利用改进相似性度量方法进行高光谱海冰检测
|
摘要
针对高光谱数据波段之间的相似性和冗余性导致传统海冰检测方法的精度和效率都难以提高的问题,提出了一种基于改进相似性度量的方法用于海冰检测。首先,使用互信息方法确定信息量最大的波段作为第1个初始波段;随后,使用光谱相似性度量方法选择与第1个初始波段最不相似的波段作为第2个初始波段;最后,使用线性预测方法选择剩余波段,并采用支持向量机分类器模型进行海冰分类。在2个高光谱海冰实验中,将所提出方法与传统海冰检测方法进行了对比验证,实验结果表明相对于其他方法,改进相似性度量方法在总体上具有更好的性能,该方法可以更有效地应用于高光谱海冰检测。
Because of the similarity and redundancy between hyperspectral data bands,it is difficult to improve the accuracy and efficiency of the traditional sea ice detection method.This article proposes an improved similarity measure method for the sea ice detection.First,the first original band with a large amount of information is determined based on the mutual information theory.Subsequently,the second original band with the least similarity is chosen by the spectral correlation measure method.Finally,the subsequent bands are selected through the linear prediction method,and the support vector machine classifier model is utilized for sea ice classification.In two experiments,comparative analyses are carried out between the proposed method and traditional sea ice detection methods.The experimental results indicate that the proposed method exhibits better performance overall than other methods and can be effectively applied in hyperspectral sea ice detection.
Because of the similarity and redundancy between hyperspectral data bands,it is difficult to improve the accuracy and efficiency of the traditional sea ice detection method.This article proposes an improved similarity measure method for the sea ice detection.First,the first original band with a large amount of information is determined based on the mutual information theory.Subsequently,the second original band with the least similarity is chosen by the spectral correlation measure method.Finally,the subsequent bands are selected through the linear prediction method,and the support vector machine classifier model is utilized for sea ice classification.In two experiments,comparative analyses are carried out between the proposed method and traditional sea ice detection methods.The experimental results indicate that the proposed method exhibits better performance overall than other methods and can be effectively applied in hyperspectral sea ice detection.
引文
[1]DESER C,WALSH J E,TIMLIN M S.Arctic sea ice variability in the context of recent atmospheric circulation trends[J].Journal of Climate,2014,13(3):617-633.
[2]罗征宇,孙林.基于高光谱影像的渤海海冰遥感监测研究[J].测绘科学,2012,37(1):54-55.
[3]LAINE V.Antarctic ice sheet and sea ice regional albedo and temperature change,1981—2000,from AVHRR Polar Pathfinder data[J].Remote Sensing of Environment,2008,112(3):646-667.
[4]HALL D K,KEY J R,CASEY K A,et al.Sea ice surface temperature product from MODIS[J].IEEE Transactions on Geoscience&Remote Sensing,2004,42(5):1076-1087.
[5]柯长青,谢红接,雷瑞波,等.北极海冰的光谱特征分析[J].光谱学与光谱分析,2012,32(4):1081-1084.
[6]范群贞,刘金清.基于PCA/ICA的人脸特征提取新方法[J].电子测量技术,2010,33(8):31-34.
[7]WANG H Z,ANGELOPOULOU E.Average normalized information:a novel entropy-based band selection method[J].Doctoral,2004.
[8]DU Q,YANG H.Similarity-based unsupervised band selection for hyperspectral image analysis[J].IEEE Geoscience&Remote Sensing Letters,2008,5(4):564-568.
[9]YANG J H,YIN Q,ZHOU N.An improved method of hyperspectral remote sensing data adaptive band selection[J].Remote Sensing Technology&Application,2007.
[10]周杨,厉小润,赵辽英.改进的高光谱图像线性预测波段选择算法[J].光学学报,2013(8):256-263.
[11]CHANG C,DU Q.Estimation of number of spectrally distinct signal sources in hyperspectral imagery[J].IEEE Transactions on Geoscience&Remote Sensing,2004,42(3):608-619.
[12]HAN Y L,REN J,HONG Z H,et al.Active learning algorithms for the classification of hyperspectral sea ice images[J].Mathematical Problems in Engineering,2015.
[13]WIKIPEDIA.Landsat_7from Wikipedia[EB/OL].[2016-10-27].https://en.wikipedia.org/wiki/Landsat_7.
[14]BARRY P.EO-1/hyperion science data user’s guide,level 1_b[J].TRW Space,Defense and Information Systems,2001,555-557.
[2]罗征宇,孙林.基于高光谱影像的渤海海冰遥感监测研究[J].测绘科学,2012,37(1):54-55.
[3]LAINE V.Antarctic ice sheet and sea ice regional albedo and temperature change,1981—2000,from AVHRR Polar Pathfinder data[J].Remote Sensing of Environment,2008,112(3):646-667.
[4]HALL D K,KEY J R,CASEY K A,et al.Sea ice surface temperature product from MODIS[J].IEEE Transactions on Geoscience&Remote Sensing,2004,42(5):1076-1087.
[5]柯长青,谢红接,雷瑞波,等.北极海冰的光谱特征分析[J].光谱学与光谱分析,2012,32(4):1081-1084.
[6]范群贞,刘金清.基于PCA/ICA的人脸特征提取新方法[J].电子测量技术,2010,33(8):31-34.
[7]WANG H Z,ANGELOPOULOU E.Average normalized information:a novel entropy-based band selection method[J].Doctoral,2004.
[8]DU Q,YANG H.Similarity-based unsupervised band selection for hyperspectral image analysis[J].IEEE Geoscience&Remote Sensing Letters,2008,5(4):564-568.
[9]YANG J H,YIN Q,ZHOU N.An improved method of hyperspectral remote sensing data adaptive band selection[J].Remote Sensing Technology&Application,2007.
[10]周杨,厉小润,赵辽英.改进的高光谱图像线性预测波段选择算法[J].光学学报,2013(8):256-263.
[11]CHANG C,DU Q.Estimation of number of spectrally distinct signal sources in hyperspectral imagery[J].IEEE Transactions on Geoscience&Remote Sensing,2004,42(3):608-619.
[12]HAN Y L,REN J,HONG Z H,et al.Active learning algorithms for the classification of hyperspectral sea ice images[J].Mathematical Problems in Engineering,2015.
[13]WIKIPEDIA.Landsat_7from Wikipedia[EB/OL].[2016-10-27].https://en.wikipedia.org/wiki/Landsat_7.
[14]BARRY P.EO-1/hyperion science data user’s guide,level 1_b[J].TRW Space,Defense and Information Systems,2001,555-557.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |