基于卷积神经网络的遥感图像分类算法  

Remote Sensing Image Classification Algorithm based On Convolutional Neural Network

作　　者：黄玉芬 HUANG Yu-fen(School of Sugon Big Data,Liaoning Institute of Science and Technology,Benxi Liaoning 117004,China)

机构地区：[1]辽宁科技学院曙光大数据学院,辽宁本溪117004

出　　处：《辽宁科技学院学报》2022年第3期15-16,44,共3页Journal of Liaoning Institute of Science and Technology

基　　金：2020年度辽宁省社会科学规划基金项目“基于大数据技术建立健全地方门户网站舆情监控及预警机制的研究”(L20BXW002).

摘　　要：随着信息技术、遥感技术的快速发展,人们获得的遥感数据急速增长,如何对遥感图像进行分类成为亟待解决的问题。文章采用深度学习技术搭建卷积神经网络,通过在卷积层后增加池化层对卷积层生成的特征下进行采样;采用最大池化实现对特征进一步地提取和压缩;基于全连接层将特征加权求和进行特征汇总,输出层采用Softmax逻辑回归分类器得到输入图像最大的概率值对应的标签,从而实现遥感图像分类。With the fast development of information technology and remote sensing technology,the remote sensing data acquired by people increases rapidly,how to obtain remote sensing image classification has thus become an urgent problem to be solved.In this paper,a convolution neural network is built based on deep learning technology,and the features generated by the convolution layer are subsampled by adding a pooling layer after the convolution layer.The feature is further extracted and compressed on the basis of max pooling.Based on the fully connected layers,the features are weighted and summed up,and the output layer uses Softmax logical regression classifier to obtain the label corresponding to the maximum probability value of the input image.Rremote sensing image classification can therefore be realized.

关 键 词：遥感图像 图像分类 深度学习 卷积神经网络 逻辑回归 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP751[自动化与计算机技术—控制科学与工程]