| 基于径向基函数神经网络的混合像元分解 |
| |
| 引用本文： | 张彦,邵美珍.基于径向基函数神经网络的混合像元分解[J].遥感学报,2002,6(4):285-288. |
| |
| 作者姓名： | 张彦 邵美珍 |
| |
| 作者单位： | 1. 北京大学,数学学院,视觉与听觉信息处理国家重点实验室,北京,100871
2. 信息工程大学信息科学系,郑州,450002 |
| |
| 摘 要： | 遥感图像中普通存在着混合像元。对这部分像元进行分类（即混合像元分解）是遥感图像处理中的难点。基于主分量分析的混合像元分解 法是一种较为成熟的算法，但它存在着计算量大，适应性差等缺点。在深入研究混合像元分解原理的基础上，提出了用径向基函数神经网络拟合分解结果超平面，以实现混合像元分解的算法，实验结果证明：该算法的结果与基于主分量分析的混合像元分解算法结果相近（相关系数达到0．00），而计算量大大减少，具有较强的适应性。
|
| 关 键 词： | 混合像元 主分量分析 径向基函数神经网络 曲面拟合 遥感图像 |
| 文章编号： | 1007-4619(2002)04-0285-04 |
| 收稿时间： | 7/3/2001 12:00:00 AM |
| 修稿时间： | 2001/11/29 0:00:00 |
Mixed Image Cell Decomposition Based on Radial-basis Function Neural Networks |
| |
| ZHANG Yan and SHAO Mei-zhen.Mixed Image Cell Decomposition Based on Radial-basis Function Neural Networks[J].Journal of Remote Sensing,2002,6(4):285-288. |
| |
| Authors: | ZHANG Yan and SHAO Mei-zhen |
| |
| Institution: | School of Mathematical Science of the Peking University,National Laboratory on Machine Perception,Beijing 100871,China;Department of Information Science,Unirersity of Information Engineering,Zhengzhou 450002,China |
| |
| Abstract: | Remote sensing images contain a lot of mixed image cells, and it is difficult to classify these cells. Mixed image cells decomposition algorithm based on principle component analysis is a widely used algorithm, but the large computation amount and less flexibility are its main drawbacks. By researching the curve fitting (approximation)theory of the radial basis function neural networks, and the principles of the mixed image cells decomposition algorithm based on principle component analysis, the paper proposes a new decomposition algorithm, which uses the radial basis function neural networks to fit (approximate) the hyperplane of the decomposition results of the principle component analysis algorithm. Experimental results prove that the results of the new algorithm are almost the same with the results of the principle component analysis algorithm (correlation coefficients are above 0.99). However, the new algorithm has much less computation complexity and more flexibility than the principle component analysis algorithm. |
| |
| Keywords: | mixed image cells principle component analysis radial basis function neural networks (RBFN) curve fitting (approximation) |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《遥感学报》浏览原始摘要信息 |
| 点击此处可从《遥感学报》下载免费的PDF全文 |
