基于RBF神经网络的高光谱遥感影像降维及分类

高光谱遥感影像数据量大,针对该特点,为尽可能保留数据中有价值的信息,首先采用线性判别分析(Linear Discriminant Analysis,LDA)方法对高光谱遥感影像数据进行降维,接着应用径向基函数(Radial Basis Function,RBF)神经网络方法对其进行分类处理。实验结果表明,分类精度可达到70%以上,具有良好的分类效果,证明了该方法的可行性。

Dimensionality Reduction and Classification for Hyperspectral Remote Sensing Imagery Based on Radial Basis Function Neural Network

In view of the large amount of hyperspectral remote sensing image data, it is possible to retain the value of the infor-mation, Firstly, Linear Discriminant Analysis (LDA) method is used to reduce the high spectral remote sensing image data. Then, Radial Basis Function (RBF) neural network method is used to classify the data. Experimental results show that the classification accuracy can reach more than 70% with good classification results, and it proved the feasibility of the method.