Graph-Based Deep Convolutional Networks for Hyperspectral Image Classification

Classification has been among the central issues of hyperspectral application. However, due to the well-known Hughes phenomenon, most of the methods suffer from the curse of dimensionality and deeply rely on traditional dimensional reduction like Principle Component Analysis (PCA). In this paper, combining spatial and spectral information jointly, we propose a novel deep classification framework. It consists of two parts: graph-based spatial fusion and Convolutional Neural Network (CNN). Spatial fusion acts as a pre-training stage that extracts spatial-spectral features from high-order data. CNN learns and infers spectrum efficiently from fused input via deep hierarchy with convolutional and pooling layers, thus forming a relationship between spectral-spatial features and class distribution. Experiment results show that the performance of the proposed classifier is competitive enough with other pixel-wise classifiers.