山东农业科学2018，Vol.50Issue(3)：132-136,141,6.DOI:10.14083/j.issn.1001-4942.2018.03.030
基于高分辨率遥感影像的耕地信息快速提取方法研究
Farmland Information Extraction Method Based on High-Resolution Remotely-Sensed Images
摘要
Abstract
In this paper,Changping District of Beijing City was selected as research area,and its farm-land information was extracted from 2.5 -meter SPOT5 remotely-sensed images using SEaTH and CART methods on the basis of automatic access to classification rules.The results showed that the overall accuracy of the two classification methods were above 90%,and the KAPPA coefficient could reach 0.80.Compared with CART method,the leakage of farmland was decreased obviously and the classification stability was better using SEaTH method.关键词
高分辨率遥感影像/耕地/信息提取/面向对象影像分析Key words
High -resolution remotely -sensed image/Farmland/Information extraction/Object -based image analysis分类
农业科技引用本文复制引用
孙家波,张晓艳,牛鲁燕,刘延忠,刘炳福,张维战..基于高分辨率遥感影像的耕地信息快速提取方法研究[J].山东农业科学,2018,50(3):132-136,141,6.基金项目
山东省农业科学院青年科研基金项目(2015YQN47) （2015YQN47）
国家重点研发计划项目(2017YFD0301004) （2017YFD0301004）
