Category imbalance hyperspectral image classification method based on enhanced oversampling

The invention discloses a category imbalance hyperspectral image classification method based on enhanced oversampling. The category imbalance hyperspectral image classification method comprises the steps of obtaining a to-be-classified hyperspectral image and a to-be-trained hyperspectral image set; carrying out dimension reduction processing by using a principal part analysis method, and edge filling and blocking are carried out on each hyperspectral image after dimension reduction; performing enhanced oversampling imbalance processing on the training sample set; and building a convolutional neural network model, training the convolutional neural network, and performing category prediction on the to-be-classified pixel blocks. According to the method, the problem of low classification accuracy caused by small samples and unbalanced categories in hyperspectral image classification is solved, and the classification accuracy is improved. 本发明公开了一种基于增强过采样的类别不平衡高光谱图像分类方法，包括步骤：获取待分类高光谱图像和待训练高光谱图像集；采用主成分分析法进行降维处理，再对