摘要
在高光谱遥感图像中,地物的空间分布往往呈现两种特征:一是都有各自的主导区域;二是在地表空间上分布连续.利用这两种先验信息,分别引入了对丰度的正交约束与平滑约束,提出了一种基于丰度约束的非负矩阵分解算法.为进一步地提高算法的性能,另外还提出了一种新的算法停止准则及权重因子调整策略,以适应信噪比以及像元混合程度的变化.在仿真数据和实测数据上的实验结果表明,该算法不仅能很好地表征地物的分布特征,提高解混精度,而且在信噪比较低,无纯像元的条件下,仍然能得到较好的解混结果.
In hyperspectral remote sensing imagery, material usually present two spatial distribution characteristics: one is its dominance in some special areas, another is its consistency on the land surface. By utilizing this two prior informa- tion, we propose an algorithm named nonnegative matrix factorization (NMF) with abundance constraint, which intro- duces both orthogonality and smoothness into abundance. To further improve the algorithm performance, we also pro- pose a new stop criterion and an adjusting method of adapting weight factor to the varying signal-to-noise (SNR) and mixing degree. Experimental results based on synthetic and real hyperspectral data show that our algorithm not only re- presents material distribution characteristics very well, but also increases the unmixing accuracy. Meanwhile, the algo- rithm can lead to satisfactory unmixin results under the conditions of low SNR and no oure ~ixels.
出处
《红外与毫米波学报》
SCIE
EI
CAS
CSCD
北大核心
2014年第5期560-570,共11页
Journal of Infrared and Millimeter Waves
基金
国家自然科学基金资助项目(41201363)~~
关键词
高光谱遥感
光谱解混
非负矩阵分解
正交约束
平滑约束
hyperspectral remote sensing, spectral unmixing, nonnegative matrix factorization, orthogonality constraint,smoothness constraint