|
|
|
| Crash risk early warning in highway work zone based on road surveillance camera |
Bo WANG1,2,3( ),Changhe LIU1,2,Chi ZHANG1,2,*(),Min ZHANG4,Guidong WU5 |
1. School of Highway, Chang’an University, Xi’an 710064, China
2. Engineering Research Center of Highway Infrastructure Digitalization, Ministry of Education, Xi’an 710000, China
3. School of Civil and Environmental Engineering, Nanyang Technological University, Singapore 639789, Singapore
4. College of Transportation Engineering, Chang’an University, Xi’an 710064, China
5. Sichuan Transportation Research Institute, Sichuan Vocational and Technical College of Communications, Chengdu 611130, China |
|
|
|
Abstract A crash risk early warning method for work zones based on closed-circuit television system was proposed, in order to improve the timely detection of collision risks within highway work zones. Computer vision techniques were employed for vehicle detection, coordinate transformation, and 3D vehicle shape estimation, enabling the extraction of traffic flow and vehicle information within the work zone. Crash risks in the upstream transition section were predicted based on the traffic features at the starting point of the warning area, utilizing the improved time to accident (ITA) as a quantified indicator for crash risk assessment. By integrating the one-dimensional convolutional neural network (1D CNN), long short-term memory (LSTM) and the attention mechanism, a crash risk prediction model based on the 1D CNN+LSTM+Attention (CLA) framework was constructed. Results showed that the proposed data collection method met the needs for crash risk prediction. The proposed ITA exhibits better sensitivity in risk quantification, compared to other conflict indicators. The CLA-based prediction model demonstrates superior accuracy compared to the LSTM and 1D CNN+LSTM models, with a goodness of fit coefficient and root mean square error of 0.805 and 0.359, respectively. The proposed method can provide crash risk warnings for work zones 90 seconds in advance.
|
|
Received: 14 July 2023
Published: 25 May 2024
|
|
|
| Fund: 陕西省自然科学基础研究计划资助项目(2023-JC-YB-391)；国家重点研发计划资助项目(2020YFC1512005)；四川省科技计划资助项目(2022YFG0048)；四川省交通运输厅科技资助项目(2022-ZL-04)；山西省重点研发计划资助项目(202102020101014). |
|
Corresponding Authors:
Chi ZHANG
E-mail: wb1010110wb@chd.edu.cn;zhangchi@chd.edu.cn
|
基于道路监控的高速公路作业区碰撞风险预警
为了更及时地掌握高速公路作业区车辆碰撞风险态势，提出基于闭路电视监控的作业区碰撞风险预警方法. 采用计算机视觉技术进行车辆检测、坐标转换和车辆3D形态估计，获取作业区交通流和车辆信息. 以改进事故时间指数 (ITA) 为上游过渡段的碰撞风险量化指标，依据警告区起点的交通流特征，实现上游过渡段的碰撞风险预测. 通过集成一维卷积神经网络 (1D CNN)、长短期记忆网络 (LSTM) 和注意力机制，构建基于1D CNN+LSTM+Attention (CLA)框架的碰撞风险预测模型. 结果表明：所提数据采集方法满足碰撞风险预测的需求. 相较其他冲突指标，ITA在风险量化中具有更适宜的敏感度. 相较LSTM和1D CNN+LSTM，基于CLA的预警模型准确度更高，其拟合优度确定系数和均方根误差分别为0.805和0.359. 所提方法能够提前90 s为作业区提供碰撞风险预警.
关键词：
公路工程,
作业区,
计算机视觉,
改进事故时间指数,
碰撞风险预警
|
|
| [1] |
贾兴利, 富志鹏, 许金良, 等 高速公路半幅封闭施工区限速标志效能试验[J]. 交通运输工程学报, 2015, 15 (4): 93- 100
JIA Xingli, FU Zhipeng, XU Jinliang, et al Effectiveness test of speed-limit sign in one-way closed work zone for expressway[J]. Journal of Traffic and Transportation Engineering, 2015, 15 (4): 93- 100
|
|
|
| [2] |
United States Department of Transportation National Highway Traffic Safety Administration. Traffic safety facts 2019 [R]. Washington: National Highway Traffic Safety Administration, 2021.
