Fechar
Metadados

1. Identificação
Tipo de ReferênciaArtigo em Revista Científica (Journal Article)
Sitemtc-m21d.sid.inpe.br
Código do Detentorisadg {BR SPINPE} ibi 8JMKD3MGPCW/3DT298S
Identificador8JMKD3MGP3W34T/45HFHL8
Repositóriosid.inpe.br/mtc-m21d/2021/10.04.15.37   (acesso restrito)
Última Atualização2021:10.04.15.37.15 (UTC) simone
Repositório de Metadadossid.inpe.br/mtc-m21d/2021/10.04.15.37.15
Última Atualização dos Metadados2022:04.04.04.50.16 (UTC) administrator
DOI10.1016/j.isprsjprs.2021.08.026
ISSN0924-2716
Chave de CitaçãoSotoVegaCoFeOrAlHeRo:2021:UnDoAd
TítuloAn unsupervised domain adaptation approach for change detection and its application to deforestation mapping in tropical biomes
Ano2021
MêsNov.
Data de Acesso18 maio 2024
Tipo de Trabalhojournal article
Tipo SecundárioPRE PI
Número de Arquivos1
Tamanho22364 KiB
2. Contextualização
Autor1 Soto Vega, Pedro Juan
2 Costa, Gilson Alexandre Ostwald Pedro da
3 Feitosa, Raul Queiroz
4 Ortega Adarme, Mabel Ximena
5 Almeida, Cláudio Aparecido de
6 Heipke, Christian
7 Rottensteiner, Franz
Grupo1
2
3
4
5 DIPE1-COGPI-INPE-MCTI-GOV-BR
Afiliação1 Universidade Federal do Rio de Janeiro (UFRJ)
2 Universidade do Estado do Rio de Janeiro (UERJ)
3 Universidade Federal do Rio de Janeiro (UFRJ)
4 Universidade Federal do Rio de Janeiro (UFRJ)
5 Instituto Nacional de Pesquisas Espaciais (INPE)
6 Leibniz Universitat Hannover (LUH)
7 Leibniz Universitat Hannover (LUH)
Endereço de e-Mail do Autor1
2
3
4
5 claudio.almeida@inpe.br
RevistaISPRS Journal of Photogrammetry and Remote Sensing
Volume181
Páginas113-128
Nota SecundáriaA1_GEOCIÊNCIAS A2_INTERDISCIPLINAR A2_CIÊNCIAS_AMBIENTAIS B1_ENGENHARIAS_IV B1_BIODIVERSIDADE C_CIÊNCIAS_AGRÁRIAS_I
Histórico (UTC)2021-10-04 15:37:15 :: simone -> administrator ::
2021-10-04 15:37:16 :: administrator -> simone :: 2021
2021-12-16 17:44:25 :: simone -> administrator :: 2021
2022-04-04 04:50:16 :: administrator -> simone :: 2021
3. Conteúdo e estrutura
É a matriz ou uma cópia?é a matriz
Estágio do Conteúdoconcluido
Transferível1
Tipo do ConteúdoExternal Contribution
Tipo de Versãopublisher
Palavras-ChaveChange detection
CycleGAN
Deep learning
Deforestation detection
Domain adaptation
Remote sensing
ResumoChanges in environmental conditions, geographical variability and different sensor properties typically make it almost impossible to employ previously trained classifiers for new data without a significant drop in classification accuracy. Domain adaptation (DA) techniques been proven useful to alleviate that problem. In particular, appearance adaptation techniques may be used to adapt images from a specific dataset in such a way that the generated images have a style that is similar to the images from another dataset. Such techniques are, however, prone to creating artifacts that hinder proper classification of the adapted images. In this work we propose an unsupervised DA approach for change detection tasks, which is based on a particular appearance adaptation method: the Cycle-Consistent Generative Adversarial Network (CycleGAN). Specifically, we extend that method by introducing additional constraints in the training phase of the model components, which make it preserve the semantic structure and class transitions in the adapted images. We evaluate the proposed approach on a deforestation detection application, considering different sites in the Amazon rain-forest and in the Brazilian Cerrado (savanna) using Landsat-8 images. In the experiments, each site corresponds to a domain, and the accuracy of a classifier trained with images and references from one (source) domain is measured in the classification of another (target) domain. The results show that the proposed approach is successful in producing artifact-free adapted images, which can be satisfactory classified by the pre-trained source classifiers. On average, the accuracies achieved in the classification of the adapted images outperformed the baselines (when no adaptation was made) by 7.1% in terms of mean average precision, and 9.1% in terms of F1-Score. To the best of our knowledge, the proposed method is the first unsupervised domain adaptation approach devised for change detection.
ÁreaSRE
ArranjoAn unsupervised domain...
Conteúdo da Pasta docacessar
Conteúdo da Pasta sourcenão têm arquivos
Conteúdo da Pasta agreement
agreement.html 04/10/2021 12:37 1.0 KiB 
4. Condições de acesso e uso
Idiomaen
Arquivo Alvovega_unsupervised.pdf
Grupo de Usuáriossimone
Grupo de Leitoresadministrator
simone
Visibilidadeshown
Política de Arquivamentodenypublisher denyfinaldraft24
Permissão de Leituradeny from all and allow from 150.163
Permissão de Atualizaçãonão transferida
5. Fontes relacionadas
Unidades Imediatamente Superiores8JMKD3MGPCW/46L2FGP
Lista de Itens Citandosid.inpe.br/bibdigital/2022/04.04.04.47 1
DivulgaçãoWEBSCI; PORTALCAPES; COMPENDEX; SCOPUS.
Acervo Hospedeirourlib.net/www/2021/06.04.03.40
6. Notas
Campos Vaziosalternatejournal archivist callnumber copyholder copyright creatorhistory descriptionlevel e-mailaddress format isbn label lineage mark mirrorrepository nextedition notes number orcid parameterlist parentrepositories previousedition previouslowerunit progress project resumeid rightsholder schedulinginformation secondarydate secondarykey session shorttitle sponsor subject tertiarymark tertiarytype url
7. Controle da descrição
e-Mail (login)simone
atualizar 


Fechar