Prof. Fuding Xie, Liaoning Normal University

In this talk, we will introduce some hyperspectral image classification methods based on deep learning architecture. Recently, deep learning-based hyperspectral image classification has attracted more and more attention due to its excellent classification performance. Firstly, the development history of deep learning is briefly introduced. Then two typical deep learning architectures, convolutional neural network and graph convolutional network, are depicted. Finally, two hyperspectral image classification methods based on deep learning are proposed. A large number of experimental and comparative results demonstrate the effectiveness of the proposed method.