摘要
混合像元是遥感领域研究的热点,而基于线性混合模型的光谱解混合技术正在越来越广泛地应用在光谱数据分析和遥感地物量化中,这项技术的关键就在于确定端元光谱。本文归纳了目前几种比较成熟的端元提取算法,分析了它们的主要思想和存在的优缺点,最后介绍了端元提取技术的应用及其发展趋势。
Mixed-pixel is a hot spot in the domain of remote sensing.Spectral unmixing techniques based on the linear mixing model are widely used for hyperspectral data analysis.The identification of the purest spectral signatures of ground constituents(end- member)in a scene is a previous step in all unmixing approaches.Several different algorithms for extracting endmembers are derived from the linear mixing model,the main ideas of these methods,as well as the advantages and disadvantages are presented and dis- cuss...
出处
《测绘科学》
CSCD
北大核心
2008年第S1期49-51,共3页
Science of Surveying and Mapping
基金
辽宁省高等学校重点实验室项目"基于采矿对环境影响特征知识库的遥感监测研究"(编号:20060370)
辽宁省教育厅创新团队项目"基于RS与GIS的矿区地表灾害监测与信息管理研究"(编号:2007T073)
关键词
混合像元
线性混合模型
端元提取
mixed-pixel
the linear mixing model
Endmember extraction