高速公路能见度估计算法  

Visibility Estimation Algorithm of Highway Visibility

作　　者：祁媛 王梅 QI Yuan;WANG Mei(School of Mechanical Engineering,Nantong Vocational University,Nantong,Jiangsu 226000,China;School of Internet of Things and Artificial Intelligence,Wuxi Vocational College of Science and Technology,Wuxi,Jiangsu 214000,China)

机构地区：[1]南通职业大学机械工程学院,江苏南通226000 [2]无锡科技职业学院物联网与人工智能学院,江苏无锡214000

出　　处：《自动化应用》2024年第22期133-136,共4页Automation Application

基　　金：南通职业大学自然科学研究项目(21ZK05)。

摘　　要：雾天的高速公路只有模糊的监控图像,没有真实的能见度数据,为此,建立了不依赖能见度仪观测数据的能见度估计算法。首先,该算法计算图片的亮度差,并对其进行区域分割得到雾气最浓区域,使用局部熵法估计大气光强度值;其次,基于暗原色先验理论求解透射率,并采用双边滤波法进行细化;再次,采用Canny算子检测车道线边缘,得到车道线两端位置细化后的大气透射率;然后,利用车道线两端透射率计算衰减系数;最后,根据能见度测量基本方程估算得出能见度值MOR。通过实验结果验证了该算法的可行性,为交管部门提供了有效的数据支持,进而提高了在恶劣天气下驾车的安全性。On foggy highways,there are only blurry surveillance images and no real visibility data.Therefore,a visibility estimation algorithm that does not rely on visibility meter observation data has been established.This algorithm first calculates the brightness difference of the image,performs region segmentation to obtain the most foggy area,and uses local entropy method to estimate the atmospheric light intensity value.Secondly,based on the prior theory of dark primary colors,the transmittance is calculated and refined using the bilateral filtering method.Next,the Canny operator is used to detect the edge of the lane line and obtain the atmospheric transmittance after refining the positions at both ends of the lane line.Then,the attenuation coefficient is calculated using the transmittance at both ends of the lane line,and the visibility value MOR is estimated based on the basic equation of visibility measurement.The feasibility of the algorithm has been verified through experimental results,providing effective data support for traffic management departments and improving the safety of driving in adverse weather conditions.

关 键 词：高速公路 暗原色先验理论 透射率 衰减系数 CANNY算子 

分 类 号：U495[交通运输工程—交通运输规划与管理]