摘要
针对图片去雾算法应用于视频图像处理时存在的实时性差和去雾效果不好等问题,提出了一种雾天交通视频的优化去雾算法。该算法首先识别出运动目标,仅针对选中的运动目标进行去雾,可有效提高去雾的效率和实时性。利用视频图像中运动物体前后帧关联的特点,在传统暗原色先验去雾算法的基础上,对图像进行重构。实验结果表明,该算法不仅可以提高视频图像的去雾效率和实时性,而且还可明显增强运动目标的去雾效果和清晰度,为运动目标信息提取奠定基础。
Aiming at the problems of image defogging algorithm applied to video image processing,such as poor real-time performance and poor defogging effect,this paper proposes an optimized defogging algorithm for foggy traffic video. The algorithm first recognizes the moving target and defogges only the selected moving target,which can effectively improve the efficiency and real-time of the defogging. Based on the characteristics of the frame association before and after the moving object in the video image,the image is reconstructed based on the traditional dark primary color prior defogging algorithm. The experimental results show that the proposed algorithm can not only improve the defogging efficiency and real-time performance of video images,but also significantly enhance the defogging effect and clarity of moving targets,and lay a foundation for the extraction of moving target information.
作者
王一璇
黎英
Wang Yixuan;Li Ying(Information Engineering and Automation School,Kunming University of Science and Technology,Kunming 650000,China)
出处
《电子测量技术》
2019年第12期118-121,共4页
Electronic Measurement Technology
关键词
交通监控视频
目标检测
去雾
图像配准
traffic surveillance video
target detection
defogging
image registration
