两种基于空间相关性的遥感亚像元分类制图方法对比分析  

Comparative Analysis between Two Sub-pixel Mapping Methods based on Spatial Correlation Characteristics

作　　者：陈跃红[1,2] 葛咏[1] 

机构地区：[1]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,北京100101 [2]中国科学院研究生院,北京100049

出　　处：《遥感技术与应用》2012年第5期686-691,共6页Remote Sensing Technology and Application

基　　金：国家自然科学基金项目(40971222);中国科学院地理科学与资源研究所自主部署创新项目(201003009)资助

摘　　要：为了对比基于Hopfield Neural Network(HNN)和几何绘图的遥感亚像元分类制图方法的具体性能,验证空间相关性原理用于遥感亚像元定位的可行性。以一个研究区的TM影像为对象,通过利用HNN和几何亚像元制图方法,获得该区的亚像元定位结果,对比分析了各方法的视觉效果、精度和时间复杂度。结果表明:空间相关性特性在两种方法中得到了良好的体现,为后续亚像元制图研究应用提供参考。Compared two sub-pixel mapping methods which are based on the spatial correlation characteris- tics. One method is based on Hopfield Neural Network（HNN） and the other is based on geometric theory. A study with TM imagery data is employed to evaluate the performance measured by accuracy, visual effects and time consuming on the two methods. The comparisons illustrate that the availability of the spa- tial correlation incorporated into the two means is perfecteiy expressed in the results, and five conclusions are provided for the sequential researches of sub-pixel mapping as well.

关 键 词：遥感 亚像元 分类 HNN 几何绘图 对比 

分 类 号：TP75[自动化与计算机技术—检测技术与自动化装置]