利用双灭点估计的车道线检测

doi:10.13474/j.cnki.11-2246.2020.0004

测绘通报 ›› 2020, Vol. 0 ›› Issue (1): 16-20.doi: 10.13474/j.cnki.11-2246.2020.0004

利用双灭点估计的车道线检测

陈世增¹, 李必军^1,2, 周继苗¹

1. 武汉大学测绘遥感信息工程国家重点实验室, 湖北武汉 430079;
2. 武汉大学时空数据智能获取技术与应用教育部工程研究中心, 湖北武汉 430079

收稿日期:2019-09-10 修回日期:2019-11-08 发布日期:2020-02-10
通讯作者: 李必军。E-mail:lee@whu.edu.cn E-mail:lee@whu.edu.cn
作者简介:陈世增(1995-),男,硕士生,主要研究方向为自动驾驶环境感知及决策应用。E-mail:csz@whu.edu.cn
基金资助:
国家自然科学基金（41671441）；国家自然科学基金汽车产业创新发展联合基金（U1764262）

Lane detection with double vanishing points estimation

CHEN Shizeng¹, LI Bijun^1,2, ZHOU Jimiao¹

1. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China;
2. Engineering Research Center of Spatio-Temporal Data Smart Acquisition and Application, Ministry of Education, Wuhan University, Wuhan 430079, China

Received:2019-09-10 Revised:2019-11-08 Published:2020-02-10

摘要/Abstract

摘要： 车道线检测是自动驾驶汽车或高级驾驶辅助系统的重要组成部分，利用安装在车辆前方的单目相机以实时成像的方式获取车辆在当前车道的横向偏移，从而为车辆的车道保持、超车换道等横向控制策略提供参考。本文提出了一种基于双灭点估计的实时、稳健的车道检测方法。首先利用尺度自适应的局部对称算子对车道线点特征进行提取；其次对左右车道线分别估计灭点，以灭点为导向，构建特征点的统计直方图；然后选择穿过大多数特征点的直线且通过特征点和所选线之间的重叠度对灭点进行估计更新，重复上一步骤以获得稳定的灭点；最后基于稳定的灭点验证并选择最佳的车道线。本文在公共数据集对提出的方法进行了测试，试验结果表明，本文方法在满足实时性的前提下，能有效提高算法整体的稳健性。

关键词: 车道线检测, 直方图, 双灭点估计, 重叠度, 自动驾驶

Abstract: In automatic vehicles or advanced driving assistance systems, lane detection provides a way to guide the vehicle to drive along its own lane. An efficient lane detection method is proposed in this paper. Firstly, the lane features are extracted, and the lines are generated from vanishing points to image bottom. Then the lines crossing most features are selected and vanishing points are updated by the overlap between features and selected lines. Last step will be repeated until stable vanishing points are obtained. The last selected lines are most likely to be lane lines. Finally, validate and select the best lane lines. The proposed method has been tested on a public dataset. The experimental results show that the method can improve robustness under real-time automated driving.

Key words: lane detection, histogram, double vanishing points estimation, overlap, automated driving

中图分类号:

P208

陈世增, 李必军, 周继苗. 利用双灭点估计的车道线检测[J]. 测绘通报, 2020, 0(1): 16-20.

CHEN Shizeng, LI Bijun, ZHOU Jimiao. Lane detection with double vanishing points estimation[J]. Bulletin of Surveying and Mapping, 2020, 0(1): 16-20.

