基于视觉显著性加权与梯度奇异值最大的红外与可见光图像融合  

Fusion of infrared and visible light images based on visual saliency weighting and maximum gradient singular value

作　　者：程博阳 李婷[1] 王喻林 CHENG Bo-yang;LI Ting;WANG Yu-lin(Institute of Remote Sensing Satellite,China Academy of Space Technology,Beijing 100094,China)

机构地区：[1]中国空间技术研究院遥感卫星总体部,北京100094

出　　处：《中国光学（中英文）》2022年第4期675-688,共14页Chinese Optics

基　　金：国家重大航天工程。

摘　　要：为了综合利用红外与可见光图像的光谱显著性信息,同时提高融合图像的视觉对比度,本文提出了一种基于视觉显著性加权与梯度奇异值最大的红外与可见光图像融合方法。首先,该全新算法通过滚动引导剪切波变换作为多尺度分析工具,来获取图像的近似层分量与多方向细节层分量。其次,针对反映图像主体能量特征的近似层分量,采用视觉显著性加权融合作为其融合规则,该方法利用显著性加权系数矩阵指导图像内的光谱显著性信息有效融合,提高了融合图像的视觉观察度。此外,采用基于梯度奇异值最大原则来指导细节层分量的融合,该方法可以极大程度地将隐藏在两种源图像内的梯度特征还原到融合图像中,使融合图像具有更加清晰的边缘细节。为了验证本文算法的有效性,进行了5组独立的融合实验,最终的实验结果表明,本文算法融合图像的对比度更高,边缘细节更加丰富,并且相较于其它现有典型方法,AVG、IE、Q^(E)、SF、SD、SCD等客观参数指标分别提高了16.4%、3.9%、11.8%、17.1%、21.4%、10.1%,因此具有更加优良的视觉效果。In order to effectively integrate the spectral saliency information of infrared and visible light images and improve the visual contrast of the fused images,a fusion method of infrared and visible light images based on weighted visual saliency and maximum gradient singular value is proposed in this paper.Firstly,the new algorithm uses the rolling guidance shearlet transform as a multi-scale analysis tool to obtain the approximate layer components and multi-directional detail layer components of the image.Secondly,for the approximate layer components that reflect the energy characteristics of the image subject,visual saliency weighted fusion is used as its fusion rule.This method uses the saliency weighted coefficient matrix to guide the effective fusion of spectral saliency information in the image,and improves the visual observation of the fused image.In addition,the principle of maximum gradient singular value is used to guide the fusion of detail layer components.This method can restore the gradient features hidden in the two source images to the fused image to a great extent,so that the fused image has clearer edge details.In order to verify the effectiveness of this algorithm,we have adopted five groups of independent fusion experiments.The final experimental results show that this algorithm has higher contrast and richer edge details.Compared with the existing typical methods,the objective parameters such as AVG,IE,Q^(E),SF,SD and SCD are improved by 16.4%,3.9%,11.8%,17.1%,21.4%and 10.1%,respectively,so it has better visual effect.

关 键 词：图像融合 滚动引导剪切波变换 显著性加权 梯度奇异值 

分 类 号：TP394.1[自动化与计算机技术—计算机应用技术] TH691.9[自动化与计算机技术—计算机科学与技术]