Improved fully convolutional network with conditional random field for building extraction

Detalhes bibliográficos
Autor(a) principal: Shrestra, Sanjeevan
Data de Publicação: 2018
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10362/33652
Resumo: Dissertation submitted in partial fulfilment of the requirements for the degree of Master of Science in Geospatial Technologies
id RCAP_9833d4fd82d51d4f97e4c67d1d83fe51
oai_identifier_str oai:run.unl.pt:10362/33652
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 field for building extractionBuilding ExtractionHigh Resolution Aerial ImageryDeep LearningDeep Convolutional Neural NetworkFully Convolutional NetworkConditional Random FieldDissertation submitted in partial fulfilment of the requirements for the degree of Master of Science in Geospatial TechnologiesBuilding 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 are dedicated to the applications of Deep Convolutional Neural Network (DCNN) for building extraction using aerial/satellite imagery exists; however, in all these contributions a good accuracy is always paid at the price of extremely complex and large network architectures. In this paper, we present an enhanced Fully Convolutional Network (FCN) framework especially molded for building extraction of remotely sensed images by applying Conditional Random Field (CRF). The main purpose here is to propose a framework which balances maximum accuracy with less network complexity. The modern activation function called Exponential Linear Unit (ELU) is applied to improve the performance of the Fully Convolutional Network (FCN), resulting in more, yet accurate building prediction. To further reduce the noise (false classified buildings) and to sharpen the boundary of the buildings, a post processing CRF 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 FCN baseline, which is the existing baseline framework for semantic segmentation, in term of performance measure, the F1-score and Intersection Over Union (IoU) measure. Additionally, the proposed method stood superior to the pre-existing classifier for building extraction using the same dataset in terms of performance measure and network complexity at once.Vanneschi, LeonardoHillen, FlorianMuseros, LledóRUNShrestra, Sanjeevan2018-04-02T18:11:12Z2018-02-272018-02-27T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/33652TID:201892499enginfo: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:RCAAP2024-03-11T04:18:28Zoai:run.unl.pt:10362/33652Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:30:03.109068Repositório 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 field for building extraction
title Improved fully convolutional network with conditional random field for building extraction
spellingShingle Improved fully convolutional network with conditional random field for building extraction
Shrestra, Sanjeevan
Building Extraction
High Resolution Aerial Imagery
Deep Learning
Deep Convolutional Neural Network
Fully Convolutional Network
Conditional Random Field
title_short Improved fully convolutional network with conditional random field for building extraction
title_full Improved fully convolutional network with conditional random field for building extraction
title_fullStr Improved fully convolutional network with conditional random field for building extraction
title_full_unstemmed Improved fully convolutional network with conditional random field for building extraction
title_sort Improved fully convolutional network with conditional random field for building extraction
author Shrestra, Sanjeevan
author_facet Shrestra, Sanjeevan
author_role author
dc.contributor.none.fl_str_mv Vanneschi, Leonardo
Hillen, Florian
Museros, Lledó
RUN
dc.contributor.author.fl_str_mv Shrestra, Sanjeevan
dc.subject.por.fl_str_mv Building Extraction
High Resolution Aerial Imagery
Deep Learning
Deep Convolutional Neural Network
Fully Convolutional Network
Conditional Random Field
topic Building Extraction
High Resolution Aerial Imagery
Deep Learning
Deep Convolutional Neural Network
Fully Convolutional Network
Conditional Random Field
description Dissertation submitted in partial fulfilment of the requirements for the degree of Master of Science in Geospatial Technologies
publishDate 2018
dc.date.none.fl_str_mv 2018-04-02T18:11:12Z
2018-02-27
2018-02-27T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/33652
TID:201892499
url http://hdl.handle.net/10362/33652
identifier_str_mv TID:201892499
dc.language.iso.fl_str_mv eng
language eng
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_ 1799137924646699008

Registros relacionados