Mapping deciduous forests by using time series of filtered MODIS NDVI and neural networks

Detalhes bibliográficos
Autor(a) principal: Oliveira, Thomaz Chaves de Andrade
Data de Publicação: 2015
Outros Autores: Carvalho, Luis Marcelo Tavares de, Oliveira, Luciano Teixeira de, Martinhago, Adriana Zanella, Acerbi Júnior, Fausto Weimar, Lima, Mariana Peres de
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UFLA
Texto Completo: http://www.cerne.ufla.br/site/index.php/CERNE/article/view/673
http://repositorio.ufla.br/jspui/handle/1/14002
Resumo: Multi-temporal images are now of standard use in remote sensing of vegetation during monitoring and classification.Temporal vegetation signatures (i. e., vegetation indices as functions of time) generated, poses many challenges, primarily due tosignal to noise-related issues. This study investigates which methods generate the most appropriate smoothed curves of vegetationsignatures on MODIS NDVI time series. The filtering techniques compared were the HANTS algorithm which is based on Fourieranalyses and Wavelet temporal algorithm which uses the wavelet analysis to generate the smoothed curves. The study was conductedin four different regions of the Minas Gerais State. The smoothed data were used as input data vectors for vegetation classificationby means of artificial neural networks for comparison purpose. A comparison of the results was ultimately discussed in this workshowing encouraging results and similarity between the two filtering techniques used.
id UFLA_a546ed2a4d883fb0f5a1c9f5e0191d3b
oai_identifier_str oai:localhost:1/14002
network_acronym_str UFLA
network_name_str Repositório Institucional da UFLA
repository_id_str
spelling Mapping deciduous forests by using time series of filtered MODIS NDVI and neural networksMapamento de florestas decícuas através de redes neurais artificiais e séries temporais de NDVI MODISRemote sensingSignal processingTime seriesWavelets analysisFourierSensoriamento remotoProcessamento de sinaisSéries temporaisAnálise waveletMulti-temporal images are now of standard use in remote sensing of vegetation during monitoring and classification.Temporal vegetation signatures (i. e., vegetation indices as functions of time) generated, poses many challenges, primarily due tosignal to noise-related issues. This study investigates which methods generate the most appropriate smoothed curves of vegetationsignatures on MODIS NDVI time series. The filtering techniques compared were the HANTS algorithm which is based on Fourieranalyses and Wavelet temporal algorithm which uses the wavelet analysis to generate the smoothed curves. The study was conductedin four different regions of the Minas Gerais State. The smoothed data were used as input data vectors for vegetation classificationby means of artificial neural networks for comparison purpose. A comparison of the results was ultimately discussed in this workshowing encouraging results and similarity between the two filtering techniques used.Imagens multitemporais são de pronominal uso no Sensoriamento Remoto, para o monitoramento e classificação davegetação. As decorrentes assinaturas temporais da vegetação possuem muitos desafios na sua utilização em razão da elevadarelação sinal/ruído. Este estudo investigou dois métodos para gerar assinaturas temporais suavizadas de vegetação do índice devegetação de diferença normalizada (NDVI), sendo estas originadas do sensor MODIS. As técnicas de filtragem utilizadas foram oalgoritmo baseado em Fourier HANTS e algoritmo Wavelet Temporal que utiliza análise Wavelet. O estudo foi conduzido em 4diferentes conjuntos de dados, correspondente a áreas separadas geograficamente no estado de Minas Gerais. Para realizar acomparação entre as séries temporais filtradas pelos diferentes algoritmos, as séries filtradas foram utilizadas como entradas dedados para classificação da vegetação em diferentes fitofisionomias. A Classificação foi feita por meio das redes neurais artificiais. Oresultado dessa classificação mostrou similaridade entre os métodos de filtragem de séries temporais NDVI comparados neste trabalho.Universidade Federal de Lavras (UFLA), Departamento de Ciências Florestais (DCF)2015-10-292017-08-01T20:13:17Z2017-08-01T20:13:17Z2017-08-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttp://www.cerne.ufla.br/site/index.php/CERNE/article/view/673OLIVEIRA, T. C. de A. et al. Mapping deciduous forests by using time series of filtered MODIS NDVI and neural networks. CERNE, Lavras, v. 16, n. 2, p. 123-130, abr./jun. 2010.http://repositorio.ufla.br/jspui/handle/1/14002CERNE; Vol 16 No 2 (2010); 123–1302317-63420104-7760reponame:Repositório Institucional da UFLAinstname:Universidade Federal de Lavras (UFLA)instacron:UFLAenghttp://www.cerne.ufla.br/site/index.php/CERNE/article/view/673/561Copyright (c) 2015 CERNEinfo:eu-repo/semantics/openAccessOliveira, Thomaz Chaves de AndradeCarvalho, Luis Marcelo Tavares deOliveira, Luciano Teixeira deMartinhago, Adriana ZanellaAcerbi Júnior, Fausto WeimarLima, Mariana Peres de2020-09-20T23:13:03Zoai:localhost:1/14002Repositório InstitucionalPUBhttp://repositorio.ufla.br/oai/requestnivaldo@ufla.br || repositorio.biblioteca@ufla.bropendoar:2020-09-20T23:13:03Repositório Institucional da UFLA - Universidade Federal de Lavras (UFLA)false
