基于GF-2高分辨率遥感影像的水体提取方法研究  

Research on Water Body Extraction Method Based on GF-2 High Resolution Remote Sensing Image

作　　者：刘双童 王明孝[4] 杨树文 杨明泽 杨立华 LIU Shuangtong;WANG Mingxiao;YANG Shuwen;YANG Mingze;YANG Lihua(Faculty of Geomatics,Lanzhou Jiaotong University,Lanzhou 730070,China;Gansu Provincial Engineering Laboratory for National Geographic State Monitoring,Lanzhou 730070,China;Post-Doctor Research Center of PLA 68029 Troops,Lanzhou 730020,China;Lanzhou Precision Sand Table Model Intelligent Manufacturing Co.,Ltd.,Lanzhou 730020,China)

机构地区：[1]兰州交通大学测绘与地理信息学院 [2]甘肃省地理国情监测工程实验室 [3]兰州精准地形沙盘模型智能制造有限公司 [4]中国人民解放军68029部队博士后科研工作站

出　　处：《全球定位系统》2018年第6期37-43,共7页Gnss World of China

基　　金：国家自然科学基金(41761082);国家重点研发计划资助(2017YFB0504201)

摘　　要：针对GF-2卫星影像数据的特点,利用单波段阈值法、多波段算法、归一化水体指数(NDWI)阈值法、单波段阈值法与阴影水体指数(SWI)相结合的决策树法对刘家峡地区的水体信息进行了提取,同时提出一种单波段阈值法与增强阴影水体指数(ESWI)相结合的决策树分类法,并对以上几种水体提取的效果进行比较分析,发现单波段阈值法与ESWI相结合的决策树分类法能够有效地消除绝大部分阴影的影响,且提取效果较SWI的效果要好,NDWI与多波段算法提取效果次之,单波段阈值法提取效果较差.For the characteristics of GF-2 satellite image data,the water information in Liujiaxia area is extracted by single-band threshold method,multi-band algorithm,normalized difference water index threshold method(NDWI)and the decision tree method combining single-band threshold method with shadow water index(SWI).At the same time,a decision tree classification method combining single-band threshold method and enhanced shadow water index(ESWI)is proposed.The comparison of the effects of these water extraction method is carried out.It is found that the decision tree classification method combining single-band threshold method with ESWI can effectively eliminate the influence of most shadows,and the extraction effect is better than that of SWI.NDWI and multi-band algorithm has a second extraction effect.The single-band threshold method has a poor extraction effect.

关 键 词：GF-2 NDWI阈值法 水体信息 ESWI 决策树分类法 

分 类 号：TP[自动化与计算机技术]