基于约束非负矩阵分解的混合象元分解新方法

New Scheme for Decomposition of Mixed Pixels Based on Constrained Nonnegative Matrix Factorization

针对高光谱混合象元分解中顶点成分分析要求每一端元在图像中至少存在一个纯象元的不足,以及非负矩阵分解易受初值影响产生局部最小的问题,提出了一种高光谱遥感图像混合象元分解的新方法。该方法用顶点成分分析求得的端元和最小二乘法求得的丰度作为平滑约束非负矩阵分解方法迭代的初始值来实现混合象元分解。通过对模拟高光谱数据和真实遥感影像的仿真研究,结果表明新方法分解混合象元精度略优于顶点成分分析方法,但明显好于约束的非负矩阵分解方法。

In the decomposition of mixed pixels of hyperspectral remote sensing images,the vertex component analysis(VCA) needs that there is at least one pure pixel for every endmember existing in the images,and nonnegative matrix factorization(NMF) easily result in the problem of local minimum,owing to the influence of algorithm initializations.To solve the problems,this paper presents a new scheme based on the smooth constrained NMF(CNMF).We adopt the endmembers extracted by VCA,and abundance obtained by least squa...