光学-极化SAR影像特征融合与分类
|
摘要
针对多源遥感影像分类的需要,本文提出一种光学-极化SAR影像特征融合与分类,利用山东省泰安市区域的Landsat-5与全极化ALOS PALSAR卫星进行了实验验证。实验结果表明,引入全极化SAR目标分解后向散射特征与极化均值纹理特征的特征级影像融合分类,总体精度达到98.804 8%,能够充分利用影像特征之间的合作性与互补性,减少分类结果的椒盐噪声,从而有效地提高影像的分类精度。
To make full use of the multi-source remote sensing images for classification,a new method was proposed based on features fusion and classification of optical and full-polarization Advanced Land Observing Satellite-the Phased Array Type L-band Synthetic Aperture Radar( ALOS PALSAR) images. The Landsat-5 and full-polarization ALOS PALSAR satellite in Taian City of Shandong province are used to verify the results of the experiments. The experiment result shows that the overall accuracy reached to 98.804 8%when the full-polarization SAR target decomposition backscattering features and polarmetric mean texture feature are introduced,which can make full use of the cooperation and complimentarily between the image features,reduce the salt and pepper noise and effectively improve the classification accuracy.
To make full use of the multi-source remote sensing images for classification,a new method was proposed based on features fusion and classification of optical and full-polarization Advanced Land Observing Satellite-the Phased Array Type L-band Synthetic Aperture Radar( ALOS PALSAR) images. The Landsat-5 and full-polarization ALOS PALSAR satellite in Taian City of Shandong province are used to verify the results of the experiments. The experiment result shows that the overall accuracy reached to 98.804 8%when the full-polarization SAR target decomposition backscattering features and polarmetric mean texture feature are introduced,which can make full use of the cooperation and complimentarily between the image features,reduce the salt and pepper noise and effectively improve the classification accuracy.
引文
[1]Bastin L.Comparison of fuzzy c-means classification,linear mixture modelling and MLC probabilities as tools for unmixing coarse pixels[J].International Journal of Remote Sensing,1997,18(17):3 629-3 648.
[2]Giacinto G,Roli F,Bruzzone L.Combination of neural and statistical algorithms for supervised classification of remote-sensing images[J].Pattern Recognition Letters,2000,21(5):385-397.
[3]Ferro-Famil L,Pottier E,Lee J S.Unsupervised classification of multifrequency and fully polarimetric SAR images based on the H/A/Alpha-Wishart classifier[J].IEEETransactions on Geoscience&Remote Sensing,2017,39(11):2 332-2 342.
[4]D'Elia C,Ruscino S,Abbate M,et al.SAR Image Classification Through Information-Theoretic Textural Features,MRF Segmentation,and Object-Oriented Learning Vector Quantization[J].IEEE Journal of Selected Topics in Applied Earth Observations&Remote Sensing,2014,7(4):1 116-1 126.
[5]JunZhan,Wang,JianJun.Classification of fullpolarization ALOS-PALSAR imagery using SVM in arid area of Dunhuang[J].Sciences in Cold and Arid Regions,2016,8(3):263-267.
[6]Wei Z,Shen H,Huang C,et al.Fusion of polarimetric and texture information for urban building extraction from fully polarimetric SAR imagery[J].Remote Sensing Letters,2016,7(1):31-40.
[7]Freeman A,Durden S L.A three-component scattering model for polarimetric SAR data[J].IEEE Transactions on Geoscience and Remote Sensing,1998,36(3):963-973.
[8]Yamaguchi Y,Moriyama T,Ishido M,et al.Four-component scattering model for polarimetric SAR image decomposition[J].IEEE Transactions on Geoscience&Remote Sensing,2005,43(8):1 699-1 706.
[9]Pei L,Du Pei-Jun,Kun T.A novel remotely sensed image classification based on ensemble learning and feature integration[J].Journal of Infrared and Millimeter Waves,2014,33(3):311-317.
[10]冯兰平.融合多源数据的土地利用分类与变化分析研究[D].长沙:中南大学,2016.
[11]Teimouri M,Mokhtarzade M,Zoej M J V.Optimal fusion of optical and SAR high-resolution images for semiautomatic building detection[J].Mapping Sciences&Remote Sensing,2016,53(1):45-62.
[12]Clewley D,Lucas R,Accad A,et al.An Approach to Mapping Forest Growth Stages in Queensland,Australia through Integration of ALOS PALSAR and Landsat Sensor Data[J].Remote Sensing,2012,4(8):2 236-2 255.
[13]Lee J S.Refined filtering of image noise using local statistics[J].Computer Graphics&Image Processing,1980,15(4):380-389.
[14]Haralick R M,Shanmugam K,Dinstein I.Textural Features for Image Classification[J].Systems Man&Cybernetics IEEE Transactions on,1973,smc-3(6):610-621.
[2]Giacinto G,Roli F,Bruzzone L.Combination of neural and statistical algorithms for supervised classification of remote-sensing images[J].Pattern Recognition Letters,2000,21(5):385-397.
[3]Ferro-Famil L,Pottier E,Lee J S.Unsupervised classification of multifrequency and fully polarimetric SAR images based on the H/A/Alpha-Wishart classifier[J].IEEETransactions on Geoscience&Remote Sensing,2017,39(11):2 332-2 342.
[4]D'Elia C,Ruscino S,Abbate M,et al.SAR Image Classification Through Information-Theoretic Textural Features,MRF Segmentation,and Object-Oriented Learning Vector Quantization[J].IEEE Journal of Selected Topics in Applied Earth Observations&Remote Sensing,2014,7(4):1 116-1 126.
[5]JunZhan,Wang,JianJun.Classification of fullpolarization ALOS-PALSAR imagery using SVM in arid area of Dunhuang[J].Sciences in Cold and Arid Regions,2016,8(3):263-267.
[6]Wei Z,Shen H,Huang C,et al.Fusion of polarimetric and texture information for urban building extraction from fully polarimetric SAR imagery[J].Remote Sensing Letters,2016,7(1):31-40.
[7]Freeman A,Durden S L.A three-component scattering model for polarimetric SAR data[J].IEEE Transactions on Geoscience and Remote Sensing,1998,36(3):963-973.
[8]Yamaguchi Y,Moriyama T,Ishido M,et al.Four-component scattering model for polarimetric SAR image decomposition[J].IEEE Transactions on Geoscience&Remote Sensing,2005,43(8):1 699-1 706.
[9]Pei L,Du Pei-Jun,Kun T.A novel remotely sensed image classification based on ensemble learning and feature integration[J].Journal of Infrared and Millimeter Waves,2014,33(3):311-317.
[10]冯兰平.融合多源数据的土地利用分类与变化分析研究[D].长沙:中南大学,2016.
[11]Teimouri M,Mokhtarzade M,Zoej M J V.Optimal fusion of optical and SAR high-resolution images for semiautomatic building detection[J].Mapping Sciences&Remote Sensing,2016,53(1):45-62.
[12]Clewley D,Lucas R,Accad A,et al.An Approach to Mapping Forest Growth Stages in Queensland,Australia through Integration of ALOS PALSAR and Landsat Sensor Data[J].Remote Sensing,2012,4(8):2 236-2 255.
[13]Lee J S.Refined filtering of image noise using local statistics[J].Computer Graphics&Image Processing,1980,15(4):380-389.
[14]Haralick R M,Shanmugam K,Dinstein I.Textural Features for Image Classification[J].Systems Man&Cybernetics IEEE Transactions on,1973,smc-3(6):610-621.