4853 10.1590/S1982-21702018000100006 S1982-21702018000100069 2-s2.0-85045150395 S1982-21702018000100069.pdf |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Boletim de Ciencias Geodesicas 0,188 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
69-84 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_ |
1808129593268240384 |