Classification of Optical Remote Sensing Images Based on Convolutional Neural Network

Abstract

Based on deep convolutional neural network, an optical remote sensing image classification method is proposed in this paper. Aiming at the particularity of remote sensing image and natural object classification, combined with the theory of deep learning convolutional neural network, a five-layer convolutional neural network was designed, which applied to classify the optical remote sensing image into two category. Testing and parameter optimization on the UC Merced Land Use data set. The convolutional neural network designed in this paper is trained and tested on the same test set. The result shows it has better effect of classifying on the current data set reach 98.15%. The experimental results indicate this network designed can apply to the scene of two-category image classification and improve the classification accuracy of aerial image.