Cargando…

Hybrid Dilated Convolution with Multi-Scale Residual Fusion Network for Hyperspectral Image Classification

The convolutional neural network (CNN) has been proven to have better performance in hyperspectral image (HSI) classification than traditional methods. Traditional CNN on hyperspectral image classification is used to pay more attention to spectral features and ignore spatial information. In this pap...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Chenming, Qiu, Zelin, Cao, Xueying, Chen, Zhonghao, Gao, Hongmin, Hua, Zaijun
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8151123/
https://www.ncbi.nlm.nih.gov/pubmed/34068823
http://dx.doi.org/10.3390/mi12050545
_version_ 1783698309563547648
author Li, Chenming
Qiu, Zelin
Cao, Xueying
Chen, Zhonghao
Gao, Hongmin
Hua, Zaijun
author_facet Li, Chenming
Qiu, Zelin
Cao, Xueying
Chen, Zhonghao
Gao, Hongmin
Hua, Zaijun
author_sort Li, Chenming
collection PubMed
description The convolutional neural network (CNN) has been proven to have better performance in hyperspectral image (HSI) classification than traditional methods. Traditional CNN on hyperspectral image classification is used to pay more attention to spectral features and ignore spatial information. In this paper, a new HSI model called local and hybrid dilated convolution fusion network (LDFN) was proposed, which fuses the local information of details and rich spatial features by expanding the perception field. The details of our local and hybrid dilated convolution fusion network methods are as follows. First, many operations are selected, such as standard convolution, average pooling, dropout and batch normalization. Then, fusion operations of local and hybrid dilated convolution are included to extract rich spatial-spectral information. Last, different convolution layers are gathered into residual fusion networks and finally input into the softmax layer to classify. Three widely hyperspectral datasets (i.e., Salinas, Pavia University and Indian Pines) have been used in the experiments, which show that LDFN outperforms state-of-art classifiers.
format Online
Article
Text
id pubmed-8151123
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-81511232021-05-27 Hybrid Dilated Convolution with Multi-Scale Residual Fusion Network for Hyperspectral Image Classification Li, Chenming Qiu, Zelin Cao, Xueying Chen, Zhonghao Gao, Hongmin Hua, Zaijun Micromachines (Basel) Article The convolutional neural network (CNN) has been proven to have better performance in hyperspectral image (HSI) classification than traditional methods. Traditional CNN on hyperspectral image classification is used to pay more attention to spectral features and ignore spatial information. In this paper, a new HSI model called local and hybrid dilated convolution fusion network (LDFN) was proposed, which fuses the local information of details and rich spatial features by expanding the perception field. The details of our local and hybrid dilated convolution fusion network methods are as follows. First, many operations are selected, such as standard convolution, average pooling, dropout and batch normalization. Then, fusion operations of local and hybrid dilated convolution are included to extract rich spatial-spectral information. Last, different convolution layers are gathered into residual fusion networks and finally input into the softmax layer to classify. Three widely hyperspectral datasets (i.e., Salinas, Pavia University and Indian Pines) have been used in the experiments, which show that LDFN outperforms state-of-art classifiers. MDPI 2021-05-10 /pmc/articles/PMC8151123/ /pubmed/34068823 http://dx.doi.org/10.3390/mi12050545 Text en © 2021 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
Li, Chenming
Qiu, Zelin
Cao, Xueying
Chen, Zhonghao
Gao, Hongmin
Hua, Zaijun
Hybrid Dilated Convolution with Multi-Scale Residual Fusion Network for Hyperspectral Image Classification
title Hybrid Dilated Convolution with Multi-Scale Residual Fusion Network for Hyperspectral Image Classification
title_full Hybrid Dilated Convolution with Multi-Scale Residual Fusion Network for Hyperspectral Image Classification
title_fullStr Hybrid Dilated Convolution with Multi-Scale Residual Fusion Network for Hyperspectral Image Classification
title_full_unstemmed Hybrid Dilated Convolution with Multi-Scale Residual Fusion Network for Hyperspectral Image Classification
title_short Hybrid Dilated Convolution with Multi-Scale Residual Fusion Network for Hyperspectral Image Classification
title_sort hybrid dilated convolution with multi-scale residual fusion network for hyperspectral image classification
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8151123/
https://www.ncbi.nlm.nih.gov/pubmed/34068823
http://dx.doi.org/10.3390/mi12050545
work_keys_str_mv AT lichenming hybriddilatedconvolutionwithmultiscaleresidualfusionnetworkforhyperspectralimageclassification
AT qiuzelin hybriddilatedconvolutionwithmultiscaleresidualfusionnetworkforhyperspectralimageclassification
AT caoxueying hybriddilatedconvolutionwithmultiscaleresidualfusionnetworkforhyperspectralimageclassification
AT chenzhonghao hybriddilatedconvolutionwithmultiscaleresidualfusionnetworkforhyperspectralimageclassification
AT gaohongmin hybriddilatedconvolutionwithmultiscaleresidualfusionnetworkforhyperspectralimageclassification
AT huazaijun hybriddilatedconvolutionwithmultiscaleresidualfusionnetworkforhyperspectralimageclassification