投影寻踪方法与高光谱遥感图像数据特征提取的研究

The Application of Projection Pursuit in Hyperspectral Image Analysis

高光谱技术的发展与应用对高维的高光谱遥感数据的处理方法提出了更高的要求 .投影寻踪方法是一种处理高维数据的十分有效的降维方法 .高光谱图像分析对投影寻踪方法仍是一个全新的领域 .本文介绍了投影寻踪的一般概念 ,分析了基于信息散度指标投影的寻踪方法在高光谱图像处理中的应用 ,给出了它与主成份分析处理结果的对比 ,并提出

The development of hyperspectral remote sensing technology brings forward higher request on approaches for hyperspectral data analysis.Projectin Pursuit(PP) is a powerful tol for analyzing hige dimensional data and has achieved great success in many areas.However it is still a nwe method for hyperspectral image analysis.In this paper we introduce the conception of PP,study thd information deiivergence index,give an practical comparison between PP and PCA in hyperspectral image analysis,and propose some advices on the research of combination of PP and hyperspectral data analysis.