通信与信息技术Issue(4)：13-17,5.
基于改进MSR理论的夜间图像增强算法研究
Research on night image enhancement algorithm based on improved MSR theory
摘要
Abstract
In order to solve the problems of loss of image detail,dimming of brightness and color distortion caused by the processing results of the traditional Retinex algorithm in night images,a night image enhancement algorithm based on the improved MSR(Multi-Scale Retinex)theory was proposed.Firstly,the image is converted to HSV space,the Gaussian filter in the traditional MSR algorithm is changed to multiple window gradient guided filtering,and multiple windows are used to estimate the illuminance component of the V channel independently,and then the illuminance component of V is fused with the image.The reflection component of the fused image is obtained according to the MSR theory,and then the reflection component is guided by gradient domain filtering and denoising.Finally,adaptive Gamma correction is performed to output an enhanced image.Experimental results show that,compared with the dark channel prior theory and the traditional multi-scale retina algorithm,the proposed algorithm in this paper has improved the standard deviation,mean gradient,peak signal-to-noise ratio and structural similarity,and the image quality of low-light at night has been effectively en-hanced,which is of great significance for improving the efficiency of night driving in low-light environment.关键词
Retinex算法/MSR增强算法/HSV空间/多个窗口梯度引导滤波/伽马校正Key words
Retinex algorithm/Multi-scale Retinex enhancement algorithm/HSV space/Multi-scale gradient domain guided filter-ing/Gamma correction分类
信息技术与安全科学引用本文复制引用
徐冰倩,和晓军..基于改进MSR理论的夜间图像增强算法研究[J].通信与信息技术,2025,(4):13-17,5.基金项目
国家自然科学基金项目(项目编号:12202285) （项目编号:12202285）
辽宁省教育厅高等学校基本科研项目(项目编号:JYTMS20230207 （）
项目编号:JYTMS20230182) （）
