基于改进暗通道算法的雾天车辆偏离预警研究  

Research of vehicle departure alarm in fog weather based on improved dark channel prior algorithm

作　　者：周劲草[1] 魏朗[1] 张在吉 ZHOU Jin-cao WEI Lang ZHANG Zai-ji(College of Automobile,Chang＇an University, Xi＇an 710064, China Tianjin Key Lab For Advanced Signal Processing,Civil Aviation University of China,Tianjin 300300,China)

机构地区：[1]长安大学汽车学院,陕西西安710064 [2]中国民航大学智能信号与图像处理重点实验室,天津300300

出　　处：《东北师大学报（自然科学版）》2017年第1期62-67,共6页Journal of Northeast Normal University(Natural Science Edition)

基　　金：国家自然科学基金资助项目(51278062)

摘　　要：针对在雾天工况下仅凭常规车道线识别方法无法准确提取车道线这一现状,给出了一种基于改进暗通道算法的雾天车道线识别算法.首先利用基于双边滤波器的暗通道算法对雾天工况下的图片进行去雾并对去雾图像进行亮度修正;然后利用Sobel算子和大津法得到包含清晰道路边缘的二值化图像;最后利用Hough变换对车道线精确提取.实验表明:该算法能够在雾天工况下对车道线进行准确、快速地识别;与常规算法相比,该算法具有更高的准确性和实时性,对于提高雾天车辆主动安全性具有较大意义.In this paper,a new algorithm based on dark channel prior was proposed for lane detection in fog weather which couldn＇t be detected by traditional algorithm. Firstly, the lane images in fog weather was defogged by improved dark channel prior based on gauss bilateral filter and then luminosity of defogged pictures were adjusted. Secondly,binary images of road edges was obtained by Sobel operator and Ostu algorithm. Finally, the road lane was extracted by Hough transform. Experimental results showed this new algorithm could detect road lane in fog weather accurately and rapidly. Compared with traditional lane detection method, this new algorithm has higher accuracy and instantaneity thus has great influence on the improvement of automobile active safety in fog weather.

关 键 词：车辆主动安全性 雾天 双边滤波 车道偏离预警 图像去雾 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]