一种Landsat-8影像提取不透水面的新方法  

A New Extraction Method of Impervious Surface Based on Landsat-8

作　　者：闫如柳 杨树文 张珊 贾鑫 YAN Ruliu;YANG Shuwen;ZHANG Shan;JIA Xin(Faculty of Geomatics,Lanzhou Jiaotong University,Lanzhou 730070,China;National-Local Joint Engineering Research Center of Technologies and Applications for National Geographic State Monitoring,Lanzhou 730070,China;Gansu Provincial Engineering Laboratory for National Geographic State Monitoring,Lanzhou 730070,China)

机构地区：[1]兰州交通大学测绘与地理信息学院,兰州730070 [2]地理国情监测技术应用国家地方联合工程研究中心,兰州730070 [3]甘肃省地理国情监测工程实验室,兰州730070

出　　处：《遥感信息》2019年第4期128-132,共5页Remote Sensing Information

基　　金：兰州市人才创新创业项目(2015-RC-28);国家重点研发计划(地球观测与导航)(2017YFB0504201);国家自然科学基金(41761082);兰州交通大学优秀平台支持(201806)

摘　　要：针对V-H-L-S模型在提取不透水面中端元选取不足的问题,提出了一种基于Landsat-8OLI影像提取不透水面的新方法。该方法首先集成了归一化水体指数(NDWI)、归一化植被指数(NDVI)和调整型土壤调节植被指数(MSAVI);其次,通过制作水体、植被及土壤掩膜,将三者信息进行叠加;然后,运用MNF变换将原始影像信息集中至前三波段;最后,将掩膜文件与MNF变换后影像合成,选取阈值提取不透水面信息。实验结果验证了该方法可以快速有效地提取不透水面,总体精度达90.94%,Kappa系数为0.81。A new method of extracting impervious surface based on Landsat-8 OLI image is proposed to solve the problem of insufficient selection of endmember in the V-H-L-S model.First,the method integrates normalized difference water index(NDWI),normalized difference vegetation index(NDVI),and modified soil-adjusted vegetation index(MSAVI).Second,the three pieces of information are superimposed by making water,vegetation and soil masks.Then,use the MNF transform to concentrate the original image information into the first three bands.Finally,the mask files are combined with the MNF transformed images,and the threshold values are extracted to extract the impervious surface information.The result shows that this method can extract impervious surface quickly and availably with the overall accuracy 90.94% and Kappa coefficient 0.81.

关 键 词：不透水面 Landsat-8 V-H-L-S MNF 掩膜 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]