arXiv cs.CY· Ou Zheng, Ruyi Feng, Yufeng Yang, Shengxuan Ding, Lishengsa Yue, Ye Li, Baichuan Mo, Yunhan Zheng, Minwei Kong, Dingyi Zhuang, Ao Qu, Zhibin Li, Meng Li, Dongjie Wang, Wangyang Ying·· 13 小时前AI 评分31
Ozone：面向交通研究的统一平台
Ozone: A Unified Platform for Transportation Research
AI 导读
研究团队推出统一交通研究平台 Ozone，按硬件、数据、模型、评估四层组织，并以原型层支持部署应用。其数据层通过共享轨迹 schema 打通车辆轨迹、交通冲突、事故重建与数字孪生地图，覆盖 8 国 59 个站点的 19 个轨迹数据集，其中 12 个已完成转换器。
正文 · 原文
Authors:Ou Zheng, Ruyi Feng, Yufeng Yang, Shengxuan Ding, Lishengsa Yue, Ye Li, Baichuan Mo, Yunhan Zheng, Minwei Kong, Dingyi Zhuang, Ao Qu, Zhibin Li, Meng Li, Dongjie Wang, Wangyang Ying
Abstract:Transportation research increasingly depends on heterogeneous data from roadside cameras, UAV imagery, LiDAR, and in-vehicle sensors. Differences in data representations, model interfaces, and evaluation protocols complicate cross-dataset benchmarking and reproducibility. We present Ozone, a unified transportation research platform organized around Hardware, Data, Model, and Evaluation layers, with a Prototype layer supporting deployment-oriented applications. Its data layer links vehicle trajectories, traffic conflicts, reconstructed crashes, and digital-twin maps through a shared trajectory schema. The source inventory spans 19 trajectory datasets recorded at 59 sites in eight countries, with completed converters for 12 sources and adaptation ongoing for seven. The converters align coordinate systems, object classes, oriented bounding boxes, and kinematic fields. A shared implementation of surrogate safety measures supports conflict extraction, while map and motion constraints link crash reports to reconstructed trajectories. CARLA digital-twin maps and SUMO traffic logic connect these records to simulation, model development, and evaluation. Validation on 500 vehicles from four datasets reports mean position, heading, and speed errors below 0.15 m, 2.5°, and 0.3 m/s. A workflow study reports an 85 % reduction in experiment setup time. Case studies demonstrate human-factor experiments and automated-driving safety testing, while the model interfaces support traffic modeling and world-model research. The source code and datasets are publicly available.
| Subjects: | Databases (cs.DB); Computers and Society (cs.CY) |
| Cite as: | arXiv:2604.10959 [cs.DB] |
| (or arXiv:2604.10959v3 [cs.DB] for this version) | |
| https://doi.org/10.48550/arXiv.2604.10959 arXiv-issued DOI via DataCite |
Submission history
From: Ruyi Feng [view email]
[v1]
Mon, 13 Apr 2026 03:55:39 UTC (842 KB)
[v2]
Tue, 19 May 2026 07:10:31 UTC (10,597 KB)
[v3]
Wed, 21 Oct 2026 08:12:46 UTC (20,205 KB)
来源：arXiv cs.CY · arxiv.org