基于类别可分性的高光谱图像波段选择

计算机科学 ›› 2015, Vol. 42 ›› Issue (4): 274-275.doi: 10.11896/j.issn.1002-137X.2015.04.056

基于类别可分性的高光谱图像波段选择

许明明,张良培,杜博,张乐飞

武汉大学测绘遥感信息工程国家重点实验室武汉430079;武汉大学计算机学院武汉430079,武汉大学测绘遥感信息工程国家重点实验室武汉430079,武汉大学计算机学院武汉430079,武汉大学计算机学院武汉430079

出版日期:2018-11-14 发布日期:2018-11-14
基金资助:
本文受国家“973计划”项目(2012CB719905),国家自然科学基金资助

Supervised Band Selection Based on Class Separability for Hyperspectral Image

XU Ming-ming, ZHANG Liang-pei, DU Bo and ZHANG Le-fei

Online:2018-11-14 Published:2018-11-14

摘要/Abstract

摘要： 高光谱遥感数据具有丰富的光谱信息,应用十分广泛,但其冗余的光谱信息有时会限制高光谱图像的分类等的精度以及计算复杂度。为了提高解译效率,高光谱图像降维不可或缺,这也是高光谱图像处理的研究热点之一。提出了一种基于类别可分性的高光谱图像波段选择方法(Endmember Separability Based band Selection,ESBB),该方法通过Mahalanobis 距离最大化图像中各类地物的可分性来确定最优的波段组合。相较于其他监督波段选择算法,该方法不需要大量训练样本,不用对每个组合做分类处理。对波段选择后的结果进行分类的实验结果证明,该方法是一个快速有效的波段选择方法,可以得到一个较好的分类精度。

关键词: 监督波段选择,高光谱图像,类别可分

Abstract: Hyperspectral remote sensing data contain abundant spectral information,which are widely used,but sometimes the redundant spectral information limits the classification accuracy and computational complexity.In order to improve the interpretation efficiency,hyperspectral image dimension reduction is necessary,which is also one of the highlights in the hyperspectral image processing.This paper presented a hyperspectral image band selection method based on endmember separability (EBSS).This method maximizes class separability using Mahalanobis distance to determine the optimal band combination.Compared with other supervision of band selection algorithms,the proposed method does not need the training samples,and does not conduct classification during band selection.The experiment results show that the proposed method is effective and can get better classification accuracy.

Key words: Supervised band selection,Hyperspectral image,Class separability

许明明,张良培,杜博,张乐飞. 基于类别可分性的高光谱图像波段选择[J]. 计算机科学, 2015, 42(4): 274-275. https://doi.org/10.11896/j.issn.1002-137X.2015.04.056

XU Ming-ming, ZHANG Liang-pei, DU Bo and ZHANG Le-fei. Supervised Band Selection Based on Class Separability for Hyperspectral Image[J]. Computer Science, 2015, 42(4): 274-275. https://doi.org/10.11896/j.issn.1002-137X.2015.04.056

参考文献

[1] 杜博,张良培,李平湘,等.一种基于随机场模型的高光谱影像目标探测算法 [J].计算机科学,2010,37(6):289-292
[2] 李洪利,沈焕锋,杜博,等.一种高保真同态滤波遥感影像薄云去除方法 [J].遥感信息,2011(1):41-44
[3] Ifarraguerri A.Visual method for spectral band selection[J].IEEE Geoscience and Remote Sensing Letters,2004,1(2):101-106
[4] Huang Rui,He Ming-yi.Band selection based on feature weighting for classification of hyperspectral imagery [J].IEEE Geoscience and Remote Sensing Letters,2005,2(2):156-159
[5] Backer S D,Kempeneers P,Debruyn W,et al.A band selection technique for spectral classification [J].IEEE Geoscience and Remote Sensing Letters,2005,2(3):319-323
[6] 吴昊,李士进,林林,等.多策略结合的高光谱图像波段选择新方法[J].计算机科学与探索,2010,4(3):465-468
[7] 苏红军,杜培军,盛业华.高光谱影像波段选择算法研究[J].计算机应用研究,2008,25(4):1093-1096
[8] 葛亮,王斌,张立明.基于偏最小二乘法的高光谱图像波段选择[J].计算机辅助设计与图形学学报,2011,23(11):1844-1852
[9] Xu Ming-ming,Du Bo,Zhang Liang-pei.Spatial-Spectral information based abundance-constrained endmember extraction methods [J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2014,7(8):2004-2015
[10] Mahalanobis P C.On the generalised distance in statistics[C]∥Proceedings of the National Institute of Science of India.1936,12:49-55
[11] De Maesschalck R,Jouan-Rimbaud D,Massart D L.The maha-lanobis distance [J].Chemometrics and intelligent laboratory systems,2000,50(1):1-18
[12] Yang He,Du Qian,Su Hong-jun,et al.An efficient method for supervised hyperspectral band selection [J].IEEE Geoscience and Remote Sensing Letters,2011,8(1):138-142

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed