复杂环境下道路边缘检测算法的研究  

Research on Road Edge Detection Algorithm in Complex Environment

作　　者：王郝 杜梦递 WANG Hao;DU Mengdi(School of Electrical Engineering,Jiangsu College of Safety Technology,Xuzhou Jiangsu 221000,China;School of Mechanical Engineering,Jiangsu University of Science and Technology,Zhenjiang,Jiangsu 212003,China)

机构地区：[1]江苏安全技术职业学院电气工程学院,江苏徐州221000 [2]江苏科技大学江苏省船海机械装备先进制造重点实验室,江苏镇江212003

出　　处：《机械设计与制造》2025年第4期331-335,共5页Machinery Design & Manufacture

基　　金：国家自然科学基金(51375230)。

摘　　要：针对复杂环境下传统算法对道路边缘检测抗干扰性差,准确率低的缺点,提出了一种在复杂环境下基于离群值过滤的道路边缘检测算法。该算法首先对原始图像进行对灰度处理,再根据道路边缘的区域信息作感兴趣区域提取并降噪,减少非边缘信息的干扰。采用Canny算子求出图像的边缘,在概率Hough变换直线检测的基础上对检测出的直线作分类处理,并根据设定的阈值对分类后的直线进行筛选。结果表明,本算法检测出的直线数量平均每帧比传统算法减少约50%,不同道路场景下的平均识别准确率为94.33%,具有较好的抗噪性、鲁棒性与检测精度。Aiming at the disadvantages of poor anti-interference and low accuracy of traditional algorithms for road edge detec⁃tion in complex environment,a road edge detection algorithm based on outlier filtering in complex environment is proposed.The algorithm first processes the gray level of the original image,and then extracts the region of interest,binarization and morpholog⁃ical filtering according to the regional information of road edge.Reduce the interference of non edge information in the process of edge extraction.Then Canny operator is used to get the edge of the image.Finally,based on the line detection of probabilistic Hough transform,the detected lines are classified,the classified lines are filtered according to the set threshold,and the filtered lines are fitted according to the endpoint information.Experimental results show that the proposed algorithm can effectively im⁃prove the anti-interference and accuracy of road edge detection,and has better robustness.

关 键 词：边缘检测 概率Hought变换 离群值过滤 

分 类 号：TH16[机械工程—机械制造及自动化] TP391[自动化与计算机技术—计算机应用技术]