摘要
针对车道线检测技术在车道偏离预警、自动泊车和车道变换等各种辅助驾驶系统中的重要作用,国内外专家学者对车道线检测技术做了较多的研究,但是近年来少见有关于车道线检测的综述,因此本文主要阐述了近几年国内外机器视觉的车道线检测研究进展。首先简单介绍了机器视觉的车道线检测的基本流程;其次重点阐述了基于特征、基于模型和基于深度学习三种典型方法的基本检测原理和研究现状,并对比三种典型研究方法;最后,提出了机器视觉的车道线检测方法主要存在的问题,并针对问题提出未来的发展方向。
Aiming at the important role of lane line detection technology in lane departure warning,automatic parking and lane change in various driving assistance systems,foreign experts and scholars have done more research on lane detection technology,but in recent years,there have been rare cases about lanes,so this article mainly elaborates the basic situation of the progress of line detection based on machine vision at home and abroad in recent years.First,this paper briefly introduces the basic process of lane line detection based on machine vision,and then illustrates on the basic testing principle and current state of research of the three typical methods based on feature,model and deep learning,and compares the three typical research methods.Finally,the main problems of the lane line detection method based on machine vision are put forward,and the future development direction is proposed.
作者
赵强
王瑞
朱宝全
李哲煜
ZHAO Qiang;WANG Rui;ZHU Bao-quan;LI Zhe-yu(School of Traffic and Transportation,Northeast Forestry University,Harbin,Heilongjiang 150040,China)
出处
《计算技术与自动化》
2022年第1期34-40,共7页
Computing Technology and Automation
基金
国家重点研发计划重点专项(2017YFC0803901),黑龙江省留学归国人员科学基金(LC2015019)。
关键词
车道线检测
机器视觉
特征检测
模型检测
深度学习
lane line detection
machine vision
feature detection
model checking
deep learning
