Howlader Md Mohasin, Haque Md Mazharul
Queensland University of Technology (QUT), School of Civil and Environmental Engineering, Faculty of Engineering, Brisbane, QLD 4000, Australia.
Accid Anal Prev. 2025 Aug;218:108073. doi: 10.1016/j.aap.2025.108073. Epub 2025 May 7.
Recent advancements in artificial intelligence (AI) and traffic sensing technologies provide significant opportunities for real-time crash risk forecasting. While forecasting based on historical crash data yields macroscopic insights into future crash risks, such information is often insufficient for real-time applications. In contrast, traffic conflict techniques (TCTs) leveraged by extreme value theory (EVT) and AI-based video analytics have enabled crash risk estimation to a granular level, presenting a promising potential for real-time applications. This study develops a unified framework of integrating generalized extreme value (GEV) theory with parametric and non-parametric forecasting models to predict opposing-through crash risks at signalized intersections. A deep neural network-based computer vision technique was employed to extract post encroachment time (PET) traffic conflicts from 97 h of video footage. Crash risks were estimated using a non-stationary GEV model, incorporating traffic conflict counts, speed variations, and signal timing characteristics. These risk estimates were then forecasted using autoregressive integrated moving average (ARIMA), gated recurrent unit (GRU), and long short-term memory (LSTM) models to analyze short-term crash trends. Results show that the mean crash frequency estimates fell within the 95 % confidence limits of observed crashes and confirm the adequacy of the developed EVT model in estimating opposing-through crashes. The autoregressive and recurrent neural network models exhibit similar forecasting accuracy for crash risk forecasting, with reliable predictions extending up to 11 future signal cycles. The proposed real-time crash risk forecasting framework can be a crucial component of an intelligent transport system, leading to proactive safety management for signalized intersections.
人工智能（AI）和交通传感技术的最新进展为实时碰撞风险预测提供了重大机遇。虽然基于历史碰撞数据的预测能对未来碰撞风险有宏观洞察，但此类信息对于实时应用往往不够充分。相比之下，由极值理论（EVT）和基于AI的视频分析所利用的交通冲突技术（TCTs）已使碰撞风险估计达到粒度级别，为实时应用展现出广阔潜力。本研究开发了一个统一框架，将广义极值（GEV）理论与参数和非参数预测模型相结合，以预测信号交叉口的对向直行车碰撞风险。采用基于深度神经网络的计算机视觉技术，从97小时的视频片段中提取侵入后时间（PET）交通冲突。使用非平稳GEV模型估计碰撞风险，该模型纳入了交通冲突计数、速度变化和信号定时特征。然后使用自回归积分移动平均（ARIMA）、门控循环单元（GRU）和长短期记忆（LSTM）模型预测这些风险估计值，以分析短期碰撞趋势。结果表明，平均碰撞频率估计值落在观察到的碰撞的95%置信区间内，并证实了所开发的EVT模型在估计对向直行车碰撞方面的充分性。自回归和递归神经网络模型在碰撞风险预测方面表现出相似的预测准确性，可靠预测可延伸至未来11个信号周期。所提出的实时碰撞风险预测框架可以成为智能交通系统的关键组成部分，从而实现对信号交叉口的主动安全管理。
