计算机应用研究2016，Vol.33Issue(10)：3177-3180,4.DOI:10.3969/j.issn.1001-3695.2016.10.068
基于差分搜索的高光谱图像解混算法
Unmixing of hyperspectral images based on differential search
摘要
Abstract
With regard to the issues of hyperspectral unmixing,the distribution of endmembers were not completely indepen-dent in hyperspectral images,thus could not directly apply blind source separation to hyperspectral unmixing.This paper pro-posed a novel hyperspectral unmixing algorithm based on differential search.According to the abundance non-negative and a-bundance sum-to-one features,this algorithm constructed corresponding constraint terms and combined it with mutual informa-tion as an objective function,and then optimized the function through differential search algorithm to realize hyperspectral un-mixing.The experimental results on simulated and real hyperspectral data demonstrate that the proposed algorithm can effec-tively solve the problem of hyperspectral unmixing.Compared with other algorithms,it can avoid falling into local extremum and get more accurate results,and also be used to unmix hyperspectral data without pure pixels.关键词
高光谱图像解混/差分搜索算法/盲源分离/丰度非负约束/丰度和为一约束/互信息Key words
hyperspectral images unmixing/differential search algorithm/blind source separation/abundance non-negative constraint/abundance sum-to-one constraint/mutual information分类
信息技术与安全科学引用本文复制引用
张立毅,刘静光,陈雷,李锵,孙彦慧..基于差分搜索的高光谱图像解混算法[J].计算机应用研究,2016,33(10):3177-3180,4.基金项目
国家自然科学基金资助项目（61401307）；天津市应用基础与前沿技术研究计划资助项目（15JCYBJC17100）；中国博士后科学基金资助项目 （）
