Research on Application of Convolutional Neural Network in Remote Sensing Image Recognition
Download as PDF
DOI: 10.23977/mcee2020.017
Author(s)
Chenlong Bao, Ying Chen
Corresponding Author
Chenlong Bao
ABSTRACT
With the advancement of science and technology in recent years, the amount of remote sensing image data has become more and more abundant and has important research value. As a current research hotspot, remote sensing image recognition has attracted more and more people to study it. Based on this, the application of convolutional neural network in remote sensing image recognition is studied in this article. First, the basic principles of convolutional neural network are introduced, including image preprocessing, image local connection, zero-padded, multi-convolution kernel application, pooling processing and pre-processing. It then analyzes the current research status of remote sensing image recognition, briefly analyzes the problems of deep learning in remote sensing image processing, and predicts its future applications. Finally, it elaborates the application of convolutional neural network in remote sensing image recognition. Only by intensifying research can we better utilize the application value of convolutional neural networks in remote sensing image recognition, and then promote the development of remote sensing image processing technology.
KEYWORDS
Remote sensing image, convolutional neural network, recognition, application