Vehicle trajectory dataset from drone videos including off-ramp and congested traffic-Analysis of data quality, traffic flow, and accident risk  

作　　者：Moritz Berghaus Serge Lamberty Jörg Ehlers Eszter Kalló Markus Oeser 

机构地区：[1]Institute of Highway Engineering,RWTH Aachen University,Aachen,52074,Germany Federal Highway Research Institute,Bergisch Gladbach,51427,Germany

出　　处：《Communications in Transportation Research》2024年第1期218-228,共11页交通研究通讯(英文)

基　　金：The work presented in this study is part of the projects BueLaMo(Bürgerlabor Mobiles Münsterland-Citizens'Laboratory Mobile Münsterland)funded by the German Federal Ministry for Education and Research,FeGis+(Früherkennung von Gefahrenstellen im Straβenverkehr-Early Detection of Dangerous Areas in Traffic)funded by the German Federal Ministry for Digital and Transport,and NeMo(Neue Ansätze der Verkehrsmodellierung unter Berücksichtigung komplexer Geometrien und Daten-New traffic models considering complex geometries and data)funded by the German Research Foundation(DFG).

摘　　要：Vehicle trajectory data have become essential for many research fields,such as traffic flow,traffic safety,and automated driving.To make trajectory data useable for researchers,an overview of the included road section and traffic situation as well as a description of the data processing methodology is necessary.In this paper,we present a trajectory dataset from a German highway with two lanes per direction,an off-ramp and congested traffic in one direction,and an on-ramp in the other direction.The dataset contains 8,648 trajectories and covers 87min and an∼1,200m long section of the road.The trajectories were extracted from drone videos using a posttrained YOLOv5 object detection model and projected onto the road surface via three-dimensional(3D)camera calibration.The postprocessing methodology can compensate for most false detections and yield accurate speeds and accelerations.The trajectory data are also compared with induction loop data and vehicle-based smartphone sensor data to evaluate the plausibility and quality of the trajectory data.The deviations of the speeds and accelerations are estimated at 0.45m/s and 0.3m/s^(2),respectively.We also present some applications of the data,including traffic flow analysis and accident risk analysis.

关 键 词：Vehicle trajectory dataset Traffic flow Traffic safety Computer vision 

分 类 号：TN9[电子电信—信息与通信工程]