3D: Shape Features for Objects Classification from Terrestrial Lidar Point Clouds

A mobile laser scanner is a valuable tool to collect 3D information especially in urban regions, where vertical objects, like walls, poles and trees, need to be mapped. The collected point clouds can be used to segment objects and classify them according to their shape. Nevertheless, the segmentatio...

ver descrição completa

Na minha lista:
Detalhes bibliográficos
Principais autores: Silva Centeno, Jorge Antonio, Bugalski de Andrade Peixoto, Elizabete
Formato: Online
Idioma:por
eng
Publicado em: Universidade Federal do Rio Grande do Norte
Endereço do item:https://periodicos.ufrn.br/revistadoregne/article/view/32658
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!
id oai:periodicos.ufrn.br:article-32658
record_format ojs
spelling oai:periodicos.ufrn.br:article-326582024-01-03T23:27:29Z 3D: Shape Features for Objects Classification from Terrestrial Lidar Point Clouds Descritores de Forma 3D para Classificação de Objetos em Nuvens de Pontos Lidar Terrestre: Shape Features for Objects Classification from Terrestrial Lidar Point Clouds Silva Centeno, Jorge Antonio Bugalski de Andrade Peixoto, Elizabete A mobile laser scanner is a valuable tool to collect 3D information especially in urban regions, where vertical objects, like walls, poles and trees, need to be mapped. The collected point clouds can be used to segment objects and classify them according to their shape. Nevertheless, the segmentation and classification steps still need tools to analyze 3D point clouds. In this paper it is introduces a method to describe 3D shape from point clouds obtained by mobile laser scanner within the context of classification of urban furniture. The initial aim is to describe the 3D shape of objects located at the top of poles, but the approach can be extended to other objects. For this purpose, the distribution of the points is analyzed with help of the eigenvalues of the variance-covariance matrix. It is proposed the use of two parameters, one related to planarity and another to elongation, that are normalized in the range between zero and one, which allows easier description of the shape in terms of just two well-known terms. O laser scanner móvel é uma ferramenta valiosa para coletar informações 3D, especialmente em regiões urbanas, onde objetos verticais, como paredes, postes e árvores, precisam ser mapeados. As nuvens de pontos coletadas podem ser usadas para segmentar objetos e classificá-los de acordo com sua forma. No entanto, as etapas de segmentação e classificação ainda precisam de ferramentas para analisar nuvens de pontos 3D. Neste artigo é apresentado um método para descrever a forma 3D a partir de nuvens de pontos obtidas por scanner laser móvel dentro do contexto de classificação de mobiliário urbano. O objetivo inicial é descrever a forma de objetos instalados em postes, mas a abordagem pode ser estendida a outros objetos. Para tanto, a distribuição dos pontos é analisada com o auxílio dos autovalores da matriz variância-covariância e os respectivos autovalores. Propõe-se a utilização de dois parâmetros, um relacionado à planaridade e outro ao alongamento, que são normalizados na faixa entre zero e um, o que permite uma descrição mais fácil da forma em termos de apenas dois termos bem conhecidos. Universidade Federal do Rio Grande do Norte 2023-12-06 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf application/pdf https://periodicos.ufrn.br/revistadoregne/article/view/32658 Notheast Geoscience Journal; Vol. 9 No. 2 (2023); 156-169 Revista de Geociências do Nordeste; v. 9 n. 2 (2023); 156-169 2447-3359 10.21680/2447-3359.2023v9n2 por eng https://periodicos.ufrn.br/revistadoregne/article/view/32658/17965 https://periodicos.ufrn.br/revistadoregne/article/view/32658/17966 Copyright (c) 2023 Revista de Geociências do Nordeste https://creativecommons.org/licenses/by/4.0
institution Periódicos UFRN
collection Portal de Pediódicos Eletrônicos da UFRN
language por
eng
format Online
author Silva Centeno, Jorge Antonio
Bugalski de Andrade Peixoto, Elizabete
spellingShingle Silva Centeno, Jorge Antonio
Bugalski de Andrade Peixoto, Elizabete
3D: Shape Features for Objects Classification from Terrestrial Lidar Point Clouds
author_facet Silva Centeno, Jorge Antonio
Bugalski de Andrade Peixoto, Elizabete
author_sort Silva Centeno, Jorge Antonio
title 3D: Shape Features for Objects Classification from Terrestrial Lidar Point Clouds
title_short 3D: Shape Features for Objects Classification from Terrestrial Lidar Point Clouds
title_full 3D: Shape Features for Objects Classification from Terrestrial Lidar Point Clouds
title_fullStr 3D: Shape Features for Objects Classification from Terrestrial Lidar Point Clouds
title_full_unstemmed 3D: Shape Features for Objects Classification from Terrestrial Lidar Point Clouds
title_sort 3d: shape features for objects classification from terrestrial lidar point clouds
description A mobile laser scanner is a valuable tool to collect 3D information especially in urban regions, where vertical objects, like walls, poles and trees, need to be mapped. The collected point clouds can be used to segment objects and classify them according to their shape. Nevertheless, the segmentation and classification steps still need tools to analyze 3D point clouds. In this paper it is introduces a method to describe 3D shape from point clouds obtained by mobile laser scanner within the context of classification of urban furniture. The initial aim is to describe the 3D shape of objects located at the top of poles, but the approach can be extended to other objects. For this purpose, the distribution of the points is analyzed with help of the eigenvalues of the variance-covariance matrix. It is proposed the use of two parameters, one related to planarity and another to elongation, that are normalized in the range between zero and one, which allows easier description of the shape in terms of just two well-known terms.
publisher Universidade Federal do Rio Grande do Norte
publishDate 2023
url https://periodicos.ufrn.br/revistadoregne/article/view/32658
work_keys_str_mv AT silvacentenojorgeantonio 3dshapefeaturesforobjectsclassificationfromterrestriallidarpointclouds
AT bugalskideandradepeixotoelizabete 3dshapefeaturesforobjectsclassificationfromterrestriallidarpointclouds
AT silvacentenojorgeantonio descritoresdeforma3dparaclassificacaodeobjetosemnuvensdepontoslidarterrestreshapefeaturesforobjectsclassificationfromterrestriallidarpointclouds
AT bugalskideandradepeixotoelizabete descritoresdeforma3dparaclassificacaodeobjetosemnuvensdepontoslidarterrestreshapefeaturesforobjectsclassificationfromterrestriallidarpointclouds
_version_ 1790059826619875328

Registros relacionados