| 基于线性光谱混合模型的光谱解混改进模型 |
| |
| 引用本文： | 王立国.基于线性光谱混合模型的光谱解混改进模型[J].光电子．激光,2010(8):1222-1226. |
| |
| 作者姓名： | 王立国 |
| |
| 作者单位： | 哈尔滨工程大学信息与通信工程学院; |
| |
| 基金项目： | 国家自然科学基金资助项目(60802059); 教育部博士点新教师基金资助项目(200802171003); 水下机器人国防重点实验室开放课题基金联合资助项目 |
| |
| 摘 要： | 传统的基于线性光谱混合模型(LSMM)的解混方法采用迭代求解方式,复杂度较高,为此提出一种基于几何方式的模型求解方法。另一方面,LSMM采用固定谱形固定数量的光谱端元进行解混,影响了光谱解混精度,为此提出端元谱形的区域修正方法和端元子集的局域确定方法,从而建立基于柔性端元的新解混方式。实验表明了所提出的几何求解方法及柔性光谱端元方式的有效性。
|
| 关 键 词： | 高光谱图像(HSI) 光谱解混 线性光谱混合模型(LSMM) 几何求解 柔性光谱端元 |
An improved spectral unmixing modeling based on linear spectral mixing modeling |
| |
| WANG Li-guo.An improved spectral unmixing modeling based on linear spectral mixing modeling[J].Journal of Optoelectronics·laser,2010(8):1222-1226. |
| |
| Authors: | WANG Li-guo |
| |
| Affiliation: | WANG Li-guo,ZHANG Jing(College of Information and Communications Engineering,Harbin Engineering University,Harbin 150001,China) |
| |
| Abstract: | Spectral unmixing is one of the important techniques of hyperspectral imagery processing.Traditional spectral unmixing method based on linear spectral mixing modeling(LSMM) is solved in terms of iteration manner,which suffers a heavy computational burden.In this case,a geometric solving method is proposed for LSMM instead of the iteration manner.Additionally,fixed number and fixed shape of endmembers are used in LSMM,leading to a discount unmixing accuracy.Aiming at this problem and constructing a new spect... |
| |
| Keywords: | hyperspectral imagery(HSI) spectral unmixing linear spectral mixing modeling(LSMM) geometric solving flexible endmembers |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《光电子．激光》浏览原始摘要信息 |
|
点击此处可从《光电子．激光》下载全文 |
