Improved fully convolutional network with conditional random fields for building extraction

Detalhes bibliográficos
Autor(a) principal: Shrestha, Sanjeevan
Data de Publicação: 2018
Outros Autores: Vanneschi, Leonardo
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: https://doi.org/10.3390/rs10071135
Resumo: Shrestha, S., & Vanneschi, L. (2018). Improved fully convolutional network with conditional random fields for building extraction. Remote Sensing, 10(7), [1135]. DOI: 10.3390/rs10071135
id RCAP_eb6e4e24a4f929f94f501ea98c7b34fd
oai_identifier_str oai:run.unl.pt:10362/43499
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Improved fully convolutional network with conditional random fields for building extractionBuilding extractionConditional random fieldsDeep convolutional neural networkFully convolutional networkHigh-resolution aerial imageryEarth and Planetary Sciences(all)SDG 11 - Sustainable Cities and CommunitiesShrestha, S., & Vanneschi, L. (2018). Improved fully convolutional network with conditional random fields for building extraction. Remote Sensing, 10(7), [1135]. DOI: 10.3390/rs10071135Building extraction from remotely sensed imagery plays an important role in urban planning, disaster management, navigation, updating geographic databases, and several other geospatial applications. Several published contributions dedicated to the applications of deep convolutional neural networks (DCNN) for building extraction using aerial/satellite imagery exists. However, in all these contributions, high accuracy is always obtained at the price of extremely complex and large network architectures. In this paper, we present an enhanced fully convolutional network (FCN) framework that is designed for building extraction of remotely sensed images by applying conditional random fields (CRFs). The main objective is to propose a methodology selecting a framework that balances high accuracy with low network complexity. A modern activation function, namely, the exponential linear unit (ELU), is applied to improve the performance of the fully convolutional network (FCN), thereby resulting in more accurate building prediction. To further reduce the noise (falsely classified buildings) and to sharpen the boundaries of the buildings, a post-processing conditional random fields (CRFs) is added at the end of the adopted convolutional neural network (CNN) framework. The experiments were conducted on Massachusetts building aerial imagery. The results show that our proposed framework outperformed the fully convolutional network (FCN), which is the existing baseline framework for semantic segmentation, in terms of performance measures such as the F1-score and IoU measure. Additionally, the proposed method outperformed a pre-existing classifier for building extraction using the same dataset in terms of the performance measures and network complexity.NOVA Information Management School (NOVA IMS)Information Management Research Center (MagIC) - NOVA Information Management SchoolRUNShrestha, SanjeevanVanneschi, Leonardo2018-08-06T22:10:57Z2018-07-012018-07-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttps://doi.org/10.3390/rs10071135eng2072-4292PURE: 5666361http://www.scopus.com/inward/record.url?scp=85050459863&partnerID=8YFLogxKhttps://doi.org/10.3390/rs10071135info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-03-11T04:23:28Zoai:run.unl.pt:10362/43499Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:31:40.874104Repositório 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 Improved fully convolutional network with conditional random fields for building extraction
title Improved fully convolutional network with conditional random fields for building extraction
spellingShingle Improved fully convolutional network with conditional random fields for building extraction
Shrestha, Sanjeevan
Building extraction
Conditional random fields
Deep convolutional neural network
Fully convolutional network
High-resolution aerial imagery
Earth and Planetary Sciences(all)
SDG 11 - Sustainable Cities and Communities
title_short Improved fully convolutional network with conditional random fields for building extraction
title_full Improved fully convolutional network with conditional random fields for building extraction
title_fullStr Improved fully convolutional network with conditional random fields for building extraction
title_full_unstemmed Improved fully convolutional network with conditional random fields for building extraction
title_sort Improved fully convolutional network with conditional random fields for building extraction
author Shrestha, Sanjeevan
author_facet Shrestha, Sanjeevan
Vanneschi, Leonardo
author_role author
author2 Vanneschi, Leonardo
author2_role author
dc.contributor.none.fl_str_mv NOVA Information Management School (NOVA IMS)
Information Management Research Center (MagIC) - NOVA Information Management School
RUN
dc.contributor.author.fl_str_mv Shrestha, Sanjeevan
Vanneschi, Leonardo
dc.subject.por.fl_str_mv Building extraction
Conditional random fields
Deep convolutional neural network
Fully convolutional network
High-resolution aerial imagery
Earth and Planetary Sciences(all)
SDG 11 - Sustainable Cities and Communities
topic Building extraction
Conditional random fields
Deep convolutional neural network
Fully convolutional network
High-resolution aerial imagery
Earth and Planetary Sciences(all)
SDG 11 - Sustainable Cities and Communities
description Shrestha, S., & Vanneschi, L. (2018). Improved fully convolutional network with conditional random fields for building extraction. Remote Sensing, 10(7), [1135]. DOI: 10.3390/rs10071135
publishDate 2018
dc.date.none.fl_str_mv 2018-08-06T22:10:57Z
2018-07-01
2018-07-01T00:00:00Z
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 https://doi.org/10.3390/rs10071135
url https://doi.org/10.3390/rs10071135
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 2072-4292
PURE: 5666361
http://www.scopus.com/inward/record.url?scp=85050459863&partnerID=8YFLogxK
https://doi.org/10.3390/rs10071135
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv 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_ 1799137939403309056

Registros relacionados