Hyperspectral Image Classification: An Analysis Employing CNN, LSTM, Transformer, and Attention Mechanism
Autor(a) principal: | |
---|---|
Data de Publicação: | 2016 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.26/44201 |
Resumo: | Hyperspectral images contain tens to hundreds of bands, implying a high spectral resolution. This high spectral resolution allows for obtaining a precise signature of structures and compounds that make up the captured scene. Among the types of processing that may be applied to Hyperspectral Images, classification using machine learning models stands out. The classification process is one of the most relevant steps for this type of image. It can extract information using spatial and spectral information and spatial-spectral fusion. Artificial Neural Network models have been gaining prominence among existing classification techniques. They can be applied to data with one, two, or three dimensions. Given the above, this work evaluates Convolutional Neural Network models with one, two, and three dimensions to identify the impact of classifying Hyperspectral Images with different types of convolution. We also expand the comparison to Recurrent Neural Network models, Attention Mechanism, and the Transformer architecture. Furthermore, a novelty pre-processing method is proposed for the classification process to avoid generating data leaks between training, validation, and testing data. The results demonstrated that using 1 Dimension Convolutional Neural Network (1D-CNN), Long Short-Term Memory (LSTM), and Transformer architectures reduces memory consumption and sample processing time and maintain a satisfactory classification performance up to 99% accuracy on larger datasets. In addition, the Transfomer architecture can approach the 2D-CNN and 3D-CNN architectures in accuracy using only spectral information. The results also show that using two or three dimensions convolution layers improves accuracy at the cost of greater memory consumption and processing time per sample. Furthermore, the pre-processing methodology guarantees the disassociation of training and testing data. |
id |
RCAP_d23828bdebf1c7134f509bcfd3b7961c |
---|---|
oai_identifier_str |
oai:comum.rcaap.pt:10400.26/44201 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Hyperspectral Image Classification: An Analysis Employing CNN, LSTM, Transformer, and Attention MechanismHyperspectral imagingCNNLSTMTransformerRemote sensingHyperspectral images contain tens to hundreds of bands, implying a high spectral resolution. This high spectral resolution allows for obtaining a precise signature of structures and compounds that make up the captured scene. Among the types of processing that may be applied to Hyperspectral Images, classification using machine learning models stands out. The classification process is one of the most relevant steps for this type of image. It can extract information using spatial and spectral information and spatial-spectral fusion. Artificial Neural Network models have been gaining prominence among existing classification techniques. They can be applied to data with one, two, or three dimensions. Given the above, this work evaluates Convolutional Neural Network models with one, two, and three dimensions to identify the impact of classifying Hyperspectral Images with different types of convolution. We also expand the comparison to Recurrent Neural Network models, Attention Mechanism, and the Transformer architecture. Furthermore, a novelty pre-processing method is proposed for the classification process to avoid generating data leaks between training, validation, and testing data. The results demonstrated that using 1 Dimension Convolutional Neural Network (1D-CNN), Long Short-Term Memory (LSTM), and Transformer architectures reduces memory consumption and sample processing time and maintain a satisfactory classification performance up to 99% accuracy on larger datasets. In addition, the Transfomer architecture can approach the 2D-CNN and 3D-CNN architectures in accuracy using only spectral information. The results also show that using two or three dimensions convolution layers improves accuracy at the cost of greater memory consumption and processing time per sample. Furthermore, the pre-processing methodology guarantees the disassociation of training and testing data.IEEERepositório ComumViel, FelipeRenato Cotrim MacielSeman, Laio OrielZeferino, Cesar AlbenesBezerra, EduardoLEITHARDT, VALDERI2023-03-17T11:14:48Z20162023-03-14T10:47:25Z2016-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.26/44201engcv-prod-316779110.1109/ACCESS.2023.3255164info: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:RCAAP2023-08-03T11:32:19Zoai:comum.rcaap.pt:10400.26/44201Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T17:45:10.416019Repositório 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 |
