面向稀疏道路的地空交通检测系统事件检测仿真与评价
Traffic Incident Detection Simulation and Assessment for Sparse Roads Using Ground-to-Air Traffic Detection System
DOI: 10.12677/OJTT.2022.113025, PDF,    科研立项经费支持
作者: 刘晓锋*, 赵 彪, 刘军黎, 陈 强:天津职业技术师范大学汽车与交通学院,天津
关键词: 稀疏道路交通监控无人飞机传感器系统数值模拟Sparse Road Traffic Surveillance UAV Sensor System Numerical Simulation
摘要: 面向我国西部地区稀疏低流量道路,建立由视频、无人飞机组成的地空交通检测系统,进行道路事件检测,以提高交通安全。首先,设置道路、交通流、视频、无人飞机、交通事件等参数,采用数值模拟仿真的方式,建立地空交通检测系统事件检测仿真方法。然后,分单一无人飞机检测、单一视频检测、视频–无人飞机联合检测、无人飞机折返检测四种情形,评价交通事件的检测效果。最后,结合库尔勒–库车高速的交通事件检测案例,分析了稀疏道路条件下的无人飞机事件检测适用性。
Abstract: A ground-to-air traffic detection system composed of camera video and unmanned aerial vehicle (UAV) was established to detect traffic incident for the low-volume sparse roads in Western China, so as to improve the traffic safety. First, the parameters of road, traffic flow, camera video, UAV, and traffic incident were set, and numerical simulation was adopted to propose the traffic incident detection method based on the ground-to-air traffic detection system. Then, four scenarios were analyzed, i.e., UAV detection, camera video detection, UAV-camera video detection, and UAV shuttle detection. Finally, a case study was implemented based on the Korla-Kuqa highway, and the applicability of UAV-based incident detection for sparse roads was analyzed.
文章引用:刘晓锋, 赵彪, 刘军黎, 陈强. 面向稀疏道路的地空交通检测系统事件检测仿真与评价[J]. 交通技术, 2022, 11(3): 249-259. https://doi.org/10.12677/OJTT.2022.113025

参考文献

[1] 王兵, 孙文磊, 甘琴瑜. 基于GIS-T的广域稀疏路网交通事故应急救援资源调度技术研究[J]. 公路与汽运, 2010, 9(5): 59-62.
[2] 刘晓锋, 常云涛, 王珣. 稀疏路网条件下的无人飞机交通监控部署方法[J]. 公路交通科技, 2012, 29(3): 124-130.
[3] 刘严磊. 交通事件检测California算法的改进及参数自整定研究[D]: [硕士学位论文]. 重庆: 重庆大学, 2017.
[4] 李琦, 姜桂艳. 高速公路交通事件自动检测算法[J]. 哈尔滨工程大学学报, 2013, 34(9): 1193-1198.
[5] Levin, M. and Krause, G.M. (1978) Incident Detection: A Bayesian Approach. Transportation Research Record, 682, 52-58.
[6] 李红伟, 姜桂艳, 李素兰, 朱宏伟. 基于突变强度的交通事件自动检测算法[J]. 交通运输系统工程与信息, 2019, 19(5): 59-65.
[7] 刘庆华, 丁文涛, 涂娟娟, 方守恩. 优化BPAdaBoost算法及其交通事件检测[J]. 同济大学学报(自然科学版), 2015, 43(12): 1829-1833.
[8] 周伟, 罗石贵. 基于模糊综合识别的事件检测算法[J]. 西安公路交通大学学报, 2001, 21(2): 70-73.
[9] 王武功, 马荣国. 交通事件检测的加权支持向量机算法[J]. 长安大学学报(自然科学版), 2013, 33(6): 84-87.
[10] Liu, X., Peng, Z. and Zhang, L. (2019) Real-Time UAV Rerouting for Traffic Monitoring with Decomposition Based Multi-Objective Optimization. Journal of Intelligent & Robotic Systems, 94, 491-501. [Google Scholar] [CrossRef
[11] Hu, C., Meng, Z., Qu, G., et al. (2021) Distributed Cooperative Path Planning for Tracking Ground Moving Target by Multiple Fixed-Wing UAVs via DMPC-GVD in Urban Environment. In-ternational Journal of Control, Automation and Systems, 19, 823-836. [Google Scholar] [CrossRef
[12] Yao, P., Xie, Z. and Ren, P. (2019) Optimal UAV Route Planning for Coverage Search of Stationary Target in River. IEEE Transactions on Control Systems Technology, 27, 822-829. [Google Scholar] [CrossRef
[13] 邱洪波. 基于交通安全的稀疏公路网道路标志分级体系研究[D]: [硕士学位论文]. 绵阳: 西南科技大学, 2014.
[14] 郭延永, 刘攀, 吴瑶, 杨梦琳. 基于贝叶斯多元泊松-对数正态分布的交通冲突模型[J]. 中国公路学报, 2018, 31(1): 101-109.
[15] 梁倩玉. 稀疏路网交通事件检测与设备布局优化研究[D]: [硕士学位论文]. 上海: 同济大学, 2011.