Hyperspectral image classification using 3D-2D CNN with multi-scale information extraction and fusion module

Classification is the focus and difficulty of hyperspectral imaging technology. Hyperspectral data have twodimensional spatial information and one-dimensional spectral information, which are presented as three-dimensional data blocks with large amount of information, meanwhile high-dimension, high nonlinearity and limited training samples bring great challenges. Deep learning can extract and analyze the features of target data step by step by building multi-layer deep nonlinear structure. The advanced feature, multi scale abstract information extracted by convolution neural network applied to image processing can improve the classification accuracy of complex hyperspectral data. We regard pixel level hyperspectral classification as semantic segmentation network, and creatively introduce squeeze-And-excitation network and pyramid pooling network into hyperspectral classification network and proposed a model based on the structure of 2D-3D hybrid convolution neural network, it can learn deeper spatial spectral features and fusion to improve the accuracy and speed of hyperspectral classification.