基于神经网络的Hyperion高光谱遥感影像混合像元分解
首发时间:2011-02-28
摘要:本文针对目前应用比较广泛的两种神经网络模型BP网络、RBF网络来进行Hyperion高光谱遥感影像的混合像元分解。在对数据进行预处理的基础上,基于Matlab平台建立这两种神经网络算法的模型,并应用均方根误差模型来评价这两种模型的性能。实验结果表明:针对本文实验数据,RBF神经网络模型较BP神经网络模型具有误差小、训练速度快等优点,BP神经网络则更加能突出细节信息。
关键词: 高光谱遥感 Hyperion BP神经网络 RBF神经网络 混合像元分解
For information in English, please click here
Study on Decomposing mixed Element in Hyperion Remote Sensing Image based on Neural Network
Abstract:Back propagation neural network and radial basis function are now used widely,in this paper the two model are realized to decompose mixed element in hyperion remote sensing .Taking the preprocessed EO-1 Hyperion image as the experimental data, special mixture analysis is achieved by BP Network and RBF Network based on Matlab platform, and apply the RMSE model to evaluate the two models. The results indicates that in this experiment ,the RBF network model can get the better result in error and training speed etc, but BP netwok can get more details.
Keywords: Hyperspectral Remote Sensing Hyperion BP neural network RBF neural network pixel unmixing
论文图表:
引用
No.4411443468633129****
同行评议
共计0人参与
勘误表
基于神经网络的Hyperion高光谱遥感影像混合像元分解
评论
全部评论0/1000