华南理工大学学报(自然科学版) ›› 2023, Vol. 51 ›› Issue (10): 110-125.doi: 10.12141/j.issn.1000-565X.230100

所属专题: 2023绿色智慧交通系统专辑

• 绿色智慧交通系统 • 上一篇    下一篇

基于毫米波雷达点云的路口车辆轨迹跟踪方法

林永杰1,2 陈宁1 卢凯1,2   

  1. 1.华南理工大学 土木与交通学院,广东 广州 510640
    2.人工智能与数字经济广东省实验室(广州),广东 广州 510330
  • 收稿日期:2022-03-08 出版日期:2023-10-25 发布日期:2023-06-06
  • 通信作者: 卢凯(1979-),男,教授,博士生导师,主要从事交通信号控制、交通大数据挖掘和车路协同研究。 E-mail:kailu@scut.edu.cn
  • 作者简介:林永杰(1987-),男,副教授,博士生导师,主要从事交通检测与数据建模、交通信号控制、车路协同研究。E-mail:linyjscut@scut.edu.cn
  • 基金资助:
    广东省自然科学基金青年提升资助项目(2023A1515030120);国家自然科学基金青年基金资助项目(61903145)

Vehicle Trajectory Tracking at Intersections Based on Millimeter Wave Radar Point Cloud

LIN Yongjie1,2 CHEN Ning1 LU Kai1,2   

  1. 1.School of Civil Engineering and Transportation,South China University of Technology,Guangzhou 510640,Guangdong,China
    2.Guangdong Artificial Intelligence and Digital Economy Laboratory,Guangzhou 510330,Guangdong,China
  • Received:2022-03-08 Online:2023-10-25 Published:2023-06-06
  • Contact: 卢凯(1979-),男,教授,博士生导师,主要从事交通信号控制、交通大数据挖掘和车路协同研究。 E-mail:kailu@scut.edu.cn
  • About author:林永杰(1987-),男,副教授,博士生导师,主要从事交通检测与数据建模、交通信号控制、车路协同研究。E-mail:linyjscut@scut.edu.cn
  • Supported by:
    the Natural Science Foundation of Guangdong Province Youth Enhancement Project(2023A1515030120);the National Natural Science Foundation of China(61903145)

摘要:

毫米波雷达作为一种新兴的交通检测设备,受光照、天气等环境影响较小,能为道路交通感知、安全管控和信号配时优化等方面提供可靠的数据支撑。毫米波雷达获取的车辆轨迹数据蕴含着丰富的交通信息,反映了车辆时空运动特征,对交通参数提取、事件检测、驾驶行为分析、信号配时优化等具有重要意义。针对路口毫米波雷达检测车辆时数据丢失、易被遮挡,导致轨迹碎片化、有效跟踪率低等问题,文章采用多阶段关联的思想提出了一种基于短轨迹片段关联的车辆轨迹连续跟踪方法。首先,获取路口处毫米波雷达高频采集的二维点云数据,并进行清洗获取有效目标点云;其次,通过帧间关联从二维点云中提取短轨迹片段,并使用多重运动序列特征进行轨迹片段修正以剔除分裂轨迹;第三,基于时空维度的运动特性构建模糊相关函数描述车辆经过路口时多个短轨迹碎片之间的相关度,并利用匈牙利法求解关联度最高的构成目标短轨迹集合;最后,基于三次分段Hermite插值法修复短轨迹集合中缺失的轨迹点,推算完整轨迹并实现连续跟踪。利用真实路口采集的6 627帧二维点云数据进行试验,其结果表明:相较于传统轨迹跟踪算法,提出的方法在不同车流密度、监测方向和遮挡情况下均能取得较优的跟踪性能,其跟踪准确性为92.4%,平均轨迹间断数为4.5条,估计的车辆数准确率显著提升。

关键词: 交通检测, 车辆轨迹跟踪, 毫米波雷达, 短轨迹关联, 模糊相关函数

Abstract:

As an emergent traffic detection device, millimeter wave radar is little affected by environmental factors (e.g., light and weather) and can provide reliable data support for road traffic sensing, safety control and signal timing optimization. Vehicle trajectory data collected by millimeter wave radar contains rich traffic information, reflecting spatial-temporal characterization of vehicle motion, which is critical in traffic parameter extraction, abnormal detection, driving behavior analysis, signal timing optimization, etc. Aiming at solving the problems such as trajectory fragmentation and poor valid tracking rate caused by the vehicle data loss and easy occlusion of vehicles detected by millimeter wave radar in the intersection, this paper proposed a continuous tracking method of vehicle trajectory based on short trajectory fragment associations. Firstly, the 2D point cloud data with high frequency collected by millimeter wave radar at the intersection was acquired and cleaned to obtain valid target information. Secondly, short track fragments were extracted from 2D point clouds by inter-frame association, and multiple movement sequence feature was used for track fragment correction to reject split trajectories. Thirdly, the fuzzy correlation function was constructed based on the motion characteristics of the spatiotemporal dimension to describe the correlation among multiple short track fragments. Hungarian algorithm was employed to solve the set of target short track with the highest correlation. Finally, the missing trajectory points in the vehicle tracklet set were repaired based on the piecewise cubic Hermite interpolation, which derived complete trajectories and achieved continuous tracking. The experiments were conducted using 6 627 frames of 2D point cloud data collected at the real intersection. The results indicate that the proposed method achieves better tracking performance under different traffic densities, monitoring directions, and occlusions than the traditional trajectory tracking algorithm. Specifically, the trajectory tracking accuracy is 92.4%, the number of fragmentations is 4.5, and the accuracy of estimated vehicle volume is significantly improved.

Key words: traffic detection, vehicle trajectory tracking, millimeter wave radar, short track association, fuzzy correlation function

中图分类号: