摘要
分析了几种常见的变化检测算法的鲁棒性,在此基础上提出一种光谱量值和形状优化组合的地表覆盖变化检测方法。以西安市及其周边为研究区域,分析该区域2000～2009年的地表覆盖变化。变化检测的总体精度为92.313%,Kappa系数为0.844,优于其他传统算法。
We propose a new change detection approach based on value and shape optimized combination by analyzing robustness of several traditional change detection algorithms. It was tested in Xi^an City of Shaanxi Province to analyze land cover change from 2000 to 2009. The overall accuracy and Kappa coefficient of change detection result are 92. 313% and 0. 844 respectively, which outperform other methods.
出处
《武汉大学学报（信息科学版）》
EI
CSCD
北大核心
2013年第6期669-673,共5页
Geomatics and Information Science of Wuhan University
基金
国家科技支撑计划资助项目(2012BAK12B02)
国家自然科学基金资助项目(41101442)
关键词
变化检测
光谱量值
光谱形状
优化组合
鲁棒性分析
change detection
spectral value spectral shape optimized combination robust-ness analysis
