Application of Convolutional Neural Networks in High Score Remote Sensing Image Classification

Abstract

Remote sensing image classification is a critical link in remote sensing. Traditional remote sensing image classification is based on shallow structure model algorithms such as SVM and decision tree. However, when faced with high-resolution remote sensing images, due to a large amount of data and complex data features, the recognition accuracy of traditional shallow models has been unable to meet the current needs. When faced with image classification, convolutional neural networks can better cope with image translation, scaling, and other deformations and effectively reduce the errors introduced by the above factors. At the same time, the convolutional neural network can capture and extract complex signal features with the help of a deeper feature processing level to obtain a better classification effect. This paper discusses the application of convolutional neural networks to classify high-resolution remote sensing images and provides some references for remote sensing image processing and target recognition.