|
|
|
| [3] |
AL-BAYATI A J, ALI M, NNAJI C Managing work zone safety during road maintenance and construction activities: challenges and opportunities[J]. Practice Periodical on Structural Design and Construction, 2023, 28 (1): 04022068
doi: 10.1061/PPSCFX.SCENG-1212
|
|
|
| [4] |
NNAJI C, GAMBATESE J, LEE H W, et al Improving construction work zone safety using technology: a systematic review of applicable technologies[J]. Journal of Traffic and Transportation Engineering: English edition, 2020, 7 (1): 61- 75
doi: 10.1016/j.jtte.2019.11.001
|
|
|
| [5] |
中华人民共和国国务院安全生产委员会. 国务院安全生产委员会关于印发道路交通安全“十三五”规划的通知[EB/OL]. (2017-08-08) [2023-05-22]. https://www.mem.gov.cn/gk/gwgg/agwzlfl/tz_01/201709/t20170907_235227.shtml.
|
|
|
| [6] |
PRAMANIK A, SARKAR S, MAITI J A real-time video surveillance system for traffic pre-events detection[J]. Accident Analysis and Prevention, 2021, 154: 106019
doi: 10.1016/j.aap.2021.106019
|
|
|
| [7] |
HAGHIGHAT A, SHARMA A A computer vision-based deep learning model to detect wrong-way driving using pan-tilt-zoom traffic cameras[J]. Computer-Aided Civil and Infrastructure Engineering, 2023, 38 (1): 119- 132
doi: 10.1111/mice.12819
|
|
|
| [8] |
HU L, OU J, HUANG J, et al Safety evaluation of pedestrian-vehicle interaction at signalized intersections in Changsha, China[J]. Journal of Transportation Safety and Security, 2022, 14 (10): 1750- 1775
doi: 10.1080/19439962.2021.1960662
|
|
|
| [9] |
PAUL S A, NICOLAS S, LUIS M M Large-scale automated proactive road safety analysis using video data[J]. Transportation Research Part C: Emerging Technologies, 2015, 58: 363- 379
doi: 10.1016/j.trc.2015.04.007
|
|
|
| [10] |
AHMED M M, ABDEL-ATY M, LEE J, et al Real-time assessment of fog-related crashes using airport weather data: a feasibility analysis[J]. Accident Analysis and Prevention, 2014, 72: 309- 317
doi: 10.1016/j.aap.2014.07.004
|
|
|
| [11] |
ABDEL-ATY M A, PEMMANABOINA R Calibrating a real-time traffic crash-prediction model using archived weather and ITS traffic data[J]. IEEE Transactions on Intelligent Transportation Systems, 2006, 7 (2): 167- 174
doi: 10.1109/TITS.2006.874710
|
|
|
| [12] |
GUO Y, MA J Leveraging existing high-occupancy vehicle lanes for mixed-autonomy traffic management with emerging connected automated vehicle applications[J]. Transportmetrica A: Transport Science, 2020, 16 (3): 1375- 1399
doi: 10.1080/23249935.2020.1720863
|
|
|
| [13] |
WEN J, WU C, ZHANG R, et al Rear-end collision warning of connected automated vehicles based on a novel stochastic local multivehicle optimal velocity model[J]. Accident Analysis and Prevention, 2020, 148: 105800
doi: 10.1016/j.aap.2020.105800
|
|
|
| [14] |
YANG Y, He K, WANG Y, et al Identification of dynamic traffic crash risk for cross-area freeways based on statistical and machine learning methods[J]. Physica A: Statistical Mechanics and its Applications, 2022, 595: 127083
doi: 10.1016/j.physa.2022.127083
|
|
|
| [15] |
GUO M, ZHAO X, YAO Y, et al A study of freeway crash risk prediction and interpretation based on risky driving behavior and traffic flow data[J]. Accident Analysis and Prevention, 2021, 160: 106328
doi: 10.1016/j.aap.2021.106328
|
|
|
| [16] |
NOH B, YEO H A novel method of predictive collision risk area estimation for proactive pedestrian accident prevention system in urban surveillance infrastructure[J]. Transportation Research part C: Emerging Technologies, 2022, 137: 103570
doi: 10.1016/j.trc.2022.103570
|
|
|
| [17] |
ALI Y, HAQUE M M, MANNERING F A Bayesian generalised extreme value model to estimate real-time pedestrian crash risks at signalised intersections using artificial intelligence-based video analytics[J]. Analytic Methods in Accident Research, 2023, 38: 100264
doi: 10.1016/j.amar.2022.100264
|
|
|
| [18] |
中华人民共和国国家质量监督检验检疫总局, 中国国家标准化管理委员会. 道路交通标志和标线第4部分: 作业区: GB 5768.4−2017 [S]. 北京: 中国标准出版社, 2017.
