摘要
提出一种有GIS数据辅助的以像斑为对象基于不同时相非同源的遥感影像变化检测方法,这种方法属于特征级的变化检测,以影像像斑为对象,突破了以往变化检测对数据的要求与限制,改变了传统检测方法对于遥感影像数据的要求同源的模式。通过土地利用图和遥感影像的精确配准套合获取影像像斑,再利用聚类算法按类别进行样本的更新,利用更新后的样本来进行基于非同源遥感影像的土地利用变化检测。应用基于像斑的非同源影像的变化检测方法对武汉市某区域的QuickBird和彩红外航空影像数据进行了实验,并针对坑塘变化及其居民点变化进行了分析,精度分别为80%和75%。
Based on the analysis and summarizations of researched home and aboard,the dissertation focused on land use\cover detection using disparate images on land use segment,which belongs to 'Feature class' of LUCC.It should be pointed out that the researches must be focus the disparate remote-sensed imagery other than traditional methods of the same kind remote-sensed imagery.The land use span was expressed by vector polygon along with raster region.First getting the sample of this type of land use classes,then detect changes based on segment and feature database.The method was tested on QuickBird images and infra-red color aerial photograph of adistrict in Wuhan and the precision is high as 75%(in urbanization)and 80%(in loss of stew).
出处
《地理空间信息》
2011年第1期75-78,12,共4页
Geospatial Information
基金
湖北省自然科学基金资助项目(2006ABD003)
关键词
变化检测
土地利用
非同源遥感影像
像斑
GIS
change detection,land use,disparate remotely sensed imageries,feature selection,GIS
