首页 | 本学科首页   官方微博 | 高级检索  
     

基于分段主成分分析的高光谱图像波段选择算法研究
引用本文:杨诸胜,郭雷,罗欣,胡新韬. 基于分段主成分分析的高光谱图像波段选择算法研究[J]. 测绘工程, 2006, 15(3): 15-18
作者姓名:杨诸胜  郭雷  罗欣  胡新韬
作者单位:西北工业大学,自动化学院,陕西,西安,710072
基金项目:国家高技术研究发展计划(863计划) , 西北工业大学校科研和教改项目
摘    要:提出了一种基于分段主成分分析的高光谱图像波段选择算法。该算法把每个波段被映射到主成分的信息量的大小作为是否被选择的指标,可以保证选择的波段信息丰富;通过分段分析,可以更全面的选择波段;指标的计算只需要得到原始数据的协方差阵,而不必对原始数据进行真正的主成分变换,降低了计算量。

关 键 词:分段主成分分析  波段选择  高光谱图像  贝叶斯分类
文章编号:1006-7949(2006)03-0015-04
收稿时间:2006-01-04
修稿时间:2006-01-04

Research on segmented PCA based on band selection algorithm of hyperspectral image
YANG Zhu-sheng,GUO Lei,LUO Xin,HU Xin-tao. Research on segmented PCA based on band selection algorithm of hyperspectral image[J]. Engineering of Surveying and Mapping, 2006, 15(3): 15-18
Authors:YANG Zhu-sheng  GUO Lei  LUO Xin  HU Xin-tao
Abstract:A segmented PCA based band selection algorithm of hyperspectral image is proposed.This algorithm regards the amount of the information that is mapped into the principal components of a given band as the crite- rion which can be selected.Therefore,it can ensure that the selected bands contain most information of the origi- nal data,and with the segmentation on original data comprehensive bands can be selected.In order to get the cri- terion,only the covariance metrics are needed.So,it does not need to carry principal component transformation on the original data,which save much computation time.The results of the Bayesian classification and K-means classification indicate the validity and feasibility of the algorithm.
Keywords:segmented principal component analysis  band selection  hyperspectral image  Bayesian classification
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号