Multi-Scale Convolutional Neural Networks Aggregation For Hyperspectral Images Classification

Hyperspectral image feature extraction and classification is an important part in remote sensing field, and convolutional neural networks (CNNs) show their advantages in it. However, it is still affected by the lack of training samples, which may lead to the occurrence of overfitting. This issue gets more serious when dealing with high-dimensional data such as HSI. And the single scale of the input data ignores the abundance of multi-scale spatial information. In response to the above problems, we propose a multi-scale convolutional neural network method. And the method can extract multiple scale areas centered on the pixel to be classified. Then it adjusts the areas to the same size and inputs the adjusted data into the standard convolutional neural network for training and testing. Experimental results indicate that proposed method boost the performances in terms of classification accuracies.