Application of Polarization Characteristic Combination in ALOS PALSAR Data Classification

doi:10.13474/j.cnki.11-2246.2018.0204

Abstract

Abstract: Polarimetric SAR image classification is one of the hots pots in the field of remote sensing,which provides a new means for information acquisition and classification of objects.In this paper,support vector machine (SVM) is used to classify ALOS PALSAR polarized data in Pengzhou petrochemical area,Sichuan province.In the experiment,the total power of polarization is firstly obtained,then the Cloude-Pottier polarization is decomposed,and then the feature parameters,Shannon entropy and radar vegetation index are extracted based on the eigenvalues of the coherent matrix.The SVM classification of the images is carried out by combining these polarimetric features,and compared with the SVM classification based on Freeman-Durden polarization decomposition and Wishart supervised classification.The experimental results show that the polarization characteristic combined with the information is complementary and the classification result is better,the Kappa coefficient is 97.14%,and the Kappa coefficient of the other two methods increased by 5.26% and 27.20%,respectively.

Key words: ALOS PALSAR, polarization characteristic combination, support vector machine, Cloude-Pottier decomposition, classification of objects

CLC Number:

P237

JIA Shichao, XUE Dongjian, LI Chengrao. Application of Polarization Characteristic Combination in ALOS PALSAR Data Classification[J]. 测绘通报, 2018, 0(7): 29-33,47.

References

[1] 张红,王超.极化SAR理论、方法与应用[M].北京:科学出版社,2015.
[2] HUYNEN J R.Phenomenological Theory of Radar Targets[J].Electromagnetic Scattering,1978:653-712.
[3] WANG S,LIU K,PEI J,et al.Unsupervised Classification of Fully Polarimetric SAR Images Based on Scattering Power Entropy and Copolarized Ratio[J].IEEE Geoscience and Remote Sensing Letters,2013,10(3):622-626.
[4] XUE X,DI L,GUO L,et al.An Efficient Classification Method of Fully Polarimetric SAR Image Based on Polarimetric Features and Spatial Features[C]//International Conference on Agro-Geoinformatics.Istanbul:IEEE,2015.
[5] VAN ZYL J J,BURNETTE C F.Bayesian Classification of Polarimetric SAR Images Using Adaptive a Priori Probabilities[J].International Journal of Remote Sensing,1992,13(5):835-840.
[6] 周晓光,匡纲要,万建伟.极化SAR图像分类综述[J].信号处理,2008,24(5):806-812.
[7] FUKUDA S,HIROSAWA H.Support Vector Machine Classification of Land Cover:Application to Polarimetric SAR Data[C]//Proceedings of IGARSS '01.Sydney,Australia:[s.n.],2001:187-189.
[8] 汪洋,鲁加国,张长耀.基于Cameron分解和SVM的极化SAR图像分类[J].计算机工程与应用,2006,42(36):17-19.
[9] 裴静静.基于Freeman分解的极化SAR图像分类研究[D].西安:西安电子科技大学,2012.
[10] 杨然,李坤,涂志刚,等.基于Yamaguchi分解模型的全极化SAR图像分类[J].计算机工程与应用,2009,42(36):5-7.
[11] 马騳骉,卢春燕.基于联合特征和SVM的极化SAR图像分类方法[J].无线电工程,2017,47(3):31-34.
[12] 曲永超,赵书河,庄喜阳,等.基于特征值和Singh分解的全极化Radarsat-2图像分类[J].地理空间信息,2016,14(5):60-63.
[13] CLOUDE S R,POTTIER E.An Entropy Based Classification Scheme for Land Applications of Polarimetric SAR[J].IEEE Transactions on Geoscience and Remote Sensing,1997,35(1):68-78.
[14] MORIO J,REFREGIER P,GOUDAIL F,et al.Application of Information Theory Measures to Polarimetric and Interferometric SAR Images[C]//PSIP.Mulhouse,France:[s.n.],2007.
[15] MORIO J,REFREGIER P.Shannon Entropy of Partially Polarized and Partially Coherent Light with Gaussian Fluctuations[J].Journal of the Optical Society of America A,2006,23(12):3036-3044.
[16] ZYL J J V.Application of Cloude's Target Decomposition Theorem to Polarimetric Imaging Radar Data[C]//Proceedings of SPIE. San Diego:[s.n.],1993:184-191.
[17] 陈媛媛,何秀凤,王静.基于SVM的极化SAR沿海滩涂分类[J].地理空间信息,2015,13(6):150-153.
[18] 冯青.基因微阵列数据的SVM分类器优化方法[D].长春:东北师范大学,2010.
[19] LEE J S,GRUNES M R.Classification of Multi-look Polarimetric SAR Data Based on Complex Wishart Distribution[J].International Journal of Remote Sensing,1994,15(11):2299-2311.
[20] 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.
[21] 赵一博,秦先祥,邹焕新.基于目标分解和SVM的极化SAR图像分类方法[J].航天返回与遥感,2013,34(2):50-56.