文档介绍：第卷第期中南林业科技大学学报
31 11
年月
2011 11 Journal of Central South University of Forestry & Technology
高光谱数据的降维处理方法研究
柳萍萍林辉孙华严恩萍
, , ,
(中南林业科技大学林业遥感信息工程研究中心,湖南长沙 410004)
摘要高光谱数据具有波段多光谱范围窄数据量大等特点但巨大的数据量给数据处理带来了困难同时
: 、、, ,
它的高维也容易导致现象的产生因此对其进行降维处理显得非常必要以数据为研究对
Hughes 。, 。 Hyperion
象,分别利用特征选择和特征提取的方法达到数据降维的目的。结果表明:(1)波段选择之前进行子空间划分,可
剔除相关性大的波段,并能减小数据计算量,避免信息的丢失,从而实现高维遥感数据优化处理和高效利用的目
的。(2)MNF变换后高光谱数据的有效端元数可为图像的进一步分析和应用提供参考。
关键词高光谱数据降维特征提取
: ; ; ;Hyperion
中图分类号文献标志码文章编号
: : A : 1673-923X(2011)11-0034-05
Dimensionality reduction method of Hyperion EO-1 data
LIU Ping-ping,LIN Hui,SUN Hua,YAN En-ping
(Research Center of Forestry Remote Sensing Information&Engineering,
Central South University of Forestry& Technology,Changsha 410004,Hunan,China)
Abstract:Hyperspectral data have more bands,narrow spectral range,large volumes of data,etc.,but a huge a-
mount of data make data processing very difficult,while its high-dimensional phenomenon can easily lead to the
generation of ,dimensionality reduction process is very taking Hyperion data as
the research object,using feature selection and feature extraction methods,the purpose of data reduction was a-
results show that dividing space before sub-band selection can eliminate the band with bigger correla-
tion,and can reduce the