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 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 ( Κ) to get a quantitative measure of classification performance. The results show that the K value is higher than 0.99 for both HSI datasets.