基于视野和投影修正技术的车辆纵向安全研究

doi:10.16265/j.cnki.issn1003-3033.2018.06.014

中国安全科学学报 ›› 2018, Vol. 28 ›› Issue (6): 79-84.doi: 10.16265/j.cnki.issn1003-3033.2018.06.014

基于视野和投影修正技术的车辆纵向安全研究

马玉春^1,2 讲师, 周劲草³

1 长安大学公路学院,陕西西安 710064;
2 新疆大学机械工程学院,新疆乌鲁木齐 830046;
3 长安大学汽车学院,陕西西安 710064

收稿日期:2018-03-21 修回日期:2018-05-09 出版日期:2018-06-28 发布日期:2020-11-25
作者简介:马玉春(1981—),男,新疆乌鲁木齐人,博士研究生,讲师,主要从事交通规划、交通安全等方面的研究。

Study on improving vehicle longitudinal safety based on vision revision and projection reversion technique

MA Yuchun^1,2, ZHOU Jincao³

1 College of Highway,Chang' an University,Xi' an Shaanxi 710064,China;
2 College of Mechanical Engineering,Xinjiang University,Urumqi Xinjiang 830046,China;
3 College of Automobile,Chang' an University,Xi' an Shaanxi 710064,China

Received:2018-03-21 Revised:2018-05-09 Online:2018-06-28 Published:2020-11-25

摘要/Abstract

摘要： 针对现有机器视觉测距技术存在焦距选择不当,以及由特征点离地间隙造成的纵向测距精确性较低导致纵向预警时刻滞后的问题,提出一种基于视野修正和投影修正技术的用于测量同向行驶且有不可忽视的碰撞风险的2个车辆间纵向距离的方法。采用麋鹿试验分析发散态纵向识别区域模型不足,建立收敛态纵向预警区域模型,结合安全制动距离动力学仿真结果,计算出收敛态纵向预警区域模型对应的稳态成像焦距值,完成视野修正;利用静态参数拟合回归得出纵向误差函数,完成特征点投影修正,实现高精度纵向距离测量。运用靶源板静态试验进行测量验证。结果表明:文中所给方法在30～100m测量范围内的测量精确度平均相对误差低于3.5%,绝对误差小于2.6 m。

关键词: 机器视觉, 动力学仿真, 麋鹿试验, 制动距离, 数据拟合

Abstract: In view of that the longitudinal warning system delay phenomenon caused by the low accuracy of longitudinal ranging results in traditional computer vision,a visual revision and projection reversion technique based method was developed for measuring the longitudinal distance between the two vehicles running in the same direction and having a significant risk of collision.A convergence state longitudinal early warning model was built after analyzing the defects in the traditional emanative distance detection models by using the elk test method.The static experiment based on target source plate shown that the average absolute and relative errors of distance measurement by the method are less than 2.6 m and 3.5% respectively in the 30-100 m range of distance.

Key words: computer vision, dynamics simulation, elk test, break distance, data fitting

中图分类号:

X913.4

马玉春, 周劲草. 基于视野和投影修正技术的车辆纵向安全研究[J]. 中国安全科学学报, 2018, 28(6): 79-84.

MA Yuchun, ZHOU Jincao. Study on improving vehicle longitudinal safety based on vision revision and projection reversion technique[J]. China Safety Science Journal, 2018, 28(6): 79-84.

参考文献

[1] LEE J W.A machine vision system for lane-departure detection[J].Computer Vision and Image Understanding,2002,86 (1):52-78
[2] WEN Xuezhi,SHAO Ling,FANG Wei,et al.Efficient feature selection and classification for vehicle detection[J].IEEE Transactions on Circuits & Systems for Video Technology,2015,25(3):508-517.
[3] REZAEI M,TERAUCHI M,KLETTE R.Robust vehicle detection and distance estimation under challenging lighting conditions[J].IEEE Transactions on Intelligent Transportation Systems,2015,16(5):2 723-2 743.
[4] 周劲草,魏朗,乔洁.面向雾天的双先验兴趣区域车道线识别算法研究[J].中国安全科学学报,2016,26(8):128-133.
ZHOU Jincao,WEI Lang,QIAO Jie.Study on lane detection based on dual-heuristic region of interest for fog[J].China Safety Science Journal,2016,26(8):128-133.
[5] 余厚云,张为公.基于单目视觉的跟驰车辆车距测量方法[J].东南大学学报:自然科学版,2012,42(3):542-546.
YU Houyun,ZHANG Weigong.Method of vehicle distance measurement for following car based on monocular vision[J].Journal of Southeast University:Natural Science Edition,2016,42(3):542-546.
[6] WEI Lang,LIU Yongtao,ZHOU Weixin,et al.Research on preceding vehicle distance measurement with monocular vision based on lane plane geometric model[J].ICIC Express Letters:Part B,Applications:An International Journal of Research and Surveys,2016,7(5):1057-1062.
[7] 刘喜东,刘应东.考虑转向速度的汽车操纵稳定性分析[J].机械工程学报,2011,47(10):95-100.
LIU Xidong,LIU Yingdong.Analysis on vehicle handling and stability considering steering velocity[J].Journal of Mechanical Engineering,2011,47(10):95-100.
[8] 熊璐,陈晨,冯源.基于Carsim/Simulink联合仿真的分布式驱动电动汽车建模[J].系统仿真学报,2014,26(5):1143-1148.
XIONG Lu,CHEN Chen,FENG Yuan.Modeling of distributed drive electric vehicle based on co-simulation of Carsim/Simulink[J].Journal of System Simulation,2014,26(5):1143-1148.
[9] 徐杰,杜文,孙宏.跟随车安全距离的分析[J].交通运输工程学报,2002,2(1):101-104.
XU Jie,DU Wen,SUN Hong.Safety distance about car-following[J].Journal of Traffic and Transportation Engineering,2002,2(1):101-104.
[10] 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.
GUO Lei,XU Youchun,LI Keqiang,et al.Study on real time distance detection based on monocular vision technique[J].Journal of Image and Graphics,2006,11(1):74-81.

基于视野和投影修正技术的车辆纵向安全研究

Study on improving vehicle longitudinal safety based on vision revision and projection reversion technique

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	康青春，孙沛，王淮斌，李玉. 液化石油气喷射火灾热辐射估算方法研究[J]. 中国安全科学学报, 2013, 23(11): 16-.
[2]	杨福刚. 医用输液生产中药品安全隐患分析及对策[J]. 中国安全科学学报, 2010, 20(5): 102-.
[3]	刘志强，汪澎，秦洪懋，仲晶晶，宋世亮. 基于多信息检测的车辆智能防撞预警技术研究[J]. 中国安全科学学报, 2010, 20(1): 153-.
[4]	初秀民，万剑，严新平，毛喆. 基于车载机器视觉的汽车安全技术[J]. 中国安全科学学报, 2008, 18(5): 154-.
[5]	万传风，张勇. 基于ADAMS/Rail的直线电机轨道交通安全性研究[J]. 中国安全科学学报, 2006, 16(3): 87-.