参考文献

[1] LEE C, MOON J H. Robust lane detection and tracking for real-time applications[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 19(12):4043-4048.
[2] 彭红,肖进胜,程显,等. 基于扩展卡尔曼滤波器的车道线检测算法[J]. 光电子·激光,2015,26(3):567-574.
[3] ZHANG D M, FANG B, YANG W B, et al. Robust inverse perspective mapping based on vanishing point[C]//Proceedings of 2014 IEEE International Conference on Security, Pattern Analysis, and Cybernetics (SPAC). Wuhan:IEEE,2014:458-463.
[4] 姜岩,叶刚,龚建伟.姿态反馈与概率预测的复杂环境无人车辆多模型车道线检测算法[J].兵工学报,2014,35(S1):44-50.
[5] 彭红,肖进胜,沈三明,等.一种基于随机抽样一致性的车道线快速识别算法[J].上海交通大学学报,2014,48(12):1721-1726.
[6] OZGUNALP U. Robust lane-detection algorithm based on improved symmetrical local threshold for feature extraction and inverse perspective mapping[J]. IET Image Processing, 2019, 13(6):975-982.
[7] LIU W R, LI S T, HUANG X. Extraction of lane markings using orientation and vanishing point constraints in structured road scenes[J]. International Journal of Computer Mathematics, 2014, 91(11):2359-2373.
[8] HOU C Z, HOU J, YU C C. An efficient lane markings detection and tracking method based on vanishing point constraints[C]//35th Chinese Control Conference (CCC). Chengdu:IEEE, 2016:6999-7004.
[9] YUAN J, TANG S M, PAN X Q, et al. A robust vanishing point estimation method for lane detection[C]//Proceedings of the 33rd Chinese Control Conference. Nanjing:IEEE, 2014:4887-4892.
[10] 陈龙,李清泉,毛庆洲.基于成像模型的车道线检测与跟踪方法[J].中国公路学报,2011,24(6):96-102.
[11] YOO J H, LEE S W, PARK S K, et al. A robust lane detection method based on vanishing point estimation using the relevance of line segments[J]. IEEE Transactions on Intelligent Transportation Systems, 2017, 18(12):3254-3266.
[12] VEIT T, TAREL J P, NICOLLE P, et al. Evaluation of road marking feature extraction[C]//Proceedings of the 11th International IEEE Conference on Intelligent Transportation Systems. Beijing:IEEE, 2008:174-181.
[13] LI Q Q, ZHOU J, LI B J, et al. Robust lane-detection method for low-speed environments[J]. Sensors, 2018, 18(12):4274.
[14] ALY M. Real time detection of lane markers in urban streets[C]//Proceedings of IEEE Intelligent Vehicles Symposium. Eindhoven:IEEE, 2008:7-12.
[15] NIU J W, LU J, XU M L, et al. Robust lane detection using two-stage feature extraction with curve fitting[J]. Pattern Recognition, 2016, 59:225-233.

利用双灭点估计的车道线检测

Lane detection with double vanishing points estimation

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	黄鹤, 孟维明. 基于视觉的大半径圆曲线车道线识别[J]. 测绘通报, 2022, 0(4): 134-137.
[2]	赵之星, 鲁小红, 田昕, 刘志奇. 倾斜影像重叠度计算模型及应用[J]. 测绘通报, 2021, 0(9): 89-92.
[3]	杨振凯, 华一新, 訾璐, 张政, 王继伟. 浅析高精度地图发展现状及关键技术[J]. 测绘通报, 2021, 0(6): 54-60.
[4]	刘思言, 李玲, 特日根, 李竺强, 马经宇, 朱瑞飞. 基于直方图区域生长的遥感图像阈值分割算法[J]. 测绘通报, 2021, 0(2): 25-29.
[5]	周继苗, 李必军, 陈世增. 一种多层特征融合的道路场景实时分割方法[J]. 测绘通报, 2020, 0(1): 10-15.
[6]	张世强, 王贵山. 基于高分辨率遥感影像的车道线提取[J]. 测绘通报, 2019, 0(12): 22-25.
[7]	王永康, 汪云甲, 毕京学, 曹鸿基. 一种基于图像灰度直方图相似度计算的室内定位方法[J]. 测绘通报, 2018, 0(4): 63-67.
[8]	罗文婷, 李林. 一种高精地图道路三维线形测量方法[J]. 测绘通报, 2018, 0(12): 46-51.
[9]	朱爽. 用直方图面积法进行图像相似度计算[J]. 测绘通报, 2018, 0(12): 96-100.
[10]	付睢宁, 卢小平, 卢遥. 适用于SAR影像的偏微分ROF去噪算法[J]. 测绘通报, 2018, 0(11): 16-19.
[11]	楚恒, 李洪川, 刘红彬. 基于对象直方图G统计量的遥感影像道路提取[J]. 测绘通报, 2017, 0(12): 63-67.
[12]	胡屹群, 周绍光, 岳顺, 王莎. 利用视觉词袋模型和颜色直方图进行遥感影像检索[J]. 测绘通报, 2017, 0(1): 53-57.
[13]	姜浩, 黄鹤, 赵焰, 杨军星. 高精度智能导航数据评价系统的设计与实现[J]. 测绘通报, 2016, 0(7): 98-102.
[14]	陈宇, 徐青, 姚富山, 施群山, 吕亮, 卢万杰. 影像密集匹配点云的单体化提取[J]. 测绘通报, 2016, 0(12): 51-55.
[15]	林卉, 王李娟, 康志忠, 田艳凤, 邵聪颖. 三维激光扫描建筑物立面数据的自动提取[J]. 测绘通报, 2016, 0(10): 25-30.