基于纹理特征和形态学特征融合的高光谱影像分类法

王增茂; 杜博; 张良培; 张乐飞

doi:doi:10.3788/gzxb20144308.0810002

光子学报, 2014, 43 (8): 0810002, 网络出版: 2014-09-01

基于纹理特征和形态学特征融合的高光谱影像分类法

Based on Texture Feature and Extend Morphological Profile Fusion for Hyperspectral Image Classification

论文大纲

王增茂 ^1,*杜博 ²张良培 ¹张乐飞 ²

作者单位

¹ 武汉大学测绘遥感信息工程国家重点实验室, 武汉 430079

² 武汉大学计算机学院, 武汉 430079

摘要

针对传统融合空间和光谱特征方法仅使用单一空间特征, 并未充分利用其双高分辨率的特点, 提出了一种基于纹理特征和形态学特征融合的高光谱影像分类方法.首先利用传统主成份分析变换降低高光谱影像的维数, 消除空间相关性, 然后对每一主成分采用灰度共生矩阵提取纹理特征, 获得扩展纹理特征, 最后结合形态学特征和部分光谱特征进行高光谱影像的分类.实验证明, 本文提出的方法能更好地克服传统光谱特征分类的局限性, 提高高光谱影像的分类准确度.

Abstract

Single spatial feature is used in the traditional spectral and spatial feature fusion,which does not make full use of the advantage of high spectral and spatial resolution.In order to overcome the shortage,a method based on texture feature and extend morphological profile fusion for hyperspectral image classification was proposed.Firstly,with the principle component analysis,the hyperspectral image dimension was reduced and the spatial correlation was eliminated,then using the gray level co-occurrence matrix the texture features for each principle component were extracted and the extend texture features were got,lastly combined the extend morphological profile and part spectral features hyperspectral image is classified.The experiments show that the proposed method can overcome the limitation of traditional spectral feature classification and improve the accuracy of hyperspectral images classification.

参考文献

[1] JLLIFFE I.Principal component analysis［M］.New York:Springer-Verlag,1986.

[2] ZUBKO V,KAUFMAN Y J,BURG R I,et al.Principal component analysis of remote sensing of aerosols over oceans［J］.IEEE Transactions on Geoscience and Remote Sensing,2007,45(3):730-745.

[3] BANDOS T V,BRUZZONE L,CAMPS-VALLS G.Classification of hyperspectral images with regularized linear discriminant analysis［J］.IEEE Transactions on Geoscience and Remote Sensing,2009,47(3):862-873.

[4] KUO B C,LANDGREBE D A.Nonparametric weighted feature extraction for classification［J］.IEEE Transactions on Geoscience and Remote Sensing,2004,42(5):1096-1105.

[5] LANDGREBE D A .Signal theory methods in multispectral remote sensing［M］.Hoboken,NJ:Wiley,2003.

[6] HUANG H Y,KUO B C.Double nearest proportion feature extraction for hyperspectral-image classification［J］.IEEE Transactions on Geoscience and Remote Sensing,2010,48(11):4034-4046.

[7] DU Bo,ZHANG Liang-pei,ZHANG Le-fei.A discriminative manifold learning based dimension reduction method for hyperspectral classification［J］.International Journal of Fuzzy Systems,2012,14(2) ,272-277.

[8] 杜博, 张乐飞, 张良培,等.高光谱图像降维的判别流形学习方法, 光子学报, 2013,42(3):320-325.

DU Bo,ZHANG Le-fei,ZHANG Liang-pei .Discriminnnt manifold learning approach for hyperspectral image dimention reduction［J］.Atca Photonica Sinica,2013,42(3):320-325.

[9] MUSTAFA T,UFUK S.Classification on hyperspectral images using enhanced fisher discriminant criterion［C］.2013 21st Signal Processing and Communications Applications Conference,2013.

[10] HOSSAIN M,JIA X,PICKERING M.Improved feature selection based on a mutual information measure for hyperspectral image classification［C］.2012 IEEE International Geoscience and Remote Sensing Symposium.2012:3058-3061.

[11] JIA X,KUO B C,CRAWFORD M M.Feature mining for hyperspectral image classification［J］.Proceedings of the IEEE,2013,101(3) ,676-697.

[12] KUO B C,LI C H,YANG J M.Kernel nonparametric weighted feature extraction for hyperspectral image classification［J］.IEEE Transactions on Geoscience and Remote Sensing,2009,47(4):1139-1155.

