[en] MANY-TO-MANY FULLY CONVOLUTIONAL RECURRENT NETWORKS FOR MULTITEMPORAL CROP RECOGNITION USING SAR IMAGE SEQUENCES
[pt] Este trabalho propõe e avalia arquiteturas profundas para o reconhecimento de culturas agrícolas a partir de seqüências de imagens multitemporais de sensoriamento remoto. Essas arquiteturas combinam a capacidade de modelar contexto espacial prórpia de redes totalmente convolucionais com a capac...
Main Author: | |
---|---|
Other Authors: | |
Language: | en |
Published: |
MAXWELL
2020
|
Subjects: | |
Online Access: | https://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=47770@1 https://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=47770@2 http://doi.org/10.17771/PUCRio.acad.47770 |
id |
ndltd-puc-rio.br-oai-MAXWELL.puc-rio.br-47770 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-puc-rio.br-oai-MAXWELL.puc-rio.br-477702020-05-01T03:20:49Z[en] MANY-TO-MANY FULLY CONVOLUTIONAL RECURRENT NETWORKS FOR MULTITEMPORAL CROP RECOGNITION USING SAR IMAGE SEQUENCES [pt] RECONHECIMENTO DE CULTURAS AGRÍCOLAS UTILIZANDO REDES RECORRENTES A PARTIR DE SEQUÊNCIAS DE IMAGENS SAR JORGE ANDRES CHAMORRO MARTINEZ[pt] SENSORIAMENTO REMOTO[en] REMOTE SENSING[pt] RECONHECIMENTO DE CULTURAS[en] CROP RECOGNITION[pt] REDES TOTALMENTE CONVOLUCIONAIS[en] FULLY CONVOLUTIONAL NETWORKS[pt] REDES RECORRENTES[en] RECURRENT NETWORKS[pt] Este trabalho propõe e avalia arquiteturas profundas para o reconhecimento de culturas agrícolas a partir de seqüências de imagens multitemporais de sensoriamento remoto. Essas arquiteturas combinam a capacidade de modelar contexto espacial prórpia de redes totalmente convolucionais com a capacidade de modelr o contexto temporal de redes recorrentes para a previsão prever culturas agrícolas em cada data de uma seqüência de imagens multitemporais. O desempenho destes métodos é avaliado em dois conjuntos de dados públicos. Ambas as áreas apresentam alta dinâmica espaçotemporal devido ao clima tropical/subtropical e a práticas agrícolas locais, como a rotação de culturas. Nos experimentos verificou-se que as arquiteturas propostas superaram os métodos recentes baseados em redes recorrentes em termos de Overall Accuracy (OA) e F1-score médio por classe.[en] This work proposes and evaluates deep learning architectures for multi-date agricultural crop recognition from remote sensing image sequences. These architectures combine the spatial modelling capabilities of fully convolutional networks and the sequential modelling capabilities of recurrent networks into end-to-end architectures so-called fully convolutional recurrent networks, configured to predict crop type at multiple dates from a multitemporal image sequence. Their performance is assessed over two publicly available datasets. Both datasets present highly spatio-temporal dynamics due to their tropical/sub-tropical climate and local agricultural practices such as crop rotation. The experiments indicated that the proposed architectures outperformed state of the art methods based on recurrent networks in terms of Overall Accuracy (OA) and per-class average F1 score.MAXWELLRAUL QUEIROZ FEITOSA2020-04-30TEXTOhttps://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=47770@1https://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=47770@2http://doi.org/10.17771/PUCRio.acad.47770en |
collection |
NDLTD |
language |
en |
sources |
NDLTD |
topic |
[pt] SENSORIAMENTO REMOTO [en] REMOTE SENSING [pt] RECONHECIMENTO DE CULTURAS [en] CROP RECOGNITION [pt] REDES TOTALMENTE CONVOLUCIONAIS [en] FULLY CONVOLUTIONAL NETWORKS [pt] REDES RECORRENTES [en] RECURRENT NETWORKS |
spellingShingle |
