摘要
针对传统显著性检测融合方法中目标对比度低,纹理细节不够丰富的问题,提出了一种基于滚动导向滤波(RGF)改进显著性检测与脉冲发放皮层模型(SCM)相结合的可见光与红外图像融合算法。该算法先将源图像经过非下采样剪切波变换(NSST)分解成低频部分和高频部分,然后利用RGF小尺度消除、大尺度边缘恢复特性对Frequency Tuned算法进行改进并提取出红外图像显著图。再使用显著图投影区域指导法融合低频部分,同时采用SCM结合区域能量与改进的拉普拉斯能量和融合高频部分,最后使用逆变换重建图像。仿真结果表明,该算法能在突出显著目标的同时保留丰富的细节信息,在质量指标如标准差、互信息、边缘保留因子等方面均优于对比方法。
In order to solve the problems of low contrast and insufficient texture detail in the traditional saliency detection fusion methods,a visible and infrared image fusion algorithm based on rolling guidance filter(RGF)improved saliency detection combined with spiking cortical model(SCM)is proposed.First,the original image is decomposed into low-frequency and high-frequency by nonsubsampled shearlet transform(NSST).Then,the frequency tuned algorithm is improved by using RGF′s small-scale elimination and large-scale edge recovery properties,and the salient image of the infrared image is extracted.The low-frequency part is fused using saliency map projection region guidance method,and the high-frequency part is fused with SCM combining region energy and Sum-Modified Laplacian,and finally,the image is reconstructed by inverse transformation.The simulation results show that the proposed algorithm can highlight significant targets while retaining abundant details,and is superior to the comparison method in terms of quality indicators such as standard deviation,mutual information and edge retention factor.
作者
巩稼民
吴成超
郭刘飞
刘威
裴梦杰
卢姣姣
高睿杰
GONG Jia-min;WU Cheng-chao;GUO Liu-fei;LIU Wei;PEI Meng-jie;LU Jiao-jiao;GAO Rui-jie(School of Communication and Information Engineering,Xi′an University of Posts and Telecommunications,Xi′an 710121,China)
出处
《激光与红外》
CAS
CSCD
北大核心
2022年第8期1251-1258,共8页
Laser & Infrared
基金
国家自然科学基金项目(No.61775180)
国际科技合作计划项目陕西省重点研发计划项目(No.2020KWZ-017)资助。
