| 基于BP神经网络的遥感影像分类方法 |
| |
| 引用本文： | 王崇倡,武文波,张建平.基于BP神经网络的遥感影像分类方法[J].辽宁工程技术大学学报(自然科学版),2009,28(1). |
| |
| 作者姓名： | 王崇倡 武文波 张建平 |
| |
| 作者单位： | 辽宁工程技术大学测绘与地理科学学院,辽宁,阜新,123000 |
| |
| 基金项目： | 辽宁省教育厅重点实验室基金，辽宁省教育厅创新团队基金，辽宁省科学技术厅基金 |
| |
| 摘 要： | 为了消除传统的遥感影像分类所带来的模糊性和不确定性,采用BP神经网络进行遥感影像分类.利用MatLab软件构建BP网络遥感影像分类算法,通过对BP网络算法进行改进,采用动量-自适应学习速率调整算法克服了网络训练速度慢、不易收敛到全局最优等缺点.对一幅全色遥感图像通过300次训练后,输出能真实反映地类的影像图.其分类总精度为86.67%,Kappa系数为0.82,分类精度能够满足遥感图像分类的需要.
|
| 关 键 词： | BP神经元刚络 遥感 分类 精度 |
Classification for remote sensing image based on bp neural network |
| |
| WANG Chongchang,WU Wenbo,ZHANG Jianping.Classification for remote sensing image based on bp neural network[J].Journal of Liaoning Technical University (Natural Science Edition),2009,28(1). |
| |
| Authors: | WANG Chongchang WU Wenbo ZHANG Jianping |
| |
| Institution: | School of Geomatics;Liaoning Technical University;Fuxin 123000;China |
| |
| Abstract: | In order to eliminate the ambiguity and uncertainty exising in the conventional classification for remote sesing images,the BP neural network is presened.However,the BP network itself also has some limitations and shortages,which are primarily represented in the aspects of low network training speed,difficult optimization for convergence to integer and so on.This paper improves the BP neural network based on MatLab sofeware by using momentum and adaptive learning rate.After 300 times of training for a sheet... |
| |
| Keywords: | BP neural network remote sensing classification precision |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
