首页 | 本学科首页   官方微博 | 高级检索  
     

基于多时相NDVI及特征波段的作物分类研究
引用本文:马丽,徐新刚,刘良云,黄文江,贾建华,程一沛.基于多时相NDVI及特征波段的作物分类研究[J].遥感技术与应用,2008,23(5):520-524.
作者姓名:马丽  徐新刚  刘良云  黄文江  贾建华  程一沛
作者单位:(1.国家农业信息化工程技术研究中心,北京 100097;2.西安科技大学测量工程系,陕西 西安 710054;3.中国科学院对地观测与数字地球科学中心,北京 100080)
基金项目:国家高技术研究发展计划(863计划),北京市科委主题重大项目,农业部主要农作物调优栽培信息化技术项目,北京市涌泉行动项目
摘    要:时相和光谱特征信息在农作物种植分类提取方面具有十分重要的应用价值。以黑龙江大型农场--友谊农场为研究区域,利用4景不同时相的TM和SPOT卫星遥感影像,提取相应时相的NDVI时间谱图像数据作为新波段信息,在分析地物目标在相应影像各波段上光谱和时间特征的基础上,设计了决策树分类算法,通过对待分类影像进行系列阈值分割和掩膜处理,成功提取黑龙江友谊农场的大豆、玉米和水稻的种植信息,分类总体精度达到98.67%。

关 键 词:多时相  NDVI  特征波段  决策树分类  

Study on Crops Classification Based on Multi-temporal NDVI and Characteristic Bands
MA Li,XU Xin-gang,LIU Liang-yun,HUANG Wen-jiang,JIA Jian-hua,CHENG Yi-pei.Study on Crops Classification Based on Multi-temporal NDVI and Characteristic Bands[J].Remote Sensing Technology and Application,2008,23(5):520-524.
Authors:MA Li  XU Xin-gang  LIU Liang-yun  HUANG Wen-jiang  JIA Jian-hua  CHENG Yi-pei
Affiliation:(1.National Engineering Research Center for Information Technology in Agriculture,Beijing 100097,China;2.Dep.of Survey Engineering,Xi'an University of Science &Technology,Xi'an 710054,China;3.Center for Earth Observation and Digital Earth Chinese Academy of Sciences,Beijing 100080,China)
Abstract:Spectral and temporal information can improve crops classification precision greatly.In this paper,4 multi-temporal TM & SPOT images were selected on Youyi farm in Heilongjiang province.We used the NDVI as a new band information by extracting the NDVI information on the correspond time.By analyzing the spectral and time feature of the objects on each band,we designed a decision tree classified arithmetic.Finally,after series value division and mask management,the areas and distributions of dadou,yumi and shuidao were successfully remotely sensed with an overall accuracy of 98.67% .
Keywords:NDVI
本文献已被 维普 万方数据 等数据库收录!
点击此处可从《遥感技术与应用》浏览原始摘要信息
点击此处可从《遥感技术与应用》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号