Cargando…

Robust Spatial–Spectral Squeeze–Excitation AdaBound Dense Network (SE-AB-Densenet) for Hyperspectral Image Classification

Increasing importance in the field of artificial intelligence has led to huge progress in remote sensing. Deep learning approaches have made tremendous progress in hyperspectral image (HSI) classification. However, the complexity in classifying the HSI data using a common convolutional neural networ...

Descripción completa

Detalles Bibliográficos
Autores principales: Munishamaiaha, Kavitha, Rajagopal, Gayathri, Venkatesan, Dhilip Kumar, Arif, Muhammad, Vicoveanu, Dragos, Chiuchisan, Iuliana, Izdrui, Diana, Geman, Oana
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9105163/
https://www.ncbi.nlm.nih.gov/pubmed/35590921
http://dx.doi.org/10.3390/s22093229
_version_ 1784707972878827520
author Munishamaiaha, Kavitha
Rajagopal, Gayathri
Venkatesan, Dhilip Kumar
Arif, Muhammad
Vicoveanu, Dragos
Chiuchisan, Iuliana
Izdrui, Diana
Geman, Oana
author_facet Munishamaiaha, Kavitha
Rajagopal, Gayathri
Venkatesan, Dhilip Kumar
Arif, Muhammad
Vicoveanu, Dragos
Chiuchisan, Iuliana
Izdrui, Diana
Geman, Oana
author_sort Munishamaiaha, Kavitha
collection PubMed
description Increasing importance in the field of artificial intelligence has led to huge progress in remote sensing. Deep learning approaches have made tremendous progress in hyperspectral image (HSI) classification. However, the complexity in classifying the HSI data using a common convolutional neural network is still a challenge. Further, the network architecture becomes more complex when different spatial–spectral feature information is extracted. Usually, CNN has a large number of trainable parameters, which increases the computational complexity of HSI data. In this paper, an optimized squeeze–excitation AdaBound dense network (SE-AB-DenseNet) is designed to emphasize the significant spatial–spectral features of HSI data. The dense network is combined with the AdaBound and squeeze–excitation modules to give lower computation costs and better classification performance. The AdaBound optimizer gives the proposed model the ability to improve its stability and enhance its classification accuracy by approximately 2%. Additionally, the cutout regularization technique is used for HSI spatial–spectral classification to overcome the problem of overfitting. The experiments were carried out on two commonly used hyperspectral datasets (Indian Pines and Salinas). The experiment results on the datasets show a competitive classification accuracy when compared with state-of-the-art methods with limited training samples. From the SE-AB-DenseNet with the cutout model, the overall accuracies for the Indian Pines and Salinas datasets were observed to be 99.37 and 99.78, respectively.
format Online
Article
Text
id pubmed-9105163
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-91051632022-05-14 Robust Spatial–Spectral Squeeze–Excitation AdaBound Dense Network (SE-AB-Densenet) for Hyperspectral Image Classification Munishamaiaha, Kavitha Rajagopal, Gayathri Venkatesan, Dhilip Kumar Arif, Muhammad Vicoveanu, Dragos Chiuchisan, Iuliana Izdrui, Diana Geman, Oana Sensors (Basel) Article Increasing importance in the field of artificial intelligence has led to huge progress in remote sensing. Deep learning approaches have made tremendous progress in hyperspectral image (HSI) classification. However, the complexity in classifying the HSI data using a common convolutional neural network is still a challenge. Further, the network architecture becomes more complex when different spatial–spectral feature information is extracted. Usually, CNN has a large number of trainable parameters, which increases the computational complexity of HSI data. In this paper, an optimized squeeze–excitation AdaBound dense network (SE-AB-DenseNet) is designed to emphasize the significant spatial–spectral features of HSI data. The dense network is combined with the AdaBound and squeeze–excitation modules to give lower computation costs and better classification performance. The AdaBound optimizer gives the proposed model the ability to improve its stability and enhance its classification accuracy by approximately 2%. Additionally, the cutout regularization technique is used for HSI spatial–spectral classification to overcome the problem of overfitting. The experiments were carried out on two commonly used hyperspectral datasets (Indian Pines and Salinas). The experiment results on the datasets show a competitive classification accuracy when compared with state-of-the-art methods with limited training samples. From the SE-AB-DenseNet with the cutout model, the overall accuracies for the Indian Pines and Salinas datasets were observed to be 99.37 and 99.78, respectively. MDPI 2022-04-22 /pmc/articles/PMC9105163/ /pubmed/35590921 http://dx.doi.org/10.3390/s22093229 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Munishamaiaha, Kavitha
Rajagopal, Gayathri
Venkatesan, Dhilip Kumar
Arif, Muhammad
Vicoveanu, Dragos
Chiuchisan, Iuliana
Izdrui, Diana
Geman, Oana
Robust Spatial–Spectral Squeeze–Excitation AdaBound Dense Network (SE-AB-Densenet) for Hyperspectral Image Classification
title Robust Spatial–Spectral Squeeze–Excitation AdaBound Dense Network (SE-AB-Densenet) for Hyperspectral Image Classification
title_full Robust Spatial–Spectral Squeeze–Excitation AdaBound Dense Network (SE-AB-Densenet) for Hyperspectral Image Classification
title_fullStr Robust Spatial–Spectral Squeeze–Excitation AdaBound Dense Network (SE-AB-Densenet) for Hyperspectral Image Classification
title_full_unstemmed Robust Spatial–Spectral Squeeze–Excitation AdaBound Dense Network (SE-AB-Densenet) for Hyperspectral Image Classification
title_short Robust Spatial–Spectral Squeeze–Excitation AdaBound Dense Network (SE-AB-Densenet) for Hyperspectral Image Classification
title_sort robust spatial–spectral squeeze–excitation adabound dense network (se-ab-densenet) for hyperspectral image classification
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9105163/
https://www.ncbi.nlm.nih.gov/pubmed/35590921
http://dx.doi.org/10.3390/s22093229
work_keys_str_mv AT munishamaiahakavitha robustspatialspectralsqueezeexcitationadabounddensenetworkseabdensenetforhyperspectralimageclassification
AT rajagopalgayathri robustspatialspectralsqueezeexcitationadabounddensenetworkseabdensenetforhyperspectralimageclassification
AT venkatesandhilipkumar robustspatialspectralsqueezeexcitationadabounddensenetworkseabdensenetforhyperspectralimageclassification
AT arifmuhammad robustspatialspectralsqueezeexcitationadabounddensenetworkseabdensenetforhyperspectralimageclassification
AT vicoveanudragos robustspatialspectralsqueezeexcitationadabounddensenetworkseabdensenetforhyperspectralimageclassification
AT chiuchisaniuliana robustspatialspectralsqueezeexcitationadabounddensenetworkseabdensenetforhyperspectralimageclassification
AT izdruidiana robustspatialspectralsqueezeexcitationadabounddensenetworkseabdensenetforhyperspectralimageclassification
AT gemanoana robustspatialspectralsqueezeexcitationadabounddensenetworkseabdensenetforhyperspectralimageclassification