Extraction of landslide information from airborne polarimetric SAR images based on Bayes decision theory
WANG Xingling1, HU Deyong2, TANG Hong3, SHU Yang3
1. National Disaster Reduction Center of China, Ministry of Civil Affairs, P R China, Beijing 100124, China;
2. College of Resource Environment and Tourism, Capital Normal University, Beijing 100048, China;
3. Academy of Disaster Reduction and Emergency Management, Beijing Normal University, Beijing 100875, China
The application of the Radar remote sensing data to landslide investigation is of great importance, especially in cloudy and rainy areas. The high-performance airborne synthetic aperture Radar system(HASARS) developed by Institute of Electronics,Chinese Academy of Sciences,is the first home-made system characterized by multi-band and multi-mode,which has the capability of interferometric survey of X band and double antennas as well as polarimetric observation of P band. In this paper, the accuracies of landslide information extraction from polarimetric SAR data using different polarization combinations were investigated to evaluate the technology, methodology and implementation ideas of the landslide applications with the HASARS, and the focuses included two aspects: the methods of information extraction and the ways to select the feature. The results show that, based on Bayes decision theory and using the samples of landslide and non-landslide in the image to analyze and make decision, the method of feature selection could make classification of polarimetric SAR image satisfactorily. Based on the results of feature selection, the authors extracted the landslide regions from SAR images with supervised classification methods, with their accuracies higher than 90%. The airborne SAR system, with high spatial resolution, high precision DEM production and P band polarimetric observations, can obtain the thematic information of landslide surface more flexibly and precisely, and hence it has a broad prospect in the landslide disaster relief applications.
王兴玲, 胡德勇, 唐宏, 舒阳. 基于Bayes决策的机载全极化SAR图像滑坡信息提取[J]. 国土资源遥感, 2014, 26(2): 121-127.
WANG Xingling, HU Deyong, TANG Hong, SHU Yang. Extraction of landslide information from airborne polarimetric SAR images based on Bayes decision theory. REMOTE SENSING FOR LAND & RESOURCES, 2014, 26(2): 121-127.
[1] 胡德勇,李京,陈云浩,等.GIS支持下滑坡灾害空间预测方法研究[J].遥感学报,2007,11(6):852-859. Hu D Y,Li J,Chen Y H,et al.GIS-based landslide spatial prediction methods:A case study in Comeron highland,Malaysia[J].Journal of Remote Sensing,2007,11(6):852-859.[2] 廖明生,唐婧,王腾,等.高分辨率SAR数据在三峡库区滑坡监测中的应用[J].中国科学:地球科学,2012,42(2):217-229. Liao M S,Tang J,Wang T,et al.Landslide monitoring with high resolution SAR data in the three Gorges region[J].Scientia Sinica Terrae,2012,42(2):217-229.[3] 刘菊,廖静娟,沈国状.基于全极化SAR数据反演鄱阳湖湿地植被生物量[J].国土资源遥感,2012,24(3):38-43. Liu J,Liao J J,Shen G Z.Retrieval of wetland vegetation biomass in Poyang lake based on quad- polarization image[J].Remote Sensing for Land and Resources,2012,24(3):38-43.[4] 王庆,曾琪明,廖静娟.基于极化分解的极化特征参数提取与应用[J].国土资源遥感,2012,24(3):103-110. Wang Q,Zeng Q M,Liao J J.Extraction and application of polarimetric characteristic parameters based on polarimetric decomposition[J].Remote Sensing for Land and Resources,2012,24(3):103-110.[5] 吴永辉,计科峰,郁文贤.基于H-α和改进C-均值的全极化SAR图像非监督分类[J].电子与信息学报,2007,29(1):30-34. Wu Y H,Ji K F,Yu W X.Unsupervised classification of fully polarimetric SAR image using H-α decomposition and modified C-mean algorithm[J].Journal of Electronics and Information Technology,2007,29(1):30-34.[6] Qi Z X,Yeh A G O,Li X,et al.A novel algorithm for land use and land cover classification using Radarsat-2 polarimetric SAR data[J].Remote Sensing of Environment,2012,118:21-39.[7] Wen X B,Zhang H,Zhang J G,et al.Multiscale modeling for classification of SAR imagery using hybrid EM algorithm and genetic algorithm[J].Progress in Natural Science,2009,19(8):1033-1036.[8] Balaguer A,Ruiz L A,Hermosilla T,et al.Definition of a comprehensive set of texture semivariogram features and their evaluation for object-oriented image classification[J].Computers and Geosciences,2010,36(2):231-240.[9] 胡德勇,李京,陈云浩,等.单波段单极化SAR图像水体和居民地信息提取方法研究[J].中国图象图形学报,2008,13(2):257-263. Hu D Y,Li J,Chen Y H,et al.Water and settlement area extraction from single-band,single-polarization SAR images based on SVM method[J].Journal of Image and Graphics,2008,13(2):257-263.[10] 吴永辉,计科峰,郁文贤.SVM全极化SAR图像分类中的特征选择[J].信号处理,2007,23(6):877-881. Wu Y H,Ji K F,Yu W X.A new feature selection algorithm for SVM-based fully polarimetric SAR image classification[J].Signal Processing,2007,23(6):877-881.[11] Bhanu B,Lin Y Q.Genetic algorithm based feature selection for target detection in SAR images[J].Image and Vision Computing,2003,21(7):591-608.[12] Li S,Wu H,Wan D S,et al.An effective feature selection method for hyperspectral image classification based on genetic algorithm and support vector machine[J].Knowledge-Based Systems,2011,24(1):40-48.[13] 刘蓉,靳红梅,段福庆.基于Bayes决策的光谱分类[J].光谱学与光谱分析,2010,30(3):838-841. Liu R,Jin H M,Duan F Q.Spectral classification based on Bayes decision[J].Spectroscopy and Spectral Analysis,2010,30(3):838-841.[14] 刘国庆,熊红,黄顺吉,等.多视极化合成孔径雷达图象的分类和极化通道优化[J].电子科学学刊,1998,20(1):56-61. Liu G Q,Xiong H,Huang S J,et al.Classification of multi-look polarimetric SAR imagery and polarization channel optimization[J].Journal of Electronics and Information Technology,1998,20(1):56-61.[15] 岳晋,杨汝良,宦若虹.贝叶斯理论在多波段SAR图像融合分类中的应用[J].中国科学院研究生院学报,2008,25(2):257-263. Yue J,Yang R L,Huan R H.Application of Bayesian theory in multiband SAR image fusion for classification[J].Journal of the Graduate School of the Chinese Academy of Sciences,2008,25(2):257-263.[16] 杨文,颜卫,涂尚坦,等.基于贝叶斯信息准则的极化干涉SAR图像非监督分类[J].电子与信息学报,2012,34(11):2628-2634. Yang W,Yan W,Tu S T,et al.An unsupervised classification method of polinSAR image based on Bayesian information criterion[J].Journal of Electronics and Information Technology,2012,34(11):2628-2634.[17] Hospedales T M,Vijayakumar S.Structure inference for Bayesian multisensor scene understanding[J].IEEE Transactions on pattern analysis and machine intelligence,2008,30(12):2140-2157.
2014, Vol. 26 
