全极化SAR数据土地覆盖分类精度分析  

Accuracy Analysis of Fully Polarimetric SAR for Land Cover Classification

作　　者：杨靖[1] 苏彩霞[1] 曹永锋[1] 

机构地区：[1]贵州师范大学数学与计算机科学学院,贵阳550000

出　　处：《遥感信息》2015年第5期88-93 101,101,共7页Remote Sensing Information

基　　金：国家自然科学基金(41161065;40901207);贵州省科学技术厅;贵州师范大学联合科技基金资助项目(黔科合J字LKS[2013]28号)

摘　　要：鉴于全极化SAR数据进行土地覆盖分类时不同特征组合会对分类结果带来巨大的影响,该文以美国国家土地覆盖数据为参考分析全极化SAR数据不同特征组合的土地覆盖分类精度。文中以分类精度为准则选取适用的分类方法,对比分析了不同分解组合和波段组合对分类结果的影响,同时给出同一时期成像的TM数据分类结果做比较。结果表明,SAR数据通过有效的分解组合能提高总体分类精度。同时,SAR数据不同分解特征之间有信息冗余和信息互补的关系,波段组合分类时需考虑其对分类结果的影响。波段组合分类得到了最高的总体分类精度71.6%和Kappa系数0.6,表明全极化SAR数据土地覆盖分类,尤其对于一些如"有林湿地"等待定类别,可以达到很好的分类质量。Because different features of the fully polarization SAR data combination get a different land cover classification result,this paper uses NLCD land cover classification results as a reference analyzing the fully polarization SAR data land cover classification accuracy.We select a suitable classification method with classification accuracy as a guideline,and then analysis the influence of different decomposition combination and band combination on the classification results.At the same time, classification results of the TM data imaging during the same period are given as a comparison.The results show that an effective decomposition combination can improve the overall classification accuracy and there is a information redundancy and complementary relationship between different decomposition characteristics of SAR data;we should consider its impact on the classification results when using band combination to classify land cover.Band combination classification has got the highest overall classification accuracy of 71.6% and Kappa coefficient of 0.6,which shows that the fully polarization SAR data, especially in class of woody wetlands,can achieve good classification quality.

关 键 词：全极化SAR 土地覆盖分类 目标分解 精度分析 特征组合 

分 类 号：P237[天文地球—摄影测量与遥感]