Cargando…

Hierarchical Spatial-Spectral Feature Extraction with Long Short Term Memory (LSTM) for Mineral Identification Using Hyperspectral Imagery

Deep learning models are widely employed in hyperspectral image processing to integrate both spatial features and spectral features, but the correlations between them are rarely taken into consideration. However, in hyperspectral mineral identification, not only the spectral and spatial features of...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhao, Huijie, Deng, Kewang, Li, Na, Wang, Ziwei, Wei, Wei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7730013/
https://www.ncbi.nlm.nih.gov/pubmed/33266267
http://dx.doi.org/10.3390/s20236854
_version_ 1783621588475707392
author Zhao, Huijie
Deng, Kewang
Li, Na
Wang, Ziwei
Wei, Wei
author_facet Zhao, Huijie
Deng, Kewang
Li, Na
Wang, Ziwei
Wei, Wei
author_sort Zhao, Huijie
collection PubMed
description Deep learning models are widely employed in hyperspectral image processing to integrate both spatial features and spectral features, but the correlations between them are rarely taken into consideration. However, in hyperspectral mineral identification, not only the spectral and spatial features of minerals need to be considered, but also the correlations between them are crucial to further promote identification accuracy. In this paper, we propose hierarchical spatial-spectral feature extraction with long short term memory (HSS-LSTM) to explore correlations between spatial features and spectral features and obtain hierarchical intrinsic features for mineral identification. In the proposed model, the fusion spatial-spectral feature is primarily extracted by stacking local spatial features obtained by a convolution neural network (CNN)-based model and spectral information together. To better exploit spatial features and spectral features, an LSTM-based model is proposed to capture correlations and obtain hierarchical features for accurate mineral identification. Specifically, the proposed model shares a uniform objective function, so that all the parameters in the network can be optimized in the meantime. Experimental results on the hyperspectral data collected by the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) in the Nevada mining area show that HSS-LSTM achieves an overall accuracy of 94.70% and outperforms other commonly used identification methods.
format Online
Article
Text
id pubmed-7730013
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-77300132020-12-12 Hierarchical Spatial-Spectral Feature Extraction with Long Short Term Memory (LSTM) for Mineral Identification Using Hyperspectral Imagery Zhao, Huijie Deng, Kewang Li, Na Wang, Ziwei Wei, Wei Sensors (Basel) Article Deep learning models are widely employed in hyperspectral image processing to integrate both spatial features and spectral features, but the correlations between them are rarely taken into consideration. However, in hyperspectral mineral identification, not only the spectral and spatial features of minerals need to be considered, but also the correlations between them are crucial to further promote identification accuracy. In this paper, we propose hierarchical spatial-spectral feature extraction with long short term memory (HSS-LSTM) to explore correlations between spatial features and spectral features and obtain hierarchical intrinsic features for mineral identification. In the proposed model, the fusion spatial-spectral feature is primarily extracted by stacking local spatial features obtained by a convolution neural network (CNN)-based model and spectral information together. To better exploit spatial features and spectral features, an LSTM-based model is proposed to capture correlations and obtain hierarchical features for accurate mineral identification. Specifically, the proposed model shares a uniform objective function, so that all the parameters in the network can be optimized in the meantime. Experimental results on the hyperspectral data collected by the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) in the Nevada mining area show that HSS-LSTM achieves an overall accuracy of 94.70% and outperforms other commonly used identification methods. MDPI 2020-11-30 /pmc/articles/PMC7730013/ /pubmed/33266267 http://dx.doi.org/10.3390/s20236854 Text en © 2020 by the authors. 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 (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Zhao, Huijie
Deng, Kewang
Li, Na
Wang, Ziwei
Wei, Wei
Hierarchical Spatial-Spectral Feature Extraction with Long Short Term Memory (LSTM) for Mineral Identification Using Hyperspectral Imagery
title Hierarchical Spatial-Spectral Feature Extraction with Long Short Term Memory (LSTM) for Mineral Identification Using Hyperspectral Imagery
title_full Hierarchical Spatial-Spectral Feature Extraction with Long Short Term Memory (LSTM) for Mineral Identification Using Hyperspectral Imagery
title_fullStr Hierarchical Spatial-Spectral Feature Extraction with Long Short Term Memory (LSTM) for Mineral Identification Using Hyperspectral Imagery
title_full_unstemmed Hierarchical Spatial-Spectral Feature Extraction with Long Short Term Memory (LSTM) for Mineral Identification Using Hyperspectral Imagery
title_short Hierarchical Spatial-Spectral Feature Extraction with Long Short Term Memory (LSTM) for Mineral Identification Using Hyperspectral Imagery
title_sort hierarchical spatial-spectral feature extraction with long short term memory (lstm) for mineral identification using hyperspectral imagery
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7730013/
https://www.ncbi.nlm.nih.gov/pubmed/33266267
http://dx.doi.org/10.3390/s20236854
work_keys_str_mv AT zhaohuijie hierarchicalspatialspectralfeatureextractionwithlongshorttermmemorylstmformineralidentificationusinghyperspectralimagery
AT dengkewang hierarchicalspatialspectralfeatureextractionwithlongshorttermmemorylstmformineralidentificationusinghyperspectralimagery
AT lina hierarchicalspatialspectralfeatureextractionwithlongshorttermmemorylstmformineralidentificationusinghyperspectralimagery
AT wangziwei hierarchicalspatialspectralfeatureextractionwithlongshorttermmemorylstmformineralidentificationusinghyperspectralimagery
AT weiwei hierarchicalspatialspectralfeatureextractionwithlongshorttermmemorylstmformineralidentificationusinghyperspectralimagery