基于改进Hough变换和斜率特征的车道线识别  

Lane line recognition based on improved Hough transformation and slope feature

作　　者：周发华 陈继清[2] 杨蓉[2] ZHOU Fahua;CHEN Jiqing;YANG Rong(School of Intelligent Manufacturing,Nanning Collegefor Vocational Technology,Nanning 530008,China;College of Mechatronic Engineering,Guangxi University,Nanning 530007,China)

机构地区：[1]南宁职业技术学院智能制造学院,广西南宁530008 [2]广西大学机械工程学院,广西南宁530007

出　　处：《现代电子技术》2023年第7期180-186,共7页Modern Electronics Technique

基　　金：国家自然科学基金项目(62163005);广西高校中青年教师科研基础能力提升项目(2021KY1015)。

摘　　要：针对干扰条件下结构化道路车道线检测识别率不高的问题,在车道线的成像特点和斜率特征的基础上,提出一种改进Hough变换的车道线检测方法。首先,用Canny边缘检测方法识别出所有车道线的边缘,确定目标车道线所在的区域为感兴趣区域;其次,用改进的Hough变换通过斜率范围限定识别出组成车道线边缘的直线段,通过设置平均斜率偏离阈值去除非目标车道线边缘的直线段;最后,取出车道线直线段的端点作为车道线的数据点集,进行最小二乘法拟合出车道线。实验结果表明,干扰条件下车道线识别的准确率达到95.3%,耗时0.025 s,可见该方法具备了较好的实时性和鲁棒性。In allusion to the problem that the detection and recognition rate of structured road lane line is not high under interference conditions,a lane line detection method based on improved Hough transform is proposed based on the imaging characteristics and slope characteristics of lane line.The Canny edge detection method is used to find the edge of all lane line,so as to determine the region where the target lane line is located as the region of interest.The improved Hough transform is used to identify the line segments that make up the edge of the lane line by limiting the slope range,and the line segments that make up the edge of the non⁃target lane line are removed by setting the average slope deviation threshold.The improved Hough transform is used to find the straight line segment of the laneline.The end point of the straight line segment of the lane line is taken as the data point set of the lane line,and the least square method is used to fit the lane line.The experimental results show that the accuracy of lane line recognition under interference conditions can reach 95.3%,and the average time is 0.025 s.It is concluded that this method has good real⁃time performance and robustness.

关 键 词：车道线检测 斜率特征 HOUGH变换 最小二乘法拟合 准确率 鲁棒性 

分 类 号：TN911.73-34[电子电信—通信与信息系统] TP391[电子电信—信息与通信工程]