上海交通大学学报(自然版) ›› 2018, Vol. 52 ›› Issue (1): 33-38.doi: 10.16183/j.cnki.jsjtu.2018.01.006

• 学报(中文) • 上一篇    下一篇

基于视觉和毫米波雷达的车道级定位方法

赵翔a,b,杨明a,b,王春香c,王冰a,b   

  1. 上海交通大学 a. 自动化系; b. 上海市北斗导航与位置服务重点实验室; c. 机器人研究所, 上海 200240
  • 出版日期:2018-01-01 发布日期:2018-01-01
  • 基金资助:
    国家自然科学基金项目(91420101)

A Lane-Level Positioning Method Based on Vision and Millimeter Wave Radar

ZHAO Xianga,b,YANG Minga,b,WANG Chunxiangc,WANG Binga,b   

  1. a. Department of Automation; b. Shanghai Key Laboratory of Navigation and Location Services; c. Research Institute of Robotics, Shanghai Jiao Tong University, Shanghai 200240, China
  • Online:2018-01-01 Published:2018-01-01

摘要: 提出了一种基于视觉和毫米波雷达的车道级定位方法.利用机器视觉方法,通过摄像头检测车道线,并用圆曲线模型进行拟合;采用毫米波雷达检测道路两旁的静止护栏边沿,以获取道路的边界信息,采用低精度全球定位系统(GPS)获取当前道路信息,并对比车道线与道路边沿的相对位置关系,从而进行车道级定位.结果表明,针对中、高速城市道路及高速公路场景,所提出的车道级定位方法的定位效果较好.

关键词: 车道线, 道路边沿, 车道级定位, 毫米波雷达, 全球定位系统

Abstract: A lane-level positioning method based on vision and millimeter wave radar is proposed. A camera is used for lane recognition with circular curve model and a millimeter wave radar is used for road curb re-cognition by detecting the stationary railways alongside. Lane-level positioning is then calculated by comparing the relative distance of lane and curb with the road prior information obtained from a low precision global position system (GPS). The results show that the lane-level positioning method proposed in this paper can achieve good positioning accuracy in city and highway scenes.

Key words: lane marking, road curb, lane-level positioning, millimeter wave radar, global position system (GPS)

中图分类号: