| 基于光谱和空间特性的高光谱解混方法 |
| |
| 引用本文： | 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). |
| |
| 作者姓名： | 贾森 钱沄涛 纪震 沈琳琳 |
| |
| 作者单位： | 1. 深圳大学德州仪器DSPs实验室,深圳大学计算机与软件学院,深圳,518060
2. 浙江大学计算机学院,杭州,310027 |
| |
| 基金项目： | 国家自然科学基金，广东省自然科学基金 |
| |
| 摘 要： | 为表征高光谱数据的光谱和空间特性,引入光谱的平滑性和地物空间分布的稀疏性约束,提出非负矩阵分解的改进算法,将其应用于高光谱解混.尺度可变的梯度下降算法保证了改进算法的收敛性.实验结果表明,改进后的非负矩阵分解算法能给出地物光谱,并精确估计其分布.
|
| 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 |
Spectral and spatial character-based hyperspectral unmixing |
| |
| JIA Sen,QIAN Yun-tao,JI Zhen,SHEN Lin-lin.Spectral and spatial character-based hyperspectral unmixing[J].Journal of Shenzhen University(Science &engineering),2009,26(3). |
| |
| Authors: | JIA Sen QIAN Yun-tao JI Zhen SHEN Lin-lin |
| |
| 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. |
| |
| Keywords: | hyperspectral unmixing mixing pixel linear spectral mixing model nonnegative matrix factorization blind source separation |
| 本文献已被 万方数据 等数据库收录！ |
|
