基于Radarsat-2的冬小麦种植面积提取方法研究  

Extraction Method of Winter Wheat Planting Area Based on Radarsat-2 Data

作　　者：单捷[1] 邱琳[1] 孙玲[1] 王志明[1] 

机构地区：[1]江苏省农业科学院农业信息研究所,江苏南京210014

出　　处：《麦类作物学报》2017年第9期1209-1215,共7页Journal of Triticeae Crops

基　　金：国家科技重大专项课题(09-Y30B03-9001-13/15-4);江苏省农业科学院基金项目(6111651;6111650);江苏省农业科学院基本科研业务专项(ZX-15-3003);农业部遥感应用中心技术创新课题(2911660);江苏省农业科技自主创新资金项目[CX(17)3020]

摘　　要：为探寻基于Radarsat-2的冬小麦种植面积提取方法,以设立在江苏盐城研究区的冬小麦为研究对象,选用2014年3月3日-2014年6月7日期间5期Radarsat-2全极化影像,采用支持向量机法和最大似然法分别对各时相的冬小麦种植面积进行提取,并以地面实测GPS样方进行精度验证。结果表明,以支持向量机法和最大似然法提取冬小麦面积的精度均在4月20日达到最高,分别为66.4%和63.9%。对4月20日支持向量机法的冬小麦面积提取结果进一步进行耕地地块优化和碎小图斑去除处理后,冬小麦面积的提取精度可提高到79.6%。In order to study the extraction method of winter wheat planting area based on Radarsat-2 data,five scenes of Radarsat-2 satellite images collected from March 3, 2014 to June 7, 2014 were used to extract winter wheat planting area through the methods of Support Vector Machine（SVM） and Maximum Likelihood Classification（MLC）, and the accuracy of this investigation is verified by on-site GPS measurement quadrat areas. The results indicated that the highest extraction accuracies of both methods were achieved on April 20, so we chose the image of April 20 to study the effect of farmland parcel optimization and classification patch optimization on SVM＇s accuracy. The extraction accuracy of SVM was improved from 66.4% to 79.6% after optimization.

关 键 词：RADARSAT-2 遥感 冬小麦 种植面积 提取方法 

分 类 号：S512.1[农业科学—作物学] S314