基于AMLE的高光谱本征维数估计方法研究  

Research of Estimating the Intrinsic Dimension of Hyperspectral Imagery Based on AMLE

作　　者：杨明[1] 余旭初[1] 张鹏强[1] 吴翰书[2] 

机构地区：[1]信息工程大学测绘学院 [2]96215部队

出　　处：《影像技术》2012年第3期39-42,共4页Image Technology

基　　金：信息工程大学测绘学院学位创新创优基金的支持

摘　　要：最大似然估计法(MLE)能快速计算高光谱影像数据的本征维数,原理简单,但它不是一种很好的本征维数估计法。因为它存在忽略单个数据点贡献的缺点,导致冗余信息放大、重要信息被湮没,不利于特征提取和分类。对此,本文引入自适应性最大似然估计法(AMLE)。该方法通过引入权函数,突出每个数据点的贡献,能提取出被最大似然估计法湮没的重要特征。在对高光谱影像进行特征提取及分类的试验中验证了该方法的有效性。Maximum likehood estimator（MLE） can estimate the intrinsic dimension of hyperspectral imagery quickly, the theroy is easy, but it isn＇t a good meathod on intrinsic dimension. Beause that it ignores the contribution of each point. This leads to important information is in silence. In the paper , adjust maximum likehood estimator is proposed to solve the problems. AMLE adjusts the contribution of each point to the estimator by making use of a weight function. This method can extract the feature which is ignored by Maximum likehood estimator. To verify the effectiveness of the proposed method,the experiment is conducted on Hyperspectral imagery feature extracion an classification, the experiment result shows the effectiveness of the proposed method.

关 键 词：最大似然估计 自适应性最大似然估计 权函数 

分 类 号：P237[天文地球—摄影测量与遥感]