Quality Assessment Method of Vehicle Trajectory Data from Roadside Perception

doi:10.12141/j.issn.1000-565X.230314

Abstract

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

CLC Number:

U491.6

LEI Cailin, ZHAO Cong, LOU Ren, JI Yuxiong, DU Yuchuan. Quality Assessment Method of Vehicle Trajectory Data from Roadside Perception[J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(6): 56-72.

Figures/Tables 24

Fig.1

Table 1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Table 2

Table 3

Fig.7

Table 4

Table 5

Fig.8

Fig.9

Fig.10

Fig.11

Fig.12

Fig.13

Fig.14

Fig.15

Fig.16

Fig.17

Table 6

Table 7

References 41

1	PATRON-PEREZ A， LOVEGROVE S， SIBLEY G ．A spline-based trajectory representation for sensor fusion and rolling shutter cameras［J］．International Journal of Computer Vision，2015，113（3）：208-219．
2	ZHAO T， XU Y， MONFORT M，et al ．Multi-agent tensor fusion for contextual trajectory prediction［C］∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition．［S. l.］：［s. n.］，2019：12126-12134．
3	LEI C， ZHAO C， JI Y，et al ．Identifying and correcting the errors of vehicle trajectories from roadside millimetre‐wave radars［J］．IET Intelligent Transport Systems，2023，17（2）：418-434．
4	CHEN Z， WU C， HUANG Z，et al ．Dangerous driving behavior detection using video-extracted vehicle trajectory histograms［J］．Journal of Intelligent Transportation Systems，2017，21（5）：409-421．
5	YU R， HAN L， ZHANG H ．Trajectory data based freeway high-risk events prediction and its influencing factors analyses［J］．Accident Analysis & Prevention，2021，154：106085/1-10．
6	杜豫川，都州扬，师钰鹏，等．路侧感知车辆轨迹数据质量智能评估方法［J］．中国公路学报，2021，34（7）：164-176．
	DU Yu-chuan， DU Zhou-yang， SHI Yu-peng，et al ．Intelligent evaluation method for roadside sensing vehicle trajectory data quality［J］．Chinese Journal of Highways，2021，34（7）：164-176．
7	ROCHA T V DA， LECLERCQ L， MONTANINO M，et al ．Does traffic-related calibration of car-following models provide accurate estimations of vehicle emissions？［J］．Transportation Research Part D：Transport and Environment，2015，34：267-280．
8	SHARMA A， ZHENG Z， BHASKAR A ．A pattern recognition algorithm for assessing trajectory completeness［J］．Transportation Research Part C：Emerging Technologies，2018，96：432-457．
9	KESTING A， TREIBER M ．Calibrating car-following models by using trajectory data：methodological study［J］．Transportation Research Record，2008，2088（1）：148-156．
10	SADEQ H， SAYED T ．Automated roundabout safety analysis：diagnosis and remedy of safety problems［J］．Journal of Transportation Engineering，2016，142（12）：04016062/1-8．
11	TAGELDIN A， SAYED T， ISMAIL K ．Evaluating the safety and operational impacts of left-turn bay extension at signalized intersections using automated video analysis［J］．Accident Analysis & Prevention，2018，120：13-27．
12	JI Y， NI L， ZHAO C，et al ．TriPField： a 3D potential field model and its applications to local path planning of autonomous vehicles［J］．IEEE Transactions on Intelligent Transportation Systems，2023，24（3）：3541-3554．
13	ZHAO C， SONG A， ZHU Y，et al ．Data-driven indoor positioning correction for infrastructure-enabled autonomous driving systems： a lifelong framework［J］．IEEE Transactions on Intelligent Transportation Systems，2023，24（4）：3908-3921．
14	FARAH H， DAAMEN W， HOOGENDOORN S ．How do drivers negotiate horizontal ramp curves in system interchanges in the Netherlands？［J］．Safety Science，2019，119：58-69．
15	BEINUM A， FARAH H， WEGMAN F，et al ．Driving behaviour at motorway ramps and weaving segments based on empirical trajectory data［J］．Transportation Research Part C：Emerging Technologies，2018，92：426-441．
16	WANG C， XU C， DAI Y ．A crash prediction method based on bivariate extreme value theory and video-based vehicle trajectory data［J］．Accident Analysis & Prevention，2019，123：365-373．
17	GU X， ABDEL-ATY M， XIANG Q，et al ．Utilizing UAV video data for in-depth analysis of drivers’ crash risk at interchange merging areas［J］．Accident Analysis & Prevention，2019，123：159-169．
18	ZHANG L Y， PENG Z R， SUN D J，et al ．A UAV-based automatic traffic incident detection system for low volume roads［R］．［S. l.］：［s. n.］，2013．
