An Advanced Spectral–Spatial Classification Framework for Hyperspectral Imagery Based on DeepLab v3+

DeepLab v3+ neural network shows excellent performance in semantic segmentation. In this paper, we proposed a segmentation framework based on DeepLab v3+ neural network and applied it to the problem of hyperspectral imagery classification (HSIC). The dimensionality reduction of the hyperspectral ima...

Full description

Bibliographic Details
Main Authors: Yifan Si, Dawei Gong, Yang Guo, Xinhua Zhu, Qiangsheng Huang, Julian Evans, Sailing He, Yaoran Sun
Format: Article
Language:English
Published: MDPI AG 2021-06-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/11/12/5703
_version_ 1797529495261937664
author Yifan Si
Dawei Gong
Yang Guo
Xinhua Zhu
Qiangsheng Huang
Julian Evans
Sailing He
Yaoran Sun
author_facet Yifan Si
Dawei Gong
Yang Guo
Xinhua Zhu
Qiangsheng Huang
Julian Evans
Sailing He
Yaoran Sun
author_sort Yifan Si
collection DOAJ
description DeepLab v3+ neural network shows excellent performance in semantic segmentation. In this paper, we proposed a segmentation framework based on DeepLab v3+ neural network and applied it to the problem of hyperspectral imagery classification (HSIC). The dimensionality reduction of the hyperspectral image is performed using principal component analysis (PCA). DeepLab v3+ is used to extract spatial features, and those are fused with spectral features. A support vector machine (SVM) classifier is used for fitting and classification. Experimental results show that the framework proposed in this paper outperforms most traditional machine learning algorithms and deep-learning algorithms in hyperspectral imagery classification tasks.
first_indexed 2024-03-10T10:14:43Z
format Article
id doaj.art-73aa45f496814eeaab440eed7984288e
institution Directory Open Access Journal
issn 2076-3417
language English
last_indexed 2024-03-10T10:14:43Z
publishDate 2021-06-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj.art-73aa45f496814eeaab440eed7984288e2023-11-22T00:53:29ZengMDPI AGApplied Sciences2076-34172021-06-011112570310.3390/app11125703An Advanced Spectral–Spatial Classification Framework for Hyperspectral Imagery Based on DeepLab v3+Yifan Si0Dawei Gong1Yang Guo2Xinhua Zhu3Qiangsheng Huang4Julian Evans5Sailing He6Yaoran Sun7National Engineering Research Center for Optical Instruments, Centre for Optical and Electromagnetic Research, Zhejiang University, Hangzhou 310058, ChinaNational Engineering Research Center for Optical Instruments, Centre for Optical and Electromagnetic Research, Zhejiang University, Hangzhou 310058, ChinaNational Engineering Research Center for Optical Instruments, Centre for Optical and Electromagnetic Research, Zhejiang University, Hangzhou 310058, ChinaResearch Institute of Zhejiang University-Taizhou, Taizhou 318000, ChinaNational Engineering Research Center for Optical Instruments, Centre for Optical and Electromagnetic Research, Zhejiang University, Hangzhou 310058, ChinaNational Engineering Research Center for Optical Instruments, Centre for Optical and Electromagnetic Research, Zhejiang University, Hangzhou 310058, ChinaNational Engineering Research Center for Optical Instruments, Centre for Optical and Electromagnetic Research, Zhejiang University, Hangzhou 310058, ChinaNational Engineering Research Center for Optical Instruments, Centre for Optical and Electromagnetic Research, Zhejiang University, Hangzhou 310058, ChinaDeepLab v3+ neural network shows excellent performance in semantic segmentation. In this paper, we proposed a segmentation framework based on DeepLab v3+ neural network and applied it to the problem of hyperspectral imagery classification (HSIC). The dimensionality reduction of the hyperspectral image is performed using principal component analysis (PCA). DeepLab v3+ is used to extract spatial features, and those are fused with spectral features. A support vector machine (SVM) classifier is used for fitting and classification. Experimental results show that the framework proposed in this paper outperforms most traditional machine learning algorithms and deep-learning algorithms in hyperspectral imagery classification tasks.https://www.mdpi.com/2076-3417/11/12/5703DeepLab v3+hyperspectral imagery classificationprincipal component analysisfeatures fusionsupport vector machine
spellingShingle Yifan Si
Dawei Gong
Yang Guo
Xinhua Zhu
Qiangsheng Huang
Julian Evans
Sailing He
Yaoran Sun
An Advanced Spectral–Spatial Classification Framework for Hyperspectral Imagery Based on DeepLab v3+
Applied Sciences
DeepLab v3+
hyperspectral imagery classification
principal component analysis
features fusion
support vector machine
title An Advanced Spectral–Spatial Classification Framework for Hyperspectral Imagery Based on DeepLab v3+
title_full An Advanced Spectral–Spatial Classification Framework for Hyperspectral Imagery Based on DeepLab v3+
title_fullStr An Advanced Spectral–Spatial Classification Framework for Hyperspectral Imagery Based on DeepLab v3+
title_full_unstemmed An Advanced Spectral–Spatial Classification Framework for Hyperspectral Imagery Based on DeepLab v3+
title_short An Advanced Spectral–Spatial Classification Framework for Hyperspectral Imagery Based on DeepLab v3+
title_sort advanced spectral spatial classification framework for hyperspectral imagery based on deeplab v3
topic DeepLab v3+
hyperspectral imagery classification
principal component analysis
features fusion
support vector machine
url https://www.mdpi.com/2076-3417/11/12/5703
work_keys_str_mv AT yifansi anadvancedspectralspatialclassificationframeworkforhyperspectralimagerybasedondeeplabv3
AT daweigong anadvancedspectralspatialclassificationframeworkforhyperspectralimagerybasedondeeplabv3
AT yangguo anadvancedspectralspatialclassificationframeworkforhyperspectralimagerybasedondeeplabv3
AT xinhuazhu anadvancedspectralspatialclassificationframeworkforhyperspectralimagerybasedondeeplabv3
AT qiangshenghuang anadvancedspectralspatialclassificationframeworkforhyperspectralimagerybasedondeeplabv3
AT julianevans anadvancedspectralspatialclassificationframeworkforhyperspectralimagerybasedondeeplabv3
AT sailinghe anadvancedspectralspatialclassificationframeworkforhyperspectralimagerybasedondeeplabv3
AT yaoransun anadvancedspectralspatialclassificationframeworkforhyperspectralimagerybasedondeeplabv3
AT yifansi advancedspectralspatialclassificationframeworkforhyperspectralimagerybasedondeeplabv3
AT daweigong advancedspectralspatialclassificationframeworkforhyperspectralimagerybasedondeeplabv3
AT yangguo advancedspectralspatialclassificationframeworkforhyperspectralimagerybasedondeeplabv3
AT xinhuazhu advancedspectralspatialclassificationframeworkforhyperspectralimagerybasedondeeplabv3
AT qiangshenghuang advancedspectralspatialclassificationframeworkforhyperspectralimagerybasedondeeplabv3
AT julianevans advancedspectralspatialclassificationframeworkforhyperspectralimagerybasedondeeplabv3
AT sailinghe advancedspectralspatialclassificationframeworkforhyperspectralimagerybasedondeeplabv3
AT yaoransun advancedspectralspatialclassificationframeworkforhyperspectralimagerybasedondeeplabv3