基于中、高分辨率遥感影像的县域尺度马铃薯和向日葵种植面积监测  

USING GF-2 AND LANDSAT 8 REMOTE SENSING IMAGE TO ESTIMATING POTATO AND SUNFLOWER ACREAGE ON COUNTY SCALE

作　　者：谢岷[1] 罗军[1] 张永平[1] 赵博 吴强 李建军 XIE Min;LUO Jun;ZHANG Yongping;ZHAO Bo;WU Qiang;LI Jianjun(College of Agronomy,Inner Mongolia Agricultural University,Hohhot 010019,China;Inner Mongolia SENWO Technology Corporation Limited,Hohhot 010010,China)

机构地区：[1]内蒙古农业大学农学院,呼和浩特010019 [2]内蒙古森沃科技有限公司,呼和浩特010010

出　　处：《内蒙古农业大学学报（自然科学版）》2019年第5期19-25,共7页Journal of Inner Mongolia Agricultural University(Natural Science Edition)

基　　金：呼和浩特市科技局基金项目(2015-农-5);内蒙古自然科学基金(2015BS0305)

摘　　要：近年来,中、高空间分辨率遥感数据在农作物遥感监测上发挥着重要作用。本研究利用Landsat 8及GF-2遥感数据,基于不同作物的物候、波谱和纹理差异,采用监督分类的方法,对内蒙古自治区呼和浩特市武川县马铃薯和向日葵种植面积进行识别提取。研究结果表明,该方法在县域尺度上能够有效监测识别2种作物的种植面积,且识别精度较高,用户、制图和总体分类精度三者均高达96%以上,Kappa系数为0.9354,可满足遥感监测作物种植面积的需求,也可为县域尺度非大宗作物的面积监测识别提供理论依据。The purpose of this study was to understand the feasibility and accuracy of estimating potato and sunflower acreage based on the Landsat 8 and GF-2 image of county scale by taking Wuchuan County at Inner Mongolia as study region.The identification and analysis of potato and sunflower fields were based on multiple acquisitions of Landsat and GF digital data used in an unsupervised clustering approach with masking of multitemporal data sets.The results showed that the user,prod and overall accuracy of method approximately reached in 96%,Kappa coefficient was 0.9354.It could meet the needs of It can meet the needs of remote sensing monitoring of crop planting area,and provided theoretical basis for monitoring and identification of non-bulk crops at county level.

关 键 词：遥感监测 马铃薯 向日葵 种植面积 

分 类 号：S-3[农业科学]