19	COIFMAN B， MCCORD M， MISHALANI R G，et al ．Roadway traffic monitoring from an unmanned aerial vehicle［J］．IEE Proceedings - Intelligent Transport Systems，2006，153（1）：11-20．
20	JIN P J， ARDESTANI S M， WANG Y，et al ．Unmanned aerial vehicle （UAV） based traffic monitoring and management［R］．New Jersey：Center for Advanced Infrastructure and Transportation of Rutgers University，2016．
21	MA W， HE Z， WANG L，et al ．Active traffic management strategies for expressways based on crash risk prediction of moving vehicle groups［J］．Accident Analysis & Prevention，2021，163：106421/1-12．
22	PUNZO V， BORZACCHIELLO M T， CIUFFO B ．On the assessment of vehicle trajectory data accuracy and application to the Next Generation SIMulation （NGSIM） program data［J］．Transportation Research Part C：Emerging Technologies，2011，19（6）：1243-1262．
23	COIFMAN B， LI L ．A critical evaluation of the Next Generation Simulation （NGSIM） vehicle trajectory dataset［J］．Transportation Research Part B：Metho-dological，2017，105：362-377．
24	WANG Z， LU M， YUAN X，et al ．Visual traffic jam analysis based on trajectory data［J］．IEEE Transactions on Visualization and Computer Graphics，2013，19（12）：2159-2168．
25	ZWAHLEN H T， RUSS A， ONER E，et al ．Evaluation of microwave radar trailers for nonintrusive traffic measurements［J］．Transportation Research Record，2005，1917（1）：127-140．
26	KIM S， COIFMAN B ．Assessing the performance of SpeedInfo radar traffic sensors［J］．Journal of Intelligent Transportation Systems，2017，21（3）：179-189．
27	王宝锋．基于机器学习与传感器融合的车辆与车道线识别研究［D］．北京：北京理工大学，2017．
28	HU H ．Measuring the effectiveness of advanced traveler information systems （ATIS）［D］．Raleigh：North Carolina State University，2008．
29	杜豫川，师钰鹏，都州扬，等．智能网联环境下路侧感知单元数据质量在线监测框架［J］．中国公路学报，2022，35（3）：273-285．
	DU Yu-chuan， SHI Yu-peng， DU Zhou-yang，et al ．A framework for online monitoring of data quality of roadside sensing units in an intelligent networked environment［J］．Chinese Journal of Highways，2022，35（3）：273-285．
30	林宇．基于 GNSS 的异常定位序列挖掘方法研究［D］．长春：吉林大学，2020．
31	LI Z， LI X， LIU S，et al ．A study on trajectory planning of hydraulic robotic excavator based on movement stability［C］∥Proceedings of 2016 13th International Conference on Ubiquitous Robots and Ambient Intelligence （URAI）．［S. l.］：IEEE，2016：582-586．
32	YANG C， GIDÓFALVI G ．Trajectory quality assessment based on movement feature stability［C］∥Proceedings of the International Symposium on Location-Based Big Data．Tokyo：［s. n.］，2019．
33	王风伟．车辆轨迹数据质量评价方法研究［D］．哈尔滨：哈尔滨工业大学，2017．
34	MEINEL H H ．Applications of microwaves and millimeter waves for vehicle communications and control in Europe［C］∥Proceedcings of 1992 IEEE MTT-S Microwave Symposium Digest．［S.l.］：IEEE，1992：609-612．
35	施莉娟，朱健，陈小鸿，等．基础交通数据质量评价研究［J］．交通信息与安全，2011，29（5）：57-61．
	SHI Lijuan， ZHU Jian， CHEN Xiaohong，et al ．Study on the quality evaluation of basic traffic data［J］．Traffic Information and Safety，2011，29（5）：57-61．
36	LIU P， YU G， WANG Z，et al ．Object classification based on enhanced evidence theory：radar-vision fusion approach for roadside application［J］．IEEE Transactions on Instrumentation and Measurement，2022，71：1-12．
37	DU L P， SU G C ．new method for target detection of MMW radar［C］∥Proceedings of the 7th International Conference on Signal Processing，2004．［S. l.］：IEEE，2004：2029-2032．
38	DIAKOULAKI D， MAVROTAS G， PAPAYANNAKIS L ．Determining objective weights in multiple criteria problems：the critic method［J］．Computers & Operations Research，1995，22（7）：763-770．
39	CAI X， LEI C， PENG B，et al ．Road traffic safety risk estimation method based on vehicle onboard diagnostic data［J］．Journal of Advanced Transportation，2020，2020：1-13．
40	ZHAO C， SONG A， DU Y，et al ．TrajGAT：a map-embedded graph attention network for real-time vehicle trajectory imputation of roadside perception［J］．Transportation Research Part C：Emerging Technologies，2022，142：103787/1-23．
41	DU Y， QIN B， ZHAO C，et al ．A novel spatio-temporal synchronization method of roadside asynchronous MMW radar-camera for sensor fusion［J］．IEEE transactions on Intelligent Transportation Systems，2021，23（11）：22278-22289．

