Study of Spatial–Spectral Feature Extraction Frameworks With 3-D Convolutional Neural Network for Robust Hyperspectral Imagery Classification
Advances in hyperspectral remote sensing have instigated multitude of applications for better understanding of our planet through remote data acquisition and observation of natural phenomena such as weather monitoring and prediction to include tornado, wild fires, global warming, etc. For this, data...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9305246/ |
id |
doaj-385e76d4fd0d49a280578a102e134e75 |
---|---|
record_format |
Article |
spelling |
doaj-385e76d4fd0d49a280578a102e134e752021-06-03T23:04:43ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352021-01-01141717172710.1109/JSTARS.2020.30464149305246Study of Spatial–Spectral Feature Extraction Frameworks With 3-D Convolutional Neural Network for Robust Hyperspectral Imagery ClassificationBishwas Praveen0https://orcid.org/0000-0002-9635-3892Vineetha Menon1https://orcid.org/0000-0001-6916-5346Department of Computer Science, University of Alabama in Huntsville, Huntsville, AL, USADepartment of Computer Science, University of Alabama in Huntsville, Huntsville, AL, USAAdvances in hyperspectral remote sensing have instigated multitude of applications for better understanding of our planet through remote data acquisition and observation of natural phenomena such as weather monitoring and prediction to include tornado, wild fires, global warming, etc. For this, data analysis methods that exploit the rich spectral and spatial information in hyperspectral data are often employed to gain insights about the natural phenomenon. This work presents a new deep learning based hyperspectral data analysis framework, which efficiently utilizes both spatial and spectral information present in the data to achieve superior classification performance. Gabor filtering is used for spatial feature extraction in conjunction with sparse random projections for spectral feature extraction and dimensionality reduction. Finally, supervised classification using a 3-D convolutional neural network was employed to perform a volumetric hyperspectral data analysis. Experimental results reveal that the proposed spatial-spectral hyperspectral data analysis frameworks outperform the conventional 2-D convolution neural network-based spectral-spatial feature extraction techniques.https://ieeexplore.ieee.org/document/9305246/3-D convolutional neural network (3-D CNN)deep learningdimensionality reduction (DR)feature extractionGabor filteringGaussian filtering |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Bishwas Praveen Vineetha Menon |
spellingShingle |
Bishwas Praveen Vineetha Menon Study of Spatial–Spectral Feature Extraction Frameworks With 3-D Convolutional Neural Network for Robust Hyperspectral Imagery Classification IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 3-D convolutional neural network (3-D CNN) deep learning dimensionality reduction (DR) feature extraction Gabor filtering Gaussian filtering |
author_facet |
Bishwas Praveen Vineetha Menon |
author_sort |
Bishwas Praveen |
title |
Study of Spatial–Spectral Feature Extraction Frameworks With 3-D Convolutional Neural Network for Robust Hyperspectral Imagery Classification |
title_short |
Study of Spatial–Spectral Feature Extraction Frameworks With 3-D Convolutional Neural Network for Robust Hyperspectral Imagery Classification |
title_full |
Study of Spatial–Spectral Feature Extraction Frameworks With 3-D Convolutional Neural Network for Robust Hyperspectral Imagery Classification |
title_fullStr |
Study of Spatial–Spectral Feature Extraction Frameworks With 3-D Convolutional Neural Network for Robust Hyperspectral Imagery Classification |
title_full_unstemmed |
Study of Spatial–Spectral Feature Extraction Frameworks With 3-D Convolutional Neural Network for Robust Hyperspectral Imagery Classification |
title_sort |
study of spatial–spectral feature extraction frameworks with 3-d convolutional neural network for robust hyperspectral imagery classification |
publisher |
IEEE |
series |
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
issn |
2151-1535 |
publishDate |
2021-01-01 |
description |
Advances in hyperspectral remote sensing have instigated multitude of applications for better understanding of our planet through remote data acquisition and observation of natural phenomena such as weather monitoring and prediction to include tornado, wild fires, global warming, etc. For this, data analysis methods that exploit the rich spectral and spatial information in hyperspectral data are often employed to gain insights about the natural phenomenon. This work presents a new deep learning based hyperspectral data analysis framework, which efficiently utilizes both spatial and spectral information present in the data to achieve superior classification performance. Gabor filtering is used for spatial feature extraction in conjunction with sparse random projections for spectral feature extraction and dimensionality reduction. Finally, supervised classification using a 3-D convolutional neural network was employed to perform a volumetric hyperspectral data analysis. Experimental results reveal that the proposed spatial-spectral hyperspectral data analysis frameworks outperform the conventional 2-D convolution neural network-based spectral-spatial feature extraction techniques. |
topic |
3-D convolutional neural network (3-D CNN) deep learning dimensionality reduction (DR) feature extraction Gabor filtering Gaussian filtering |
url |
https://ieeexplore.ieee.org/document/9305246/ |
work_keys_str_mv |
AT bishwaspraveen studyofspatialx2013spectralfeatureextractionframeworkswith3dconvolutionalneuralnetworkforrobusthyperspectralimageryclassification AT vineethamenon studyofspatialx2013spectralfeatureextractionframeworkswith3dconvolutionalneuralnetworkforrobusthyperspectralimageryclassification |
_version_ |
1721398655688114176 |