计算机科学 ›› 2015, Vol. 42 ›› Issue (Z11): 520-524.

• 智能系统及应用 • 上一篇    下一篇

基于机器视觉的轻量级驾驶辅助系统

徐邦振,汤一平,蔡国宁   

  1. 浙江工业大学信息工程学院 杭州310023,浙江工业大学信息工程学院 杭州310023,浙江工业大学信息工程学院 杭州310023
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家基金面上项目:主动三维立体全景视觉传感技术研究(61070134)资助

Machine Vision-based Lightweight Driver Assistance System

XU Bang-zhen, TANG Yi-ping and CAI Guo-ning   

  • Online:2018-11-14 Published:2018-11-14

摘要: 为了解决计算机视觉应用中数据量大、算法复杂的问题,根据道路结构特征和车辆行为特征,采用单个摄像头作为传感器,实现了一种轻量级的安全辅助驾驶系统。首先采用改进的边缘提取算法和车道线检测算法对摄像机内外参数进行离线标定;接着根据标定结果在二维平面图像上采用标识出实际空间距离的多窗口划分方法,并按不同的车间距将不同窗口划分为不同安全系数的区域,以赋予道路视觉检测的几何先验知识;当区域中出现障碍物时发出相应警示信息进行安全驾驶辅助,能为智能辅助驾驶提供轻量级的视觉检测平台。以便携式计算机和固定在车内的摄像头作为实验装置,在城市道路上进行车载实验。系统在车载实验中能够快速地提取车辆两侧的车道线,并利用离线标定的结果快速生成不同安全系数的警示区域,其中车辆在车道内正常行驶时的误检率和漏检率很小,可以忽略不计。与传统的驾驶辅助系统相比,本系统计算量大大降低,检测流程得到简化,可实现轻量级的车道和车辆检测,为系统在嵌入式系统上的实现奠定基础。

关键词: 机器视觉,视觉标定,驾驶辅助,轻量级的视觉检测

Abstract: This paper proposed a machine vision-based lightweight driver assistance system.Firstly,the adjusted algorithm for extracting edge and lane line detection algorithm are used to calibrate inside and outside parameters of cameras offline.Secondly,a multi-window division method identifying the actual distance is used on two-dimensional image according to the results of calibration,and different window is divided into regions of different safety factor according to distance,in order to provide prior knowledge of geometry of vision detection to the road.Thirdly,when there is an obstacle in the area,the corresponding warning message is displayed to assist the driver and provide lightweight visual detection platform for intelligent driver assistance system.The proposed system in this paper can extract lane line on both sides of the vehicle quickly in car-board experiments and take advantage of off-line calibration results to generate alerts regions of different safety factors quickly,and both positive false detection rate and negative false detection rate in the experiment during normal driving in the lane are small and negligible.Compared with conventional driver assistance systems,our proposed method reduces the computation amount by simplifying the detection process to achieve lightweight lane and vehicle detection,and lays the foundation for implementation of the system on embedded systems.

Key words: Machine vision,Visual calibration,Driver assistance,Lightweight visual detection

[1] 符梦星.中国驾驶员希望实现高速公路自动化驾驶[EB/OL].2014-8-30[2014-10-21].http://www.continental-press.cn/www/pressportal_cn_cn/themes/press_releases/3_automotive_group/fd_automotive_cn/pr_2014_08_30_mobility_study2013_cn.html
[2] Dagan E,Mano O,Stein G P,et al.Forward collision warningwith a single camera[C]∥Intelligent Vehicles Symposium,2004 IEEE.IEEE,2004:37-42
[3] Stein G P,Mano O,Shashua A.Vision-based ACC with a single camera:bounds on range and range rate accuracy[C]∥Procee-dingsIntelligent Vehicles Symposium,2003.IEEE,2003:120-125
[4] 贾鑫.智能车辆视觉感知中的车道标线识别方法的研究 [D].吉林:吉林大学,2008
[5] Bouguet J-Y.Camera Calibration Toolbox for Matlab[EB/OL].2013-12-02 [2014-10-21].http://www.vision.caltech.edu/bouguetj/calib_doc/index.html#parameters
[6] 郭磊,徐友春,李克强,等.基于单目视觉的实时测距方法研究[J].中国图象图形学报,2006,11(1):74-81
[7] 常娜.图像处理中的边缘检测算法研究综述[J].中国科技信息,2011(4):130-131
[8] 于增亮.基于仿真环境驾驶员临界反应能力的研究[D].吉林:吉林大学,2005
[9] 田雪健,胡江碧.车辆制动距离影响因素分析[C]∥第七届中国智能交通年会优秀论文集——智能交通技术.2012(1):245-251
[10] 徐杰,杜文.跟随车安全距离的分析[J].交通运输工程学报,2002,2(1):101-104
[11] 李星,郭晓松,郭君斌.基于HOG特征和SVM的前向车辆识别方法[J].计算机科学,2013,40:329-332
[12] 余立功,王强,陈纯.多尺度模板匹配算法[J].工程图学学报,2005,26(3):80-83

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!