基于暗通道优先和Hough变换的雾天车道线识别算法  

Lane recognition algorithm based on dark channel priority and Hough transform in haze weather

作　　者：于升源 陈乐庚[1] 蒙双 张向文[1] YU Shengyuan;CHEN Legeng;MENG Shuang;ZHANG Xiangwen(School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin 541004,China)

机构地区：[1]桂林电子科技大学电子工程与自动化学院

出　　处：《传感器与微系统》2020年第1期146-149,共4页Transducer and Microsystem Technologies

基　　金：国家自然科学基金资助项目(51465011);广西自动检测技术与仪器重点实验室基金资助项目(YQ17110)

摘　　要：针对雾天车道线无法通过常规方法识别的缺陷,提出一种改进雾天环境下车道线识别算法。采用形态学腐蚀运算对暗通道优先去雾算法做出改进并应用于选定的感兴趣区域(ROI);结合二维伽马变换和局部大津(OTSU)法得到亮度提高后的二值图;在改进极角约束Hough变换的基础上,提出了一种左右车道线分类识别的算法,实现对车辆所在车道左右两侧车道线的准确识别。实验结果表明:该算法不但能提高雾天环境下车道线识别的准确率和实时性,还对雾天行车安全具有重要的实际应用意义。In view of the defect that lane line cannot be recognized by conventional methods in haze weather,an improved lane recognition algorithm in haze environment is proposed.Dark channel priority dehazing algorithm is improved by the more efficient morphological erosion operation and applied to the selected region of interest(ROI)area.Binary images wiTHimproved brightness is obtained by combining two-dimensional Gamma transform and local OTSU algorithm.On the basis of improved polar angle Hough transform,an algorithm for classification and recognition of left and right lane lines is proposed to realize the accurate identification of the lane lines on the left and right sides of the lane where the vehicle is located.The experimental results show that the proposed algorithm can not only improve the accuracy and real-time performance of lane marking in haze weather,but also has important practical application significance for safety of driving in haze weather.

关 键 词：雾天 形态学腐蚀 暗通道优先 HOUGH变换 车道线识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]