深圳大学学报（理工版）2009，Vol.26Issue(3)：262-267,6.
基于光谱和空间特性的高光谱解混方法
Spectral and spatial character-based hyperspectral unmixing
摘要
Abstract
To represent the spectral and spatial character of hyperspectral data,by introducing the smoothness constraint of hyperspectral data and the sparseness constraint of spatial distribution of the materials,an improved nonnegative matrix factorization(INMF)was used for hyperspectral unmixing.Its monotonic convergence is guaranteed by using a gradient-based optimization algorithm.Experiments demonstrate that the INMF algorithm is yielding accurate estimation of both endmember spectra and abundance maps.关键词
高光谱解混/混合像元/线性光谱混合模型/非负矩阵分解/盲源分离Key words
hyperspectral unmixing/mixing pixel/linear spectral mixing model/nonnegative matrix factorization/blind source separation分类
信息技术与安全科学引用本文复制引用
贾森,钱沄涛,纪震,沈琳琳..基于光谱和空间特性的高光谱解混方法[J].深圳大学学报（理工版）,2009,26(3):262-267,6.基金项目
国家自然科学基金资助项目(60872071) （60872071）
广东省自然科学基金博士:启动资助项目(9451806001002287) （9451806001002287）
