基于像元混合模型估计的高光谱图像解混  

Hyperspectral Unmixing Based on Estimation of Pixels Mixing Models

作　　者：陈雷[1,2,3] 刘静光 张立毅[2,3] 李锵[2] 孙彦慧[2] 

机构地区：[1]天津大学精密仪器与光电子工程学院,天津300072 [2]天津大学电子信息工程学院,天津300072 [3]天津商业大学信息工程学院,天津300134

出　　处：《红外技术》2016年第2期132-137,共6页Infrared Technology

基　　金：国家自然科学基金资助项目(61401307);中国博士后科学基金资助项目(2014M561184);天津市应用基础与前沿技术研究计划资助项目(15JCYBJC17100)

摘　　要：在高光谱图像中,线性混合像元和非线性混合像元同时存在,若采用基于单一混合模型的解混算法,会使解混精度降低。因此,提出采用神经网络对高光谱图像中的像元混合模型进行估计,然后针对不同的混合模型进行相应的像元解混。像元解混时,在目标函数中添加丰度非负和丰度和为一约束项,利用差分搜索算法优化求解目标函数以实现高光谱图像的解混。仿真和实际高光谱数据实验表明,本算法提高了解混精度,适用于线性和非线性混合模型。Both linear and nonlinear mixing pixels exist in the hyperspectral images. The unmixing accuracy will decrease if the unmixing algorithm is only based on a single mixing model. In this paper, we propose to adopt neural network to estimate the pixels mixing model in the hyperspectral images, and then unmix the pixels under different mixing models. To achieve the hyperspectral unmixing, we introduce the abundance non-negative constraint and abundance sum-to-one constraint to the objective function, and then the differential search algorithm is used to optimize the objective function. The experimental results on simulated data and real hyperspectral data demonstrate that the proposed algorithm can improve the accuracy of the unmixing, and it can be applied to linear and nonlinear mixing models.

关 键 词：高光谱图像解混 神经网络 像元混合模型 差分搜索算法 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]