张爱武, 杜楠, 康孝岩, 郭超凡. 非线性变换和信息相邻相关的高光谱自适应波段选择[J]. 红外与激光工程, 2017, 46(5): 538001-0538001(9). DOI: 10.3788/IRLA201746.0538001
引用本文: 张爱武, 杜楠, 康孝岩, 郭超凡. 非线性变换和信息相邻相关的高光谱自适应波段选择[J]. 红外与激光工程, 2017, 46(5): 538001-0538001(9). DOI: 10.3788/IRLA201746.0538001
Zhang Aiwu, Du Nan, Kang Xiaoyan, Guo Chaofan. Hyperspectral adaptive band selection method through nonlinear transform and information adjacency correlation[J]. Infrared and Laser Engineering, 2017, 46(5): 538001-0538001(9). DOI: 10.3788/IRLA201746.0538001
Citation: Zhang Aiwu, Du Nan, Kang Xiaoyan, Guo Chaofan. Hyperspectral adaptive band selection method through nonlinear transform and information adjacency correlation[J]. Infrared and Laser Engineering, 2017, 46(5): 538001-0538001(9). DOI: 10.3788/IRLA201746.0538001

非线性变换和信息相邻相关的高光谱自适应波段选择

Hyperspectral adaptive band selection method through nonlinear transform and information adjacency correlation

  • 摘要: 通过非线性函数变换改进后的谱间Pearson相关分析可同时获取高光谱影像光谱间的综合相关系数(rcl)、相关类型和统计显著性水平;研究发现,非线性是高光谱影像的谱间相关性的主要类型。基于相关系数的波段相邻相关系数(rac)在自适应波段选择算法(ABS)中是为了表达波段的独立性,然而发现ABS算法中rac并不能有效表达波段独立性。鉴于此,提出了一种信息相邻相关系数(riac)和基于此指数改进的自适应波段选择算法(MABS)。使用公共数据和实验室采集数据,对ABS、基于线性相关系数(rl)的MABS(rl)和基于rcl的MABS(rcl)等三种算法进行实验。结果表明:在波谱范围和算法有效性及精度方面,MABS均优于ABS;MABS较好地兼顾了大信息量和强独立性原则,其波段选择结果的光谱范围明显大于ABS;MABS(rcl)的光谱范围略大于MABS(rl);三种算法的总体分类精度(OA)和Kappa系数的大小顺序均为:MABS(rcl) MABS(rl) ABS。

     

    Abstract: Through nonlinear functional transform of hyperspectral remote sensing data, the modified Pearson correlation analysis can effectively identify comprehensive correlation coefficient (rcl), correlation type, and statistical significance level between spectrums. In this paper, nonlinear correlation the main correlation relationship type between hyperspectral bands was proved. Based on correlation coefficient, the adjacent bands' correlation coefficient (rac) of adaptive band selection (ABS) is to express band independence, but rac of ABS algorithm cannot effectively express such independence. Herein, a kind of information adjacency/equivalent bands' correlation coefficient (riac), and via this index, the modified ABS (MABS) were proposed. Using public data and collected private data, the experiments of ABS, MABS(rl) based on linear correlation coefficient(rl), and MABS(rcl) based on rcl were carried out. These two case studies demonstrate that MABS is superior to ABS on spectral range, algorithm validity and accuracy. MABS can take both large amount of information and strong independence into consideration effectively. The spectral range of MABS's bands selection result is more than ABS's obviously, and MABS (rcl)'s is a little more than MABS (rl)'s. The ranking both overall classification accuracy and Kappa coefficient of those three kinds of algorithms are MABS(rcl)MABS(rl)ABS.

     

/

返回文章
返回