华南理工大学学报(自然科学版) ›› 2024, Vol. 52 ›› Issue (6): 56-72.doi: 10.12141/j.issn.1000-565X.230314

• 绿色智慧交通 • 上一篇    下一篇

路侧感知车辆轨迹数据的质量评估方法

雷财林1(), 赵聪1, 娄刃2, 暨育雄1†(), 杜豫川1   

  1. 1.同济大学 道路与交通工程教育部重点实验室, 上海 201804
    2.浙江省交通运输科学研究院 新一代人工智能技术交通运输行业研发中心, 浙江 杭州 310023
  • 收稿日期:2023-05-10 出版日期:2024-06-25 发布日期:2023-10-27
  • 通信作者: 暨育雄(1978—),男,博士,教授,博士生导师,主要从事自动驾驶可信评价、交通数据挖掘与智能决策研究。 E-mail:yxji@tongji.edu.cn
  • 作者简介:雷财林(1992—),男,博士生,主要从事轨迹数据处理、驾驶行为建模研究。E-mail: 2010762@tongji.edu.cn
  • 基金资助:
    国家重点研发计划项目(2022YFF0604900);国家自然科学基金资助项目(52302415)

Quality Assessment Method of Vehicle Trajectory Data from Roadside Perception

LEI Cailin1(), ZHAO Cong1, LOU Ren2, JI Yuxiong1(), DU Yuchuan1   

  1. 1.Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Tongji University,Shanghai 201804,China
    2.Research and Development Center of Transport Industry of New Generation of Artificial Intelligence Technology,Zhejiang Scientific Research Institute of Transport,Hangzhou 310023,Zhejiang,China
  • Received:2023-05-10 Online:2024-06-25 Published:2023-10-27
  • Contact: 暨育雄(1978—),男,博士,教授,博士生导师,主要从事自动驾驶可信评价、交通数据挖掘与智能决策研究。 E-mail:yxji@tongji.edu.cn
  • About author:雷财林(1992—),男,博士生,主要从事轨迹数据处理、驾驶行为建模研究。E-mail: 2010762@tongji.edu.cn
  • Supported by:
    the National Key Research and Development Program of China(2022YFF0604900);the National Natural Science Foundation of China(52302415)

摘要:

路侧传感器已大量部署在高速公路上,用来实时采集路段全样本车辆轨迹数据,为交通流全时空管控、微观驾驶行为分析等提供数据支持,但数据质量的快速评估一直是困扰行业管理部门的难题。现有的车辆轨迹数据评估方法大多存在操作复杂、维度单一等问题,难以满足对动态交通流中实时产生的车辆轨迹数据的评价需求。为快速判别路侧毫米波雷达车辆轨迹数据的质量,文中通过挖掘数据自身信息提出了一种数据质量评价方法。首先,在分析实测轨迹数据典型问题的基础上,从轨迹完整性、一致性、准确性及有效性4个维度建立了9个二级评价指标;然后,基于CRITIC赋权法计算综合指标;最后,针对4种不同场景的3 549条毫米波雷达实测轨迹进行了实证分析。结果表明,毫米波雷达的安装方式、型号等会显著影响车辆轨迹数据的质量,所提出的数据质量评价方法能够量化不同车辆轨迹数据的质量差异。文中研究结果可为路侧传感器采集数据性能衰变的短时监测及数据采集设备的选型提供支持,也可为车辆轨迹数据质量的提升提供方法参考。

关键词: 智能交通, 路侧毫米波雷达, 车辆轨迹数据, 数据质量, CRITIC赋权法, 评价指标体系

Abstract:

Roadside sensors have been widely installed on highways to collect full-sample real-time vehicle trajectory data, which supports full time and space control of traffic flow, microscopic driving behavior analysis, etc. However, rapid evaluating data quality is a challenge for management departments. Data quality evaluation methods in previous studies are limited to complicated operation and single dimension, which cannot meet the quality evaluation requirements of real-time vehicle trajectory data in dynamic traffic flow. In order to rapidly evaluate the quality of vehicle trajectory data from roadside millimeter-wave radar, a data quality evaluation method is proposed through mining the information of data. First, based on the typical errors of the measured trajectory data, 9 secondary evaluation metrics are established from four perspectives, including trajectory completeness, consistency, accuracy, and validity. Then, the comprehensive metric is calculated based on the CRITIC weighting method. Finally, an empirical analysis is conducted based on the vehicle trajectory data (3 549 in total) obtained by millimeter-wave radars in four different scenarios. The results show that the installation type and model of the millimeter-wave radar obviously influence the quality of vehicle trajectory data., and that the proposed evaluation method can distinguish the quality differences of vehicle trajectory data effectively. This study provides a support for the short-term performance decay monitoring and the type selecting of roadside sensors. Also, it gives a reference for improving the quality of vehicle trajectory data.

Key words: intelligent transportation, roadside millimeter-wave radar, vehicle trajectory data, data quality, CRITIC weighting method, evaluation metrics system

中图分类号: