Department of Civil Engineering, Sardar Vallabhbhai National Institute of Technology (SVNIT), Ichhchanath, Surat, India.
Int J Inj Contr Saf Promot. 2023 Jun;30(2):239-254. doi: 10.1080/17457300.2022.2147194. Epub 2022 Nov 21.
Un-signalized intersections in India witnessed the maximum number of crashes and fatalities in 2019. The nature of the crash investigation is still largely reactive, where the need for accurate and reliable crash data for effective safety diagnosis is pivotal. In India, crash records are unscientific, and critical details are missing. Therefore, a proactive approach using surrogate safety measures is more promising and prudent in analyzing traffic safety. The present study investigates and models crossing conflicts at un-signalized intersections under mixed traffic conditions. Traffic video data for 14 un-signalized intersections (eight un-signalized three-legged intersections and six un-signalized four-legged intersections) were collected under normal weather conditions. The crossing conflicts were identified and characterized as critical and noncritical conflicts based on the values of post-encroachment time (PET). Conflicts with PET values between -1 s and 1 s were identified as critical conflicts. The observation revealed the existence of both positive and negative PET values. The investigation revealed that crossing conflicts with negative PET values are riskier and more unsafe than conflicts with positive ones. Therefore, the crossing conflicts with positive and negative PETs were modeled separately. The positive and negative PET-based critical crossing conflicts are modeled as a function of traffic flow and intersection geometry-related characteristics using truncated negative binomial regression under a full Bayesian modeling framework. K-fold cross-validation with fivefold was employed to calibrate the model, and RMSE was used to find the best model. The modeling results revealed that the volume and traffic composition of the offending and conflicting stream and intersection geometry significantly influence the number of positive and negative PET-based critical crossing conflicts. The developed models can interest engineers and safety experts to analyze traffic safety and identify critical intersections in urban road networks.
在 2019 年，印度未设置信号的交叉路口发生了最多的事故和死亡。事故调查的性质在很大程度上仍然是被动的，因此需要准确和可靠的事故数据来进行有效的安全诊断。在印度，事故记录缺乏科学性，且关键细节缺失。因此，采用替代安全措施的主动方法在分析交通安全方面更有前途和谨慎。本研究调查并建立了混合交通条件下未设置信号的交叉路口的交叉冲突模型。在正常天气条件下，收集了 14 个未设置信号的交叉路口（8 个未设置信号的三岔路口和 6 个未设置信号的四岔路口）的交通视频数据。根据后侵入时间（PET）的值，将交叉冲突识别并划分为关键冲突和非关键冲突。PET 值在-1 s 到 1 s 之间的冲突被确定为关键冲突。观察结果表明存在正 PET 值和负 PET 值。调查结果表明，负 PET 值的交叉冲突比正 PET 值的交叉冲突更危险和不安全。因此，分别对正 PET 值和负 PET 值的交叉冲突进行建模。基于正 PET 和负 PET 的关键交叉冲突，在全贝叶斯建模框架下，使用截断负二项回归，分别作为交通流量和交叉口几何特征相关特性的函数进行建模。采用五折交叉验证法对模型进行校准，使用均方根误差（RMSE）来找到最佳模型。建模结果表明，冲突和冲突流的流量和交通组成以及交叉口几何形状显著影响基于正 PET 和负 PET 的关键交叉冲突的数量。开发的模型可以引起工程师和安全专家的兴趣，以分析交通安全并识别城市道路网络中的关键交叉口。
