基于GF-1影像的冬小麦和油菜种植信息提取

发布时间：2018-05-15 07:10

  本文选题：GF- + 农作物种植信息　； 参考：《遥感技术与应用》2017年04期

【摘要】：高分(GF)系列卫星的相继发射为国产高分辨率遥感数据的应用创造了新的机遇。为探索GF数据在中小尺度农作物遥感监测领域中的可行性和建立相适应的技术体系,以扬州市为例,运用决策树模型和面向对象分类方法,研究GF-1卫星的宽视场(wide field of view,WFV)数据在农作物种植信息提取中的可行性,并探索提高其提取精度的处理方法。结果表明:分区处理可以降低作物空间分布对种植区提取的不利影响;冬小麦总体精度为97%,Kappa系数为0.93;油菜总体精度为96%,Kappa系数为0.84。综上所述,国产GF-1 WFV影像可以应用于农作物种植信息的提取,并为粮区农作物种植空间调整和优化管理提供重要参考和决策支持。
[Abstract]:The successive launches of the GFG series of satellites have created a new opportunity for the application of domestic high resolution remote sensing data. In order to explore the feasibility of GF data in the field of remote sensing monitoring of small and medium scale crops and to establish a suitable technical system, taking Yangzhou City as an example, the decision tree model and object oriented classification method are used. This paper studies the feasibility of wide field of GF-1 satellite data in crop planting information extraction, and explores the processing methods to improve the precision of crop planting information extraction. The results showed that the subzone treatment could reduce the adverse effect of crop spatial distribution on the extraction of crops in growing area, the total precision of winter wheat was 97 kappa coefficient was 0.93, and the total precision of rapeseed was 96% Kappa coefficient was 0.84. To sum up, domestic GF-1 WFV images can be used to extract crop planting information, and provide important reference and decision support for crop planting space adjustment and optimal management in grain areas.
【作者单位】： 福建师范大学地理科学学院;中国科学院地理科学与资源研究所资源与环境信息系统国家重点实验室;扬州市耕地质量保护站;
【基金】：国家重大科技专项项目“新能源评估研究示范”课题(30-Y30B13-9003-14/16-04) 国家自然科学基金项目(41571158)
【分类号】：S512.11;S565.4;TP79
，

本文编号：1891492