基于图像欧氏距离流形降维的端元提取算法

Image Euclidean Distance-based Manifold Dimensionality Reduction for Endmember Extraction

由于多重反射和散射,高光谱图像中的混合像元实际上是非线性光谱混合传统的端元提取算法是以线性光谱混合模型为基础,因此提取精度不高针对高光谱图像的非线性结构.本文提出了基于图像欧氏距离非线性降维的高光谱遥感图像端元提取方法该方法结合高光谱数据的物理特性,将图像欧氏距离引入局部切空间排列进行非线性降维以更好的去除高光谱数据集中冗余的空间信息和光谱维度信息,然后对降维后的数据利用寻找最大单形体体积的方法提取端元.真实高光谱数据实验表明,提出方法对高光谱图像端元提取具有良好的效果,性能优于线性降维的主成分分析算法和原始的局部切空间排列算法.

Mixed pixel in hyperspectral image is actually nonlinear mixing of endmembers,which is caused by multiple reflectance and scattering.Since traditional endmember extraction algorithms are based on linear spectral mixture model,they perform poorly in finding the correct endmembers.Considering the physical characters of hyperspectral imagery,a new method is proposed to introduce image Euclidean distance into local tangent space alignment for nonlinear dimension reduction.The proposed methods can discard efficiently the redundant information from both the spectral and spatial dimensions.Endmembers are extracted by looking for the largest simplex volume from low-dimensional space.The experimental results of real image scenes demonstrated that the method outperformed the PCA and LTSA algorithm.