|
|
|
| [19] |
MENG Q, WENG J Evaluation of rear-end crash risk at work zone using work zone traffic data[J]. Accident Analysis and Prevention, 2011, 43 (4): 1291- 1300
doi: 10.1016/j.aap.2011.01.011
|
|
|
| [20] |
ZHANG C, WANG B, YANG S, et al. The driving risk analysis and evaluation in rightward zone of expressway reconstruction and extension engineering [EB/OL]. [2024-03-22]. https://doi.org/10.1155/2020/8943463.
|
|
|
| [21] |
ZHAO X, WANG G, HE Z, et al A survey of moving object detection methods: a practical perspective[J]. Neurocomputing, 2022, 503: 28- 48
doi: 10.1016/j.neucom.2022.06.104
|
|
|
| [22] |
KIM J, SUNG J Y, PARK S. Comparison of Faster-RCNN, YOLO, and SSD for real-time vehicle type recognition [C]// 2020 IEEE International Conference on Consumer Electronics-Asia . Seoul: IEEE, 2020: 1−4.
|
|
|
| [23] |
MAITY M, BANERJEE S, CHAUDHURI S S. Faster R-CNN and YOLO based vehicle detection: a survey [C]// 2021 5th International Conference on Computing Methodologies and Communication . Erode: IEEE, 2021: 1442-1447.
|
|
|
| [24] |
DU Y, ZHAO Z, SONG Y, et al. Strongsort: make deepsort great again [EB/OL]. (2023-01-31) [2023-05-22]. https://ieeexplore.ieee.org/abstract/document/10032656.
|
|
|
| [25] |
SONG K T, TAI J C Dynamic calibration of pan-tilt-zoom cameras for traffic monitoring[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2006, 36 (5): 1091- 1103
doi: 10.1109/TSMCB.2006.872271
|
|
|
| [26] |
ZHANG X, FENG Y, ANGELOUDIS P, et al Monocular visual traffic surveillance: a review[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23 (9): 14148- 14165
doi: 10.1109/TITS.2022.3147770
|
|
|
| [27] |
中华人民共和国国家质量监督检验检疫总局, 中国国家标准化管理委员会. 道路交通标志和标线 第3部分: 道路交通标线: GB 5768.3—2009 [S]. 北京: 中国标准出版社, 2009.
|
|
|
| [28] |
中华人民共和国交通运输部. 公路工程技术标准: JTGB01—2014 [S]. 北京: 人民交通出版社, 2014.
|
|
|
| [29] |
KANHERE N K, BIRCHFIELD S T A taxonomy and analysis of camera calibration methods for traffic monitoring applications[J]. IEEE Transactions on Intelligent Transportation Systems, 2010, 11 (2): 441- 452
doi: 10.1109/TITS.2010.2045500
|
|
|
| [30] |
WANG K, HUANG H, LI Y, et al. Research on lane-marking line based camera calibration [C]// 2007 IEEE International Conference on Vehicular Electronics and Safety . Beijing: IEEE, 2007: 1−6.
|
|
|
| [31] |
KIM S, HWANG Y A survey on deep learning based methods and datasets for monocular 3D object detection[J]. Electronics, 2021, 10 (4): 517
doi: 10.3390/electronics10040517
|
|
|
| [32] |
宋焕生, 张文涛, 孙勇, 等 高速公路相机自动标定及道路坐标系构建[J]. 中国公路学报, 2022, 35 (9): 90- 103
SONG Huansheng, ZHANG Wentao, SUN Yong, et al Automatic camera calibration and road coordinate system construction in highways[J]. China Journal of High-way and Transport, 2022, 35 (9): 90- 103
|
|
|
| [33] |
王伟, 唐心瑶, 崔华, 等 基于CenterNet的路侧单目视角车辆3D形态精确感知[J]. 中国公路学报, 2022, 35 (9): 104- 118
WANG Wei, TANG Xinyao, CUI Hua, et al Accurate perception of three-dimensional vehicle form in roadside monocular perspective based on CenterNet[J]. China Journal of Highway and Transport, 2022, 35 (9): 104- 118
|
|
|
| [34] |
DUBSKÁ M, HEROUT A, SOCHOR J. Automatic camera calibration for traffic understanding [C]// 2014 British Machine Vision Conference . Nottingham: BMVC, 2014, 4(6): 8.
