SPECTRAL-SPATIAL CLASSIFICATION OF HYPERSPECTRAL REMOTE SENSING IMAGES USING VARIATIONAL AUTOENCODER AND CONVOLUTION NEURAL NETWORK

In this paper, we propose a spectral-spatial feature extraction framework based on deep learning (DL) for hyperspectral image (HSI) classification. In this framework, the variational autoencoder (VAE) is used for extraction of spectral features from two widely used hyperspectral datasets- Kennedy Sp...

Full description

Bibliographic Details
Main Authors: A. Belwalkar, A. Nath, O. Dikshit
Format: Article
Language:English
Published: Copernicus Publications 2018-11-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-5/613/2018/isprs-archives-XLII-5-613-2018.pdf
id doaj-9fa40909cf78469fbcb26d7a6e690e76
record_format Article
spelling doaj-9fa40909cf78469fbcb26d7a6e690e762020-11-25T00:17:05ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342018-11-01XLII-561362010.5194/isprs-archives-XLII-5-613-2018SPECTRAL-SPATIAL CLASSIFICATION OF HYPERSPECTRAL REMOTE SENSING IMAGES USING VARIATIONAL AUTOENCODER AND CONVOLUTION NEURAL NETWORKA. Belwalkar0A. Nath1O. Dikshit2Dept. of Civil Engineering, Indian Institute of Technology Kanpur, IndiaDept. of Civil Engineering, Indian Institute of Technology Kanpur, IndiaDept. of Civil Engineering, Indian Institute of Technology Kanpur, IndiaIn this paper, we propose a spectral-spatial feature extraction framework based on deep learning (DL) for hyperspectral image (HSI) classification. In this framework, the variational autoencoder (VAE) is used for extraction of spectral features from two widely used hyperspectral datasets- Kennedy Space Centre, Florida and University of Pavia, Italy. Additionally, a convolutional neural network (CNN) is utilized to obtain spatial features. The spatial and spectral feature vectors are then stacked together to form a joint feature vector. Finally, the joint feature vector is trained using multinomial logistic regression (softmax regression) for prediction of class labels. The classification performance analysis is done through generation of the confusion matrix. The confusion matrix is then used to calculate Cohen’s Kappa (<i>&Kappa;</i>) to get a quantitative measure of classification performance. The results show that the K value is higher than 0.99 for both HSI datasets.https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-5/613/2018/isprs-archives-XLII-5-613-2018.pdf
collection DOAJ
language English
format Article
sources DOAJ
author A. Belwalkar
A. Nath
O. Dikshit
spellingShingle A. Belwalkar
A. Nath
O. Dikshit
SPECTRAL-SPATIAL CLASSIFICATION OF HYPERSPECTRAL REMOTE SENSING IMAGES USING VARIATIONAL AUTOENCODER AND CONVOLUTION NEURAL NETWORK
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
author_facet A. Belwalkar
A. Nath
O. Dikshit
author_sort A. Belwalkar
title SPECTRAL-SPATIAL CLASSIFICATION OF HYPERSPECTRAL REMOTE SENSING IMAGES USING VARIATIONAL AUTOENCODER AND CONVOLUTION NEURAL NETWORK
title_short SPECTRAL-SPATIAL CLASSIFICATION OF HYPERSPECTRAL REMOTE SENSING IMAGES USING VARIATIONAL AUTOENCODER AND CONVOLUTION NEURAL NETWORK
title_full SPECTRAL-SPATIAL CLASSIFICATION OF HYPERSPECTRAL REMOTE SENSING IMAGES USING VARIATIONAL AUTOENCODER AND CONVOLUTION NEURAL NETWORK
title_fullStr SPECTRAL-SPATIAL CLASSIFICATION OF HYPERSPECTRAL REMOTE SENSING IMAGES USING VARIATIONAL AUTOENCODER AND CONVOLUTION NEURAL NETWORK
title_full_unstemmed SPECTRAL-SPATIAL CLASSIFICATION OF HYPERSPECTRAL REMOTE SENSING IMAGES USING VARIATIONAL AUTOENCODER AND CONVOLUTION NEURAL NETWORK
title_sort spectral-spatial classification of hyperspectral remote sensing images using variational autoencoder and convolution neural network
publisher Copernicus Publications
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
issn 1682-1750
2194-9034
publishDate 2018-11-01
description In this paper, we propose a spectral-spatial feature extraction framework based on deep learning (DL) for hyperspectral image (HSI) classification. In this framework, the variational autoencoder (VAE) is used for extraction of spectral features from two widely used hyperspectral datasets- Kennedy Space Centre, Florida and University of Pavia, Italy. Additionally, a convolutional neural network (CNN) is utilized to obtain spatial features. The spatial and spectral feature vectors are then stacked together to form a joint feature vector. Finally, the joint feature vector is trained using multinomial logistic regression (softmax regression) for prediction of class labels. The classification performance analysis is done through generation of the confusion matrix. The confusion matrix is then used to calculate Cohen’s Kappa (<i>&Kappa;</i>) to get a quantitative measure of classification performance. The results show that the K value is higher than 0.99 for both HSI datasets.
url https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLII-5/613/2018/isprs-archives-XLII-5-613-2018.pdf
work_keys_str_mv AT abelwalkar spectralspatialclassificationofhyperspectralremotesensingimagesusingvariationalautoencoderandconvolutionneuralnetwork
AT anath spectralspatialclassificationofhyperspectralremotesensingimagesusingvariationalautoencoderandconvolutionneuralnetwork
AT odikshit spectralspatialclassificationofhyperspectralremotesensingimagesusingvariationalautoencoderandconvolutionneuralnetwork
_version_ 1725381132290097152