基于优化MSR的夜间道路图像增强方法  

Night road image enhancement method based on optimized MSR

作　　者：刘富[1,2] 刘璐 侯涛[2] 刘云[2] LIU Fu;LIU Lu;HOU Tao;LIU Yun(State Key Laboratory of Automotive Simulation and Control,Jilin University,Changchun 130022,China;College of Communication Engineering,Jilin University,Changchun 130022,China)

机构地区：[1]吉林大学汽车仿真与控制国家重点实验室,长春130022 [2]吉林大学通信工程学院,长春130022

出　　处：《吉林大学学报（工学版）》2021年第1期323-330,共8页Journal of Jilin University:Engineering and Technology Edition

基　　金：国家自然科学基金重点项目(51835006);中国博士后科学基金项目(2019M651204)。

摘　　要：为了提高夜间道路图像质量,提升目标在图像中的可见度及对比度,降低夜间道路图像目标检测难度,提出了一种基于优化多尺度Retinex算法(MSR)的夜间道路图像增强方法。首先,将RGB图像转换到YUV色彩空间;其次,将最小可觉差(JND)的倒数作为MSR算法中入射图像的系数构建优化MSR算法,并利用该优化算法对Y通道进行亮度自适应调节,同时对U、V通道按比例调整得到新图像;然后,将得到的新图像与原始图像按照1:1比例结合以保留图像细节;最后,利用限制对比度自适应直方图均衡化方法(CLAHE)提升图像对比度,得到最终增强图像。在包含有770张夜间道路图像的数据集上开展实验,结果表明:本文方法实现了夜间道路图像亮度自适应调节,缓解了图像亮度不均匀的情况,增强了图像的清晰度,增加了图像的细节信息,利用支持向量机算法(SVM)进行前方车辆检测,漏检率、误检率分别下降了2.61%、4.35%。In order to improve the image quality of night roads,to promote the visibility and contrast of the target in the image,and to reduce the difficulty of target detection in night road image,a night road image enhancement method based on the optimized Multi-scale Retinex(Multi scale retinex,MSR)algorithm is proposed in this paper. First,the Red,Green and Blue(RGB)image is converted to the YUV color space.Secondly,the optimized MSR algorithm is constructed by using the reciprocal of the Just Noticeable Distortion(Just noticeable distortion,JND) as the coefficient before the incident image in the MSR algorithm,which is used to adjust the brightness of the channel Y adaptively. Meanwhile,the channels of U and V are proportionally adjusted to obtain a new image,which is then combined with the original image in a 1∶1 ratio to preserve the image details. Finally,the Contrast-limited Adaptive Histogram Equalization method(CLAHE)is used to improve image contrast. Experiments on datasets containing 770 images of night road show that the proposed method exhibits the ability to adaptive adjustment of night image brightness,alleviate uneven brightness of the image,enhance the sharpness of nighttime images and the detail information of image. By using the support vector machine algorithm to detect vehicles in image,the missed detection rate and false detection rate are decreased by 2.61% and 4.35%,respectively..

关 键 词：模式识别与智能系统 图像处理 夜间图像增强 优化MSR算法 亮度自适应调节 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]