Feature Extraction and Classification of Hyperspectral Image Based on 3D- Convolution Neural Network

Abstract

Deep learning has huge potential for hyperspectral image (HSI) classification. In order to fully exploit the information in HSI and improve the classification accuracy, a new classification method based on 3D-convolutional neural network (3D-CNN) is proposed. In the meantime, virtual samples are introduced to solve the problem of insufficient samples of HSI. The experimental results show that the proposed method has a good application prospect in HSI classification.