基于特征结构相似度的遥感影像融合质量评价指标  

Feature-based Remote Sensing Image Fusion Quality Metrics Using Structure Similarity

作　　者：刘军[1] 邵振峰[2] 

机构地区：[1]武汉大学遥感信息工程学院 [2]武汉大学测绘遥感信息工程国家重点实验室,武汉430079

出　　处：《光子学报》2011年第1期126-131,共6页Acta Photonica Sinica

基　　金：国家重点基础研究发展计划资助(No.2010CB731800);国家高技术研究发展资助(No.2009AA121404);国家自然科学基金(No.40801165和No.10978003);中央高校基本科研业务费专项(No.20082130101000046)资助

摘　　要：在分析现有影像融合评价指标的基础上,根据人眼视觉特性,提出一种基于特征结构相似度的遥感影像融合评价指标.首先从原始影像和融合影像中提取空间特征和光谱特征,然后综合计算空间特征和光谱特征的结构相似度作为评价指标,达到评价影像质量的目的.通过对多种传感器获取的遥感影像进行融合实验,结果表明该客观评价方法与主观评价结果一致,是一种有效的遥感影像融合质量评价方法.By analyzing the existing assessment of image fusion quality,according to the characteristic of human visual system,a novel remote sensing image fusion quality assessment was proposed,which was based on the feature and structure similarity.Firstly,the spatial feature and spectral feature were extracted from the fused image and the original panchromatic（PAN） and multispectrum（MS） images,then the structure similarity of the spatial feature and spectral feature were involved to calculate the assessment index,so as to achieve the evaluation of image quality.The experimental results and objective evaluations indicate that,the evaluation of the proposed assessment is consistent with the subjective evaluation,which shows that the proposed method is an objective and effective assessment for the remote sensing image fusion quality metrics.

关 键 词：结构相似度 特征结构相似度指标 遥感影像融合 质量评价 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]