[pt] SENSORIAMENTO REMOTO [en] REMOTE SENSING [pt] RECONHECIMENTO DE CULTURAS [en] CROP RECOGNITION [pt] REDES TOTALMENTE CONVOLUCIONAIS [en] FULLY CONVOLUTIONAL NETWORKS [pt] REDES RECORRENTES [en] RECURRENT NETWORKS JORGE ANDRES CHAMORRO MARTINEZ [en] MANY-TO-MANY FULLY CONVOLUTIONAL RECURRENT NETWORKS FOR MULTITEMPORAL CROP RECOGNITION USING SAR IMAGE SEQUENCES |
description |
[pt] Este trabalho propõe e avalia arquiteturas profundas para o reconhecimento de culturas agrícolas a partir de seqüências de imagens multitemporais de sensoriamento remoto. Essas arquiteturas combinam a capacidade de modelar contexto espacial prórpia de redes totalmente convolucionais com a capacidade de modelr o contexto temporal de redes recorrentes para a previsão prever culturas agrícolas em cada data de uma seqüência de imagens multitemporais. O desempenho destes métodos é avaliado em dois conjuntos de dados públicos. Ambas as áreas apresentam alta dinâmica espaçotemporal devido ao clima tropical/subtropical e a práticas agrícolas locais, como a rotação de culturas. Nos experimentos verificou-se que as arquiteturas
propostas superaram os métodos recentes baseados em redes recorrentes em termos de Overall Accuracy (OA) e F1-score médio por classe. === [en] This work proposes and evaluates deep learning architectures for multi-date agricultural crop recognition from remote sensing image sequences. These architectures combine the spatial modelling capabilities of fully convolutional networks and the sequential modelling capabilities of recurrent networks into end-to-end architectures so-called fully convolutional recurrent networks, configured to predict crop type at multiple dates from a multitemporal image sequence. Their performance is assessed over two publicly available datasets. Both datasets present highly spatio-temporal dynamics due to their tropical/sub-tropical climate and local agricultural practices such as crop rotation. The experiments indicated that the proposed architectures outperformed state of the art methods based on recurrent networks in terms of Overall Accuracy (OA) and per-class average F1 score. |
author2 |
RAUL QUEIROZ FEITOSA |
author_facet |
RAUL QUEIROZ FEITOSA JORGE ANDRES CHAMORRO MARTINEZ |
author |
JORGE ANDRES CHAMORRO MARTINEZ |
author_sort |
JORGE ANDRES CHAMORRO MARTINEZ |
title |
[en] MANY-TO-MANY FULLY CONVOLUTIONAL RECURRENT NETWORKS FOR MULTITEMPORAL CROP RECOGNITION USING SAR IMAGE SEQUENCES |
title_short |
[en] MANY-TO-MANY FULLY CONVOLUTIONAL RECURRENT NETWORKS FOR MULTITEMPORAL CROP RECOGNITION USING SAR IMAGE SEQUENCES |
title_full |
[en] MANY-TO-MANY FULLY CONVOLUTIONAL RECURRENT NETWORKS FOR MULTITEMPORAL CROP RECOGNITION USING SAR IMAGE SEQUENCES |
title_fullStr |
[en] MANY-TO-MANY FULLY CONVOLUTIONAL RECURRENT NETWORKS FOR MULTITEMPORAL CROP RECOGNITION USING SAR IMAGE SEQUENCES |
title_full_unstemmed |
[en] MANY-TO-MANY FULLY CONVOLUTIONAL RECURRENT NETWORKS FOR MULTITEMPORAL CROP RECOGNITION USING SAR IMAGE SEQUENCES |
title_sort |
[en] many-to-many fully convolutional recurrent networks for multitemporal crop recognition using sar image sequences |
publisher |
MAXWELL |
publishDate |
2020 |
url |
https://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=47770@1 https://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=47770@2 http://doi.org/10.17771/PUCRio.acad.47770 |
work_keys_str_mv |
AT jorgeandreschamorromartinez enmanytomanyfullyconvolutionalrecurrentnetworksformultitemporalcroprecognitionusingsarimagesequences AT jorgeandreschamorromartinez ptreconhecimentodeculturasagricolasutilizandoredesrecorrentesapartirdesequenciasdeimagenssar |
_version_ |
1719314150663913472 |