海面舰船场景的视频图像海雾去除算法  

Video image defogging algorithm for surface ship scenes

作　　者：马忠丽[1] 文杰[1] 郝亮亮[1] 

机构地区：[1]哈尔滨工程大学自动化学院,黑龙江哈尔滨150001

出　　处：《系统工程与电子技术》2014年第9期1860-1867,共8页Systems Engineering and Electronics

基　　金：国家自然科学基金(51109047);黑龙江省博士后基金项目(Ibhq10140)资助课题

摘　　要：为满足海面舰船视频图像海雾去除的实时性要求,提出一种基于引导滤波的快速视频图像海雾去除方法。针对单幅图像,根据经典大气散射物理模型,首先利用暗原色先验估计大气光值和初始透射率,然后利用引导滤波优化透射率,进而求解大气散射物理模型,实现快速去雾;针对视频图像,结合帧差法和引导滤波,利用引导滤波估计视频帧序列的雾气遮罩,实现快速去雾。与其他单幅图像和逐帧视频图像去雾算法分别进行实验仿真对比研究,从主观和客观两方面进行处理结果的图像质量评价。结果表明,所提算法能实现快速海雾去除、有效提高视频去雾效率。In order to realize real-time surface vessels’video image sea-fog removal,a fast video image sea-fog removal method based on guided filtering is proposed.For a single image,according to the classical atmos-pheric scattering physical model,the dark channel prior is used to estimate atmospheric light and initial trans-mittance.Then the transmittance is optimized by guided filtering,and fast defogging is obtained by solving the atmospheric scattering physical model.For video images,the frame difference method and guided filtering are combined,and fast video defogging is realized by using guided filtering to estimate fog mask of video frames. Compared with other single image and frame by frame video image defogging algorithm from subjective and ob-jective image quality evaluation,the simulation experimental results show that the proposed algorithm can real-ize fast single sea-fog defogging,and improve the efficiency of video defogging.

关 键 词：引导滤波 海雾去除 大气散射物理模型 帧差法 视频去雾 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]