dc.title.none.fl_str_mv Mapping deciduous forests by using time series of filtered MODIS NDVI and neural networks
Mapamento de florestas decícuas através de redes neurais artificiais e séries temporais de NDVI MODIS
title Mapping deciduous forests by using time series of filtered MODIS NDVI and neural networks
spellingShingle Mapping deciduous forests by using time series of filtered MODIS NDVI and neural networks
Oliveira, Thomaz Chaves de Andrade
Remote sensing
Signal processing
Time series
Wavelets analysis
Fourier
Sensoriamento remoto
Processamento de sinais
Séries temporais
Análise wavelet
title_short Mapping deciduous forests by using time series of filtered MODIS NDVI and neural networks
title_full Mapping deciduous forests by using time series of filtered MODIS NDVI and neural networks
title_fullStr Mapping deciduous forests by using time series of filtered MODIS NDVI and neural networks
title_full_unstemmed Mapping deciduous forests by using time series of filtered MODIS NDVI and neural networks
title_sort Mapping deciduous forests by using time series of filtered MODIS NDVI and neural networks
author Oliveira, Thomaz Chaves de Andrade
author_facet Oliveira, Thomaz Chaves de Andrade
Carvalho, Luis Marcelo Tavares de
Oliveira, Luciano Teixeira de
Martinhago, Adriana Zanella
Acerbi Júnior, Fausto Weimar
Lima, Mariana Peres de
author_role author
author2 Carvalho, Luis Marcelo Tavares de
Oliveira, Luciano Teixeira de
Martinhago, Adriana Zanella
Acerbi Júnior, Fausto Weimar
Lima, Mariana Peres de
author2_role author
author
author
author
author
dc.contributor.author.fl_str_mv Oliveira, Thomaz Chaves de Andrade
Carvalho, Luis Marcelo Tavares de
Oliveira, Luciano Teixeira de
Martinhago, Adriana Zanella
Acerbi Júnior, Fausto Weimar
Lima, Mariana Peres de
dc.subject.por.fl_str_mv Remote sensing
Signal processing
Time series
Wavelets analysis
Fourier
Sensoriamento remoto
Processamento de sinais
Séries temporais
Análise wavelet
topic Remote sensing
Signal processing
Time series
Wavelets analysis
Fourier
Sensoriamento remoto
Processamento de sinais
Séries temporais
Análise wavelet
description Multi-temporal images are now of standard use in remote sensing of vegetation during monitoring and classification.Temporal vegetation signatures (i. e., vegetation indices as functions of time) generated, poses many challenges, primarily due tosignal to noise-related issues. This study investigates which methods generate the most appropriate smoothed curves of vegetationsignatures on MODIS NDVI time series. The filtering techniques compared were the HANTS algorithm which is based on Fourieranalyses and Wavelet temporal algorithm which uses the wavelet analysis to generate the smoothed curves. The study was conductedin four different regions of the Minas Gerais State. The smoothed data were used as input data vectors for vegetation classificationby means of artificial neural networks for comparison purpose. A comparison of the results was ultimately discussed in this workshowing encouraging results and similarity between the two filtering techniques used.
publishDate 2015
dc.date.none.fl_str_mv 2015-10-29
2017-08-01T20:13:17Z
2017-08-01T20:13:17Z
2017-08-01
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://www.cerne.ufla.br/site/index.php/CERNE/article/view/673
OLIVEIRA, T. C. de A. et al. Mapping deciduous forests by using time series of filtered MODIS NDVI and neural networks. CERNE, Lavras, v. 16, n. 2, p. 123-130, abr./jun. 2010.
http://repositorio.ufla.br/jspui/handle/1/14002
url http://www.cerne.ufla.br/site/index.php/CERNE/article/view/673
http://repositorio.ufla.br/jspui/handle/1/14002
identifier_str_mv OLIVEIRA, T. C. de A. et al. Mapping deciduous forests by using time series of filtered MODIS NDVI and neural networks. CERNE, Lavras, v. 16, n. 2, p. 123-130, abr./jun. 2010.
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv http://www.cerne.ufla.br/site/index.php/CERNE/article/view/673/561
dc.rights.driver.fl_str_mv Copyright (c) 2015 CERNE
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Copyright (c) 2015 CERNE
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universidade Federal de Lavras (UFLA), Departamento de Ciências Florestais (DCF)
publisher.none.fl_str_mv Universidade Federal de Lavras (UFLA), Departamento de Ciências Florestais (DCF)
dc.source.none.fl_str_mv CERNE; Vol 16 No 2 (2010); 123–130
2317-6342
0104-7760
reponame:Repositório Institucional da UFLA
instname:Universidade Federal de Lavras (UFLA)
instacron:UFLA
instname_str Universidade Federal de Lavras (UFLA)
instacron_str UFLA
institution UFLA
reponame_str Repositório Institucional da UFLA
collection Repositório Institucional da UFLA
repository.name.fl_str_mv Repositório Institucional da UFLA - Universidade Federal de Lavras (UFLA)
repository.mail.fl_str_mv nivaldo@ufla.br || repositorio.biblioteca@ufla.br
_version_ 1815438969420120064

Registros relacionados