单目视觉的前车位置识别及安全车距监测

  • 张欣 ,
  • 魏志恒 ,
  • 王兵
展开
张欣(1966—),男,河北承德人,河北大学教授,博士,主要从事机器视觉方向的研究.
E-mail:zhangxin@hbu.edu.cn

收稿日期: 2021-08-05

  网络出版日期: 2022-06-16

基金资助

国家自然科学基金资助项目(61375075);河北省自然科学基金资助项目(F2019201329);河北省教育厅重点项目(ZD2018210)

Position recognition of the vehicle ahead and safety distance monitoring based on monocular vision

  • ZHANG Xin ,
  • WEI Zhiheng ,
  • WANG Bing
Expand
  • 1. College of Electronic and Information Engineering, Hebei University, Baoding 071002, China; 2.College of Mathematics and Information Science, Hebei University, Baoding 071002, China

Received date: 2021-08-05

  Online published: 2022-06-16

摘要

针对自动驾驶中的前车位置识别及安全车距监测问题,提出了基于单目视觉的解决方案:首先,通过图像中前车轮廓与本车道及同向车行道分界线是否相交判断前车是否为监测车辆;其次,根据图像中像素坐标系与空间坐标系的对应关系构建转换模型,计算前方监测车辆与本车的真实车距;最后,根据可跨越的同向车行道分界线在连续图像帧中的位置变化计算本车的行驶速度,并依据交通法规判断本车与前方监测车辆之间是否为安全距离.实验结果表明,该解决方案可以有效地识别前车位置、监测安全车距并降低系统成本.

本文引用格式

张欣 , 魏志恒 , 王兵 . 单目视觉的前车位置识别及安全车距监测[J]. 河北大学学报(自然科学版), 2022 , 42(3) : 321 -326 . DOI: 10.3969/j.issn.1000-1565.2022.03.015

Abstract

A solution based on monocular vision is proposed to recognize the position of the vehicle ahead and to monitor the safe distance in automatic driving. Firstly, whether the vehicle ahead is a monitoring vehicle can be judged by whether the contour of the vehicle ahead intersects with the roadway and the dividing line of the roadway. Secondly, according to the corresponding relationship between pixel coordinate system and spatial coordinate system in the image, the transformation model is built to calculate the real distance from the monitored vehicle. Finally, the speed of this vehicle is calculated according to the position change of the crossable delimitation line of the same direction roadway in the continuous image frames, and the safety distance between this vehicle and the monitored vehicle is determined according to the traffic laws and regulations. Experimental results show that this solution can effectively recognize the position of the vehicle ahead, monitor the safety distance and reduce the system cost.

参考文献

[1] 程瑶,赵雷,成珊,等.基于机器视觉的车距检测系统设计[J].计量学报,2020,41(1):11-15.DOI:10.3969/j.issn.1000-1158.2020.01.03.
[2] 梁炳春.基于机器视觉的辅助驾驶系统中车辆检测与测距研究[D].上海:东华大学, 2016.
[3] 马朝阳,华云松.基于双目立体视觉的平面测距研究[J].软件,2020,41(9):194-197.DOI:10.3969/j.issn.1003-6970.2020.09.051.
[4] 佘彩云,胡贤洪,唐坤.一种多目视觉三维测距系统设计[J].制导与引信,2015,36(3):20-24.
[5] 张海焕,陈彩霞,马逸行.基于超声波雷达的自动泊车自适应测距与定位设计[J].科技视界,2020(28):1-4.DOI:10.19694/j.cnki.issn.2095-2457.2020.28.01.
[6] 黄智勇.基于毫米波雷达的汽车自动避障控制系统研究[J].佳木斯大学学报(自然科学版),2019,37(4):580-584.
[7] 顾柏园.基于单目视觉的安全车距预警系统研究[D].长春:吉林大学, 2006.
[8] ZHANG S P. Object tracking and velocity measurement based on binocular stereo vision[C] //Proceedings of 2017 4th International Conference on Power and Energy Systems, 2017:87-93. DOI:10.5729/lnes.2017.9.81.
[9] 祁昊,翁剑成,张乐典,等.基于公交车辆定位数据的公交运送速度计算模型[J].交通工程,2020,20(1):71-78.DOI:10.13986/j.cnki.jote.2020.01.012.
[10] 孙培嘉,张宝龙,邢建平,等.一种基于北斗的智能轮式载体定位定姿测速方法[C] //第十一届中国卫星导航年会论文集——S01卫星导航行业应用,[s.n.] ,2020:78-84.
[11] MATH WORKS公司. Visual perception using monocular camera[CP/OL]. [2021-02-27]. https://ww2.mathworks.cn/help/driving/ug/visual-perception-using-monocular-camera.html;jsessionid=aff5951e3aed80cb1d0122c16b5d?searchHighlight=vehicleToImageROI&s_tid=doc_srchtitle#VisualPerceptionUsingMonoCameraExample-6
[12] GB 5768.3-2009,道路交通标志和标线第3部分:道路交通标线[S].
[13] 中华人民共和国国务院.中华人民共和国道路交通安全法实施条例[Z/OL].(2017-10-07)[2021-02-27].http://www.gov.cn/gongbao/content/2019/content_5468932.htm. (
文章导航

/

〈 〉