Identification of Streetscape Compositions: A Deep Learning Approach
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | por eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | https://doi.org/10.47235/rmu.v8i1.140 |
Resumo: | The environment’s composition can have an impact on human behavior, however, this relationship remains uncertain until the cities' qualities and landscape can be analyzed empirically. Images obtained through Google Street View (GSV) enable a large volume of data for automated assessment of environmental characteristics. Deep learning techniques have advanced in the identification of compositional elements of the built environment. In this sense, this study seeks to investigate and test a procedure for identifying the configuration and composition of the urban landscape, classifying images obtained from GSV through a deep learning approach. From an image dataset of three different neighborhoods in Londrina-PR, a deep learning model for image classification was proposed. The model had a good performance, correctly attributing 87.6% of the samples to the corresponding neighborhoods in the case study. Compositional characteristics were empirically identified, considering the distribution of the samples in the obtained search space. The proposed model contributes to the definition of spatial units as well as in the measurement of environmental qualities, optimizing data collection, expanding sample sizes, and providing objectivity to results. This approach contributes to the expansion of city's analytical scales, identifying compositional and relational patterns in the understanding of elements influent in human behavior. |
id |
RCAP_b06638b71d155dee29a20eb774e99a16 |
---|---|
oai_identifier_str |
oai:ojs2.revistademorfologiaurbana.org:article/140 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Identification of Streetscape Compositions: A Deep Learning ApproachIdentificação de Composições da Paisagem Urbana: Uma abordagem de Deep Learningmorfologia urbanaambiente construídoaprendizado profundoclassificação de imagensgoogle street viewurban morphologybuilt environmentdeep learningimage classificationgoogle street viewThe environment’s composition can have an impact on human behavior, however, this relationship remains uncertain until the cities' qualities and landscape can be analyzed empirically. Images obtained through Google Street View (GSV) enable a large volume of data for automated assessment of environmental characteristics. Deep learning techniques have advanced in the identification of compositional elements of the built environment. In this sense, this study seeks to investigate and test a procedure for identifying the configuration and composition of the urban landscape, classifying images obtained from GSV through a deep learning approach. From an image dataset of three different neighborhoods in Londrina-PR, a deep learning model for image classification was proposed. The model had a good performance, correctly attributing 87.6% of the samples to the corresponding neighborhoods in the case study. Compositional characteristics were empirically identified, considering the distribution of the samples in the obtained search space. The proposed model contributes to the definition of spatial units as well as in the measurement of environmental qualities, optimizing data collection, expanding sample sizes, and providing objectivity to results. This approach contributes to the expansion of city's analytical scales, identifying compositional and relational patterns in the understanding of elements influent in human behavior.A composição do ambiente pode exercer impactos sobre comportamentos, no entanto, esta relação permanece incerta até que qualidades e a paisagem das cidades possam ser analisadas empiricamente. Imagens obtidas através do Google Street View (GSV) possibilitam um grande volume de dados para avaliação automatizada das características ambientais. Técnicas de deep learning tem avançado na identificação de elementos compositivos do ambiente construído. Neste sentido, este estudo busca investigar e testar um procedimento de identificação da configuração e composição da paisagem urbana, por meio da classificação de imagens obtidas pelo GSV. A partir de um banco de imagens de três bairros de Londrina-PR, um modelo de deep learning para classificação de imagens foi proposto. O modelo obteve um bom desempenho, atribuindo corretamente 87,6% das amostras dos respectivos bairros do estudo de caso. Características compositivas foram empiricamente identificadas, considerando a distribuição das amostras no espaço de busca obtido. O modelo proposto contribui na definição de recortes espaciais bem como na mensuração de qualidades ambientais, otimizando coletas de dados, ampliando amostras e conferindo objetividade aos resultados. Esta abordagem contribui na expansão das escalas analíticas da cidade, identificando padrões compositivos e relacionais para o entendimento de elementos influentes no comportamento humano.Portuguese-Speaking Network of Urban Morphology2020-06-30T00:00:00Zinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/otherinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttps://doi.org/10.47235/rmu.v8i1.140oai:ojs2.revistademorfologiaurbana.org:article/140Revista de Morfologia Urbana; Vol. 8 No. 1 (2020): Volume 8 n.1; e00140Revista de Morfologia Urbana; v. 8 n. 1 (2020): Volume 8 n.1; e001402182-7214reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAPporenghttp://revistademorfologiaurbana.org/index.php/rmu/article/view/140https://doi.org/10.47235/rmu.v8i1.140http://revistademorfologiaurbana.org/index.php/rmu/article/view/140/80http://revistademorfologiaurbana.org/index.php/rmu/article/view/140/82Copyright (c) 2020 Ana Luiza Favarão Leão, Hugo Queiroz Abonizio, Prof. Dr. Sylvio Barbon Júnior, Profa. Dra. Milena Kanashirohttps://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccessFavarão Leão, Ana LuizaQueiroz Abonizio, HugoBarbon Júnior, SylvioKanashiro, Milena2022-09-06T09:36:55Zoai:ojs2.revistademorfologiaurbana.org:article/140Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T15:34:43.754639Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Identification of Streetscape Compositions: A Deep Learning Approach Identificação de Composições da Paisagem Urbana: Uma abordagem de Deep Learning |
title |
Identification of Streetscape Compositions: A Deep Learning Approach |
spellingShingle |
Identification of Streetscape Compositions: A Deep Learning Approach Favarão Leão, Ana Luiza morfologia urbana ambiente construído aprendizado profundo classificação de imagens google street view urban morphology built environment deep learning image classification google street view |
title_short |
Identification of Streetscape Compositions: A Deep Learning Approach |
title_full |
Identification of Streetscape Compositions: A Deep Learning Approach |
title_fullStr |
Identification of Streetscape Compositions: A Deep Learning Approach |
title_full_unstemmed |
Identification of Streetscape Compositions: A Deep Learning Approach |
title_sort |
Identification of Streetscape Compositions: A Deep Learning Approach |
author |
Favarão Leão, Ana Luiza |
author_facet |
Favarão Leão, Ana Luiza Queiroz Abonizio, Hugo Barbon Júnior, Sylvio Kanashiro, Milena |
author_role |
author |
author2 |
Queiroz Abonizio, Hugo Barbon Júnior, Sylvio Kanashiro, Milena |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Favarão Leão, Ana Luiza Queiroz Abonizio, Hugo Barbon Júnior, Sylvio Kanashiro, Milena |
dc.subject.por.fl_str_mv |
morfologia urbana ambiente construído aprendizado profundo classificação de imagens google street view urban morphology built environment deep learning image classification google street view |
topic |
morfologia urbana ambiente construído aprendizado profundo classificação de imagens google street view urban morphology built environment deep learning image classification google street view |
description |
The environment’s composition can have an impact on human behavior, however, this relationship remains uncertain until the cities' qualities and landscape can be analyzed empirically. Images obtained through Google Street View (GSV) enable a large volume of data for automated assessment of environmental characteristics. Deep learning techniques have advanced in the identification of compositional elements of the built environment. In this sense, this study seeks to investigate and test a procedure for identifying the configuration and composition of the urban landscape, classifying images obtained from GSV through a deep learning approach. From an image dataset of three different neighborhoods in Londrina-PR, a deep learning model for image classification was proposed. The model had a good performance, correctly attributing 87.6% of the samples to the corresponding neighborhoods in the case study. Compositional characteristics were empirically identified, considering the distribution of the samples in the obtained search space. The proposed model contributes to the definition of spatial units as well as in the measurement of environmental qualities, optimizing data collection, expanding sample sizes, and providing objectivity to results. This approach contributes to the expansion of city's analytical scales, identifying compositional and relational patterns in the understanding of elements influent in human behavior. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-06-30T00:00:00Z |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/other |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://doi.org/10.47235/rmu.v8i1.140 oai:ojs2.revistademorfologiaurbana.org:article/140 |
url |
https://doi.org/10.47235/rmu.v8i1.140 |
identifier_str_mv |
oai:ojs2.revistademorfologiaurbana.org:article/140 |
dc.language.iso.fl_str_mv |
por eng |
language |
por eng |
dc.relation.none.fl_str_mv |
http://revistademorfologiaurbana.org/index.php/rmu/article/view/140 https://doi.org/10.47235/rmu.v8i1.140 http://revistademorfologiaurbana.org/index.php/rmu/article/view/140/80 http://revistademorfologiaurbana.org/index.php/rmu/article/view/140/82 |
dc.rights.driver.fl_str_mv |
https://creativecommons.org/licenses/by/4.0 info:eu-repo/semantics/openAccess |
rights_invalid_str_mv |
https://creativecommons.org/licenses/by/4.0 |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf application/pdf |
dc.publisher.none.fl_str_mv |
Portuguese-Speaking Network of Urban Morphology |
publisher.none.fl_str_mv |
Portuguese-Speaking Network of Urban Morphology |
dc.source.none.fl_str_mv |
Revista de Morfologia Urbana; Vol. 8 No. 1 (2020): Volume 8 n.1; e00140 Revista de Morfologia Urbana; v. 8 n. 1 (2020): Volume 8 n.1; e00140 2182-7214 reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799130211699130368 |