基于GF-1卫星影像数据融合的冬小麦田空间信息提取  

Spatial Information Extraction of Winter Wheat Field Based on GF-1 Satellite Image Data Fusion

在线阅读下载全文

作  者:韩振强 毛星 李卫国 李伟[3] 马廷淮[4] 张宏[2] 刘力源 HAN Zhenqiang;Mao Xing;LI Weiguo;LI Wei;MA Tinghuai;ZHANG Hong;LIU Liyuan(College of Agricultural Engineering,Jiangsu University,Zhenjiang,Jiangsu 212013,China;Institute of Agricultural Information,Jiangsu Academy of Agricultural Sciences,Nanjing,Jiangsu 210014,China;Fluid Machinery Engineering Technology Research Center,Jiangsu University,Zhenjiang,Jiangsu 212013,China;Nanjing University of Information Science and Technology,Nanjing,Jiangsu 210044,China)

机构地区:[1]江苏大学农业工程学院,江苏镇江212013 [2]江苏省农业科学院农业信息研究所,江苏南京210014 [3]江苏大学流体机械工程技术研究中心,江苏镇江212013 [4]南京信息工程大学,江苏南京210044

出  处:《麦类作物学报》2024年第8期1056-1062,共7页Journal of Triticeae Crops

基  金:国家重点研发计划项目(政府间科技创新合作)(2021YFE0104400);国防科工局高分辨率对地观测系统重大专项(74-Y50G12-9001-22/23);江苏省农业科技自主创新资金项目(CX(20)2037)。

摘  要:为给高标准农田建设规划和粮食安全生产措施的制定提供准确信息,在对国产GF-1/PMS卫星影像进行辐射定标、大气校正、几何校正和裁剪等预处理的基础上,经过影像融合提取了高标准麦田多地物的点像元光谱信息,通过分析不同地物光谱特征,利用波段反射率、归一化差值植被指数(NDVI)和差值植被指数(DVI)构建植被光谱特征指标阈值,进而对冬小麦田及非麦田进行分类,以获取高标准麦田的空间分布信息。结果表明,光谱特征指标选择BR_(4)>0.3、NDVI>0.619和DVI>0.317,可以较准确地从影像中识别出冬小麦田,并减少田间道路被误判为冬小麦田像元。在非麦田分类中,选择BR_(3)>0.15和BR_(4)>0.2,可将建筑用地与河流(沟渠)区分开。利用田间样方统计面积和遥感提取面积进行精度验证,总体精度可达97.33%,说明通过中、高空间分辨率遥感数据融合,结合多重光谱特征指标建立合理的分类阈值,可以准确提取冬小麦田及非麦田的分布信息。In order to provide accurate reference information for the construction planning of high-standard farmland and the formulation of food security production measures,based on the pre-processing of domestic GF-1/PMS satellite images with radiometric calibration,atmospheric correction,geometric correction and cropping,the point image spectral information of multiple features in high standard wheat fields was extracted through image fusion.After analyzing the spectral characteristics of different features,the spatial distribution information of high-standard wheat fields was obtained by constructing vegetation spectral feature index thresholds using band reflectance,normalized difference vegetation index(NDVI)and differential vegetation index(DVI)to classify winter wheat fields and non-wheat fields.The results showed that according to the spectral feature indicators of BR_(4)>0.3,NDVI>0.619,and DVI>0.317,winter wheat fields from the images could be identified more accurately while the image elements of field roads being misclassified as winter wheat fields was reduced.In the non-wheat field classification,according to BR_(3)>0.15 and BR_(4)>0.2,the construction land from rivers(ditches)could be distinguished.The accuracy was validated by using the statistical area of field samples and the area extracted by remote sensing,and the overall accuracy reached 97.33%,indicating that the spatial distribution information of winter wheat fields and non-wheat fields could be accurately extracted by fusing medium and high spatial resolution remote sensing data and establishing reasonable classification thresholds by combining multiple spectral feature indicators.

关 键 词:冬小麦 多光谱指标 高标准麦田 决策树分类 空间信息提取 

分 类 号:S127[农业科学—农业基础科学]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象