车辆ID	车型	横向速度/（km·h^-1）	纵向速度/（km·h^-1）	横向坐标/m	纵向坐标/m	时间戳
78	1	0.72	66.60	10.24	272.89	2021-03-09 08：20：36：165
78	0	0.56	70.20	5.86	150.35	2021-03-09 08：19：21：142
61	1	1.25	60.12	6.52	100.24	2021-03-09 07：59：15：351

数据问题	产生原因	可能产生的信息错误
不同车辆相同ID	设备储存ID有限，目标跟踪能力不足	检测轨迹数与实际流量不一致
相同车辆不同ID	物理遮挡，目标识别能力不足	轨迹不完整，断面轨迹数小于实际流量
车辆增检	目标识别能力不足	交通事故误报，断面轨迹数大于实际流量
车型检测错误	目标识别能力不足	交通流车型构成信息存在偏差
位置定位漂移	目标定位不稳定	车辆产生异常交通行为，交通事故误报

雷达编号	安装位置	雷达类型	道路等级	数据时长/min	轨迹数	检测范围长度/m	大型车占比/%
A	1	1	高速公路	20	305	300	83.15
B	2	1	高速公路	20	273	250	80.14
C	3	2	高速公路	20	2 503	350	22.65
D	3	3	高速公路	20	378	200	10.25

雷达	轨迹完整度	流量一致度	车辆ID一致度	车型一致度	纵向定位漂移率	回传时间稳定度	“假倒车”率	异常急动率	交通事故误报率
A	0.44	0.92	2.85	0.29	0.80	0.06	0.20	0.10	0.040 0
B	0.50	0.44	2.70	0.26	0.83	0.07	0.17	0.09	0.030 0
C	0.45	0.71	2.82	0.18	0.94	2.58	0.00	0.23	0.030 0
D	0.08	0.20	1.42	0.17	0.44	1.02	0.00	0.06	0.000 9

二级指标	雷达A	雷达B	雷达C	雷达D
轨迹完整度	0.07	0.08	0.02	0.12
流量一致度	0.19	0.44	0.26	0.11
车辆ID一致度	0.43	0.18	0.2	0.35
车型一致度	0.11	0.12	0.04	0.13
纵向定位漂移率	0.02	0.06	0.00	0.03
回传时间稳定度	0.01	0.04	0.44	0.09
“假倒车”率	0.10	0.02	0.00	0.13
异常急动率	0.02	0.04	0.02	0.01
交通事故误报率	0.04	0.01	0.01	0.03