Video-based trajectory extraction with deep learning for High-Granularity Highway Simulation (HIGH-SIM)
Video-based trajectory extraction with deep learning for High-Granularity Highway Simulation (HIGH-SIM)
复制标题
DOI：
10.1016/j.commtr.2021.100014
复制
发表时间：
2021-12-01
期刊：
影响因子：
--
通讯作者：
Ghiasi, Amir
中科院分区：
文献类型：
--
作者：
Shi, Xiaowei;Zhao, Dongfang;Ghiasi, Amir
高粒度的车辆轨迹数据可以帮助研究人员开发交通仿真模型，了解交通流特性，从而为道路交通管理提出有见地的策略。提出了一种新的车辆轨迹提取方法，可以从航拍视频中提取高粒度的车辆轨迹。该方法包括视频标定、车辆检测与跟踪、车道线识别和车辆运动特征计算。特别是，作者提出了一种基于蒙特-卡罗的车道标识识别方法来识别每辆车的车道。这是一个具有挑战性的问题，车辆轨迹提取，特别是当航空视频是从高空拍摄。作者应用所提出的方法提取车辆轨迹从几个高分辨率的空中视频记录从直升机。提取的数据集被命名为高粒度公路仿真（HIGH SIM）车辆轨迹数据集。为了证明所提出的方法的有效性并了解HIGH-SIM数据集的质量，我们将HIGH-SIM数据集与众所周知的数据集NGSIM US-101数据集在准确性和一致性方面进行了比较。比较结果表明，HIGH-SIM数据集比NGSIM US-101数据集具有更合理的速度和加速度分布。此外，与NGSIM US-101数据集相比，HIGH-SIM数据集的内部和排间误差较低。为了有利于未来的研究，作者在网上发布了HIGH SIM数据集供公众使用。
High-granularity vehicle trajectory data can help researchers develop traffic simulation models, understand traffic flow characteristics, and thus propose insightful strategies for road traffic management. This paper proposes a novel vehicle trajectory extraction method that can extract high-granularity vehicle trajectories from aerial videos. The proposed method includes video calibration, vehicle detection and tracking, lane marking identifi-cation, and vehicle motion characteristics calculation. In particular, the authors propose a Monte-Carlo-based lane marking identification approach to identify each vehicle's lane. This is a challenging problem for vehicle tra-jectory extraction, especially when the aerial videos are taken from a high altitude. The authors applied the proposed method to extract vehicle trajectories from several high-resolution aerial videos recorded from heli-copters. The extracted dataset is named by the High-Granularity Highway Simulation (HIGH-SIM) vehicle tra-jectory dataset. To demonstrate the effectiveness of the proposed method and understand the quality of the HIGH-SIM dataset, we compared the HIGH-SIM dataset with a well-known dataset, the NGSIM US-101 dataset, regarding the accuracy and consistency aspects. The comparison results showed that the HIGH-SIM dataset has more reasonable speed and acceleration distributions than the NGSIM US-101 dataset. Also, the internal and platoon consistencies of the HIGH-SIM dataset give lower errors compared to the NGSIM US-101 dataset. To benefit future research, the authors have published the HIGH-SIM dataset online for public use.