The development of safety-oriented research ideas and applications requires fine-grained vehicle trajectory data that not only has high accuracy but also captures a substantial number of critical safety events. This paper introduces the CitySim Dataset, which was devised with a core objective of facilitating safety-based research and applications. CitySim currently has vehicle trajectories extracted from 1140-minutes of drone videos@30 FPS recorded at 12 different locations and we are adding more location. It covers a variety of road geometries including freeway basic segments, weaving segments, expressway merge/diverge segments, signalized intersections, stop-controlled intersections, and intersections without sign/signal control. CitySim trajectories were generated through a five-step procedure which ensured the trajectory accuracy. Furthermore, the dataset provides vehicle rotated bounding box information which is demonstrated to improve safety evaluation. Compared to other video-based trajectory datasets, the CitySim Dataset has significantly more critical safety events with higher severity including cut-in, merge, and diverge events. In addition, CitySim facilitates research towards digital twin applications by providing relevant assets like the recording locations'3D base maps and signal timings. These features enable more comprehensive conditions for safety research and applications such as autonomous vehicle safety and location-based safety analysis.

Read More

• LimSim supports the freewayB and ExpresswayA maps, LimSim is a Long-term Interactive Multi-scenario traffic Simulator, which aims to provide a continuous simulation capability under the complex urban road network.

The dataset documentation and file format description can be found here.

Intersection A Signalized Intersection-USA	Intersection B Non-Signalized Intersection-USA
Intersection C (TBA) Signalized Intersection-USA	Intersection D Consecutive Signalized Intersections-USA
Intersection E Permissive Left Turn Phasing-USA	Intersection F (TBA) Non-Signalized Intersection-USA

Roundabout A One lane roundabout-USA	Roundabout B Two lane roundabout-USA

Collaboration location that will be hosted and distributed by a related team.Please contact the relevant team to access the data

Expressway A Weaving Segment Asia In associate with Southwest Jiaotong University Data Science and Traffic Safety Lab
Expressway B Weaving Segment Asia In associate with Southeast University Renteng Yuan/Dr.QiaoJun Xiang
Freeway B Basic Segment Asia In associate with Southwest Jiaotong University Data Science and Traffic Safety Lab
Freeway C Merge/Diverge Segment Asia In associate with Southwest Jiaotong University Data Science and Traffic Safety Lab
Freeway D (TBA) Merge/Diverge Segment Asia In associate with Hong Kong PolyU Dr.Tony Sze

Digital Twin Base Map	Sumo Carla Co-Simulation	Signal Timing Extraction

VR Driving Simulation	Autonomous Vehicle Simulation	Sensor Simulation
Speed Analysis	Surrogate Safety Measures	Crash Analysis

Automated Roadway Conflicts Identify System (A.R.C.I.S)

Mohamed Abdel-Aty | Ou Zheng | Zijin Wang

Lishengsa Yue | Amr Abdelraouf | Nada Mahmoud

If you use CitySim Dataset in your research , please use the following BibTeX entry.

@article{zhang2023citysim,
    author = {Ou Zheng and Mohamed Abdel-Aty and Lishengsa Yue and Amr Abdelraouf and Zijin Wang and Nada Mahmoud},
    title ={CitySim: A Drone-Based Vehicle Trajectory Dataset for Safety-Oriented Research and Digital Twins},
    journal = {Transportation Research Record},
    year = {2023},
    doi = {10.1177/03611981231185768},
}

@article{zhengdevelopment,
    title={DEVELOPMENT, VALIDATION, AND INTEGRATION OF AI-DRIVEN COMPUTER VISION AND DIGITAL-TWIN SYSTEMS FOR TRAFFIC SAFETY DIAGNOSTICS},
    author={ZHENG, OU}
}

Projects in the community that use CitySim:

• LimSim, LimSim is a Long-term Interactive Multi-scenario traffic Simulator, which aims to provide a continuous simulation capability under the complex urban road network.

See publication built on top of CitySim and ARCIS.