|
|
|
| [35] |
MAHMUD S M S, FERREIRA L, HOQUE M S, et al Application of proximal surrogate indicators for safety evaluation: a review of recent developments and research needs[J]. IATSS Research, 2017, 41 (4): 153- 163
doi: 10.1016/j.iatssr.2017.02.001
|
|
|
| [36] |
SHI X, WONG Y D, LI M Z F, et al Key risk indicators for accident assessment conditioned on pre-crash vehicle trajectory[J]. Accident Analysis and Prevention, 2018, 117: 346- 356
doi: 10.1016/j.aap.2018.05.007
|
|
|
| [37] |
CALIENDO C, GUIDA M Microsimulation approach for predicting crashes at unsignalized intersections using traffic conflicts[J]. Journal of transportation engineering, 2012, 138 (12): 1453- 1467
doi: 10.1061/(ASCE)TE.1943-5436.0000473
|
|
|
| [38] |
WANG C, XU C, DAI Y A crash prediction method based on bivariate extreme value theory and video-based vehicle trajectory data[J]. Accident Analysis and Prevention, 2019, 123: 365- 373
doi: 10.1016/j.aap.2018.12.013
|
|
|
| [39] |
ZHENG L, ISMAIL K, MENG X Traffic conflict techniques for road safety analysis: open questions and some insights[J]. Canadian Journal of Civil Engineering, 2014, 41 (7): 633- 641
doi: 10.1139/cjce-2013-0558
|
|
|
| [40] |
FILDES B N, RUMBOLD G, LEENING A. Speed behaviour and drivers’ attitude to speeding [R]. Melbourne: Monash University Accident Research Centre, 1991.
|
|
|
| [41] |
HU Y, LI Y, HUANG H, et al A high-resolution trajectory data driven method for real-time evaluation of traffic safety[J]. Accident Analysis and Prevention, 2022, 165: 106503
doi: 10.1016/j.aap.2021.106503
|
|
|
| [42] |
LAVRENZ S M, VLAHOGIANNI E I, GKRITZA K, et al Time series modeling in traffic safety research[J]. Accident Analysis and Prevention, 2018, 117: 368- 380
doi: 10.1016/j.aap.2017.11.030
|
|
|
| [43] |
LANA I, DEL Ser J, VELEZ M, et al Road traffic forecasting: Recent advances and new challenges[J]. IEEE Intelligent Transportation Systems Magazine, 2018, 10 (2): 93- 109
doi: 10.1109/MITS.2018.2806634
|
|
|
| [44] |
WANG K, MA C, QIAO Y, et al A hybrid deep learning model with 1DCNN-LSTM-Attention networks for short-term traffic flow prediction[J]. Physica A: Statistical Mechanics and its Applications, 2021, 583: 126293
doi: 10.1016/j.physa.2021.126293
|
|
|
| [45] |
HUA C, FAN W D. Freeway traffic speed prediction under the intelligent driving environment: a deep learning approach [EB/OL]. [2024-03-22]. https://doi.org/10.1155/2022/6888115.
|
|
|
| [46] |
ZHAO J, YANG X, ZHANG C. Vehicle trajectory reconstruction for intersections: an integrated wavelet transform and Savitzky-Golay filter approach [J]. Transportmetrica A: Transport Science , 2024, 20(2): 2163207.
|
|
|
| [47] |
FU C, SAYED T Comparison of threshold determination methods for the deceleration rate to avoid a crash (DRAC)-based crash estimation[J]. Accident Analysis and Prevention, 2021, 153: 106051
doi: 10.1016/j.aap.2021.106051
|
|
|
| [48] |
SAYED T, BROWN G, NAVIN F Simulation of traffic conflicts at unsignalized intersections with TSC-Sim[J]. Accident Analysis and Prevention, 1994, 26 (5): 593- 607
doi: 10.1016/0001-4575(94)90021-3
|
|
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