Hyperspectral Image Classification: An Analysis Employing CNN, LSTM, Transformer, and Attention Mechanism |
title |
Hyperspectral Image Classification: An Analysis Employing CNN, LSTM, Transformer, and Attention Mechanism |
spellingShingle |
Hyperspectral Image Classification: An Analysis Employing CNN, LSTM, Transformer, and Attention Mechanism Viel, Felipe Hyperspectral imaging CNN LSTM Transformer Remote sensing |
title_short |
Hyperspectral Image Classification: An Analysis Employing CNN, LSTM, Transformer, and Attention Mechanism |
title_full |
Hyperspectral Image Classification: An Analysis Employing CNN, LSTM, Transformer, and Attention Mechanism |
title_fullStr |
Hyperspectral Image Classification: An Analysis Employing CNN, LSTM, Transformer, and Attention Mechanism |
title_full_unstemmed |
Hyperspectral Image Classification: An Analysis Employing CNN, LSTM, Transformer, and Attention Mechanism |
title_sort |
Hyperspectral Image Classification: An Analysis Employing CNN, LSTM, Transformer, and Attention Mechanism |
author |
Viel, Felipe |
author_facet |
Viel, Felipe Renato Cotrim Maciel Seman, Laio Oriel Zeferino, Cesar Albenes Bezerra, Eduardo LEITHARDT, VALDERI |
author_role |
author |
author2 |
Renato Cotrim Maciel Seman, Laio Oriel Zeferino, Cesar Albenes Bezerra, Eduardo LEITHARDT, VALDERI |
author2_role |
author author author author author |
dc.contributor.none.fl_str_mv |
Repositório Comum |
dc.contributor.author.fl_str_mv |
Viel, Felipe Renato Cotrim Maciel Seman, Laio Oriel Zeferino, Cesar Albenes Bezerra, Eduardo LEITHARDT, VALDERI |
dc.subject.por.fl_str_mv |
Hyperspectral imaging CNN LSTM Transformer Remote sensing |
topic |
Hyperspectral imaging CNN LSTM Transformer Remote sensing |
description |
Hyperspectral images contain tens to hundreds of bands, implying a high spectral resolution. This high spectral resolution allows for obtaining a precise signature of structures and compounds that make up the captured scene. Among the types of processing that may be applied to Hyperspectral Images, classification using machine learning models stands out. The classification process is one of the most relevant steps for this type of image. It can extract information using spatial and spectral information and spatial-spectral fusion. Artificial Neural Network models have been gaining prominence among existing classification techniques. They can be applied to data with one, two, or three dimensions. Given the above, this work evaluates Convolutional Neural Network models with one, two, and three dimensions to identify the impact of classifying Hyperspectral Images with different types of convolution. We also expand the comparison to Recurrent Neural Network models, Attention Mechanism, and the Transformer architecture. Furthermore, a novelty pre-processing method is proposed for the classification process to avoid generating data leaks between training, validation, and testing data. The results demonstrated that using 1 Dimension Convolutional Neural Network (1D-CNN), Long Short-Term Memory (LSTM), and Transformer architectures reduces memory consumption and sample processing time and maintain a satisfactory classification performance up to 99% accuracy on larger datasets. In addition, the Transfomer architecture can approach the 2D-CNN and 3D-CNN architectures in accuracy using only spectral information. The results also show that using two or three dimensions convolution layers improves accuracy at the cost of greater memory consumption and processing time per sample. Furthermore, the pre-processing methodology guarantees the disassociation of training and testing data. |
publishDate |
2016 |
dc.date.none.fl_str_mv |
2016 2016-01-01T00:00:00Z 2023-03-17T11:14:48Z 2023-03-14T10:47:25Z |
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 |
http://hdl.handle.net/10400.26/44201 |
url |
http://hdl.handle.net/10400.26/44201 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
cv-prod-3167791 10.1109/ACCESS.2023.3255164 |
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.publisher.none.fl_str_mv |
IEEE |
publisher.none.fl_str_mv |
IEEE |
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_ |
1799131536786718720 |