[13] LICCIARDI G,MARPU P R,CHANUSSOT J,et al.Linear versus nonlinear PCA for the classification of hyperspectral data based on the extended morphological profiles［J］.Geoscience and Remote Sensing Letters,IEEE,2012,9(3):447-451.

[14] PESARESI M,BENEDIKTSSON J A.A new approach for the morphological segmentation of high-resolution satellite imagery［J］.IEEE Transactions on Geoscience and Remote Sensing,2001,39(2):309-320.

[15] PALMASON J A,BENEDIKTSSON J A,SVEINSSON J R,et al.Fusion of morphological and spectral information for classification of hyperspectal urban remote sensing data［C］.Proceedings of the Geoscience and Remote Sensing ,Symposium2006(IGARSS′06),2006:2506-2509.

[16] PALMASON J A,BENEDIKTSSON J A,SVEINSSON J R,et al.Classification of hyperspectral data from urban areas using morpholgical preprocessing and independent component analysis［C］.International Geoscience And Remote Sensing Symposium.2005,1:176.

[17] SHEN Lin-lin ,JIA Sen.Three-dimensional gabor wavelets for pixel-based hyperspectral imagery classification［J］.IEEE Transactions on Geoscience and Remote Sensing,2011,49(12) ,5039-5046.

[18] ZHU Ze-xuan,SHEN Lin-lin,SUN Yi-wei,et al.Memetic three-dimensional gabor feature extraction for hyperspectral imagery classification［M］.Advances in Swarm Intelligence.Springer Berlin Heidelberg,2012:479-488.

[19] FAUVEL M,BENEDIKTSSON J A,CHANUSSOT J,et al.Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles［J］.IEEE Transactions on Geoscience and Remote Sensing,2008,46(11):3804-3814.

[20] AYTEKIN O,MURA M D,ULUSOY I,et al.Classification of hyperspectral images based on weighted DMPS［C］.Geoscience and Remote Sensing Symposium (IGARSS),2012 IEEE International,2012:4154-4157.

[21] JI Rong-rong,GAO Yue,HONG Ri-chang,et al.Spectral-spatial constraint hyperspectral image classification［J］.IEEE Transactions on Geoscience and Remote Sensing,2014,52(3):1811-1824.

[22] FAUVEL M.Advances in spectral-spatial classification of hyperspectral images［J］.Proceedings of the IEEE,2013,101(3),652-675.

[23] DUDA R O,HART P E.Pattern classification and scene analysis［M］.New York:Wiley,1973.

[24] SERRA J.Image analysis and mathematical morphology［M］.Volume 2:Theoretical Advances.London,U.K.:Academic,1988.

[25] SERRA J.Image analysis and mathematical morphology［M］.London,U.K.:Academic,1982.

[26] SOILLE P.Morphological image analysis:principles and applications［M］.Springer-Verlag New York,Inc.,2003.

[27] 胡海旭,王文,何厚军.基于纹理特征与数学形态学的高分辨率影像城市道路提取［J］.地理与地理信息学,2008,6(24),47-49.

HU Hai-xu,WANG Wen.Based on texture feature and mathematical morphology for high-resolution images of city road extraction［J］.Geography and Geo-Information Science,2008,6(24),47-49.

[28] 李金莲, 刘晓玫, 李恒鹏.Spot5影像纹理特征提取与土地利用信息识别方法［J］.遥感学报,2006,10(6),927-931.

LI Jin-lian,LIU Xiao-mei,LI Heng-peng.Texture extraction and the land using information recognition methods for spot-5 image［J］.Journal of Remote Sensing,2006,10(6),927-931.

[29] 姜清香,刘慧平.利用纹理分析方法提取TM图像信息［J］.遥感学报, 2004,8(5),459-464.

JIANG Qing-xiang,LIU Hui-ping.Extract information from TM image with texture analysis methods［J］.Journal of Remote Sensing,2004,8(5),459-464.

王增茂, 杜博, 张良培, 张乐飞. 基于纹理特征和形态学特征融合的高光谱影像分类法[J]. 光子学报, 2014, 43(8): 0810002. WANG Zeng-mao, DU Bo, ZHANG Liang-pei, ZHANG Le-fei. Based on Texture Feature and Extend Morphological Profile Fusion for Hyperspectral Image Classification[J]. ACTA PHOTONICA SINICA, 2014, 43(8): 0810002.

基于纹理特征和形态学特征融合的高光谱影像分类法

关于本站 Cookie 的使用提示

全站搜索

基于纹理特征和形态学特征融合的高光谱影像分类法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索