基于改进混合像元方法的MODIS影像水体提取研究  

The Study on Extracting of Water Body from MODIS Image Using an Improved Linear Mixture Model

作　　者：刘晨洲[1,2] 施建成[1,3] 高帅[1,2] 陈亮[1,2] 

机构地区：[1]遥感科学国家重点实验室,中国科学院遥感应用研究所,北京100101 [2]中国科学院研究生院,北京100049 [3]University of California,Santa Barbara,U.S.A CA93106

出　　处：《遥感信息》2010年第1期84-88,共5页Remote Sensing Information

基　　金：SMOS土壤水分反演技术改进与FY-3土壤水分校正技术研究(2007AA12Z135)资助

摘　　要：基于MODIS的反射率数据,利用改进的线性混合像元分解方法提取水体,并结合MODIS温度产品和SRTM的DEM数据校正阴影对提取结果的影响。通过和利用ETM+影像的水体提取结果对比分析得出:该方法结果较好的体现出河流和湖泊的细节特点,同时在很大程度上消除了阴影影响,面积提取结果具有较高的精度。Improved linear mixture model was applied to extract water body based on MODIS reflectance images.The DEM and temperature data acquired from SRTM and MODIS were used to correct the result affected by shade and other factors.Finally,the accuracy of the result and performance of the algorithm were assessed using ETM＋ images.It was indicated that the details of the river can be well revealed in the result;at the same time the impact of shade can be corrected,and the final result has a high accuracy.

关 键 词：线性混合像元分解 端元 混合像元 阴影 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]