Department of Civil and Environmental Engineering, Korea Advanced Institute of Science and Technology, 291 Daehak-ro, Yuseung-gu, Daejeon, South Korea.
Accid Anal Prev. 2021 Jun;155:106104. doi: 10.1016/j.aap.2021.106104. Epub 2021 Apr 2.
In the past decade, the number of road traffic accidents and fatalities has remained about the same level. One of strategies to protect vulnerable road users (VRUs) is to analyze the factors that cause traffic accident and then to deploy safety facilities. However, most traffic safety systems currently in operation rely on historical data, which is post-facto approach. Thus, it is necessary to prevent accident in advance and to respond in proactive manner before the accident. In this study, we propose a framework for potential pedestrian risk analysis using a multi-dimensional on-line analytical processing (OLAP), called SafetyCube, which enables decision-makers to understand the situations by scrutinizing interactive behaviors between vehicle and pedestrian. First, we collect the behavioral features of traffic-related objects (e.g., vehicles and pedestrians) extracted from closed circuit televisions (CCTVs) deployed on crosswalks throughout the overall urban, and accumulate them in a data warehouse over an extended period in order to construct a data cube model. Then, we conduct comprehensive analyses in multi-dimensional perspective using OLAP operations by varying the abstraction levels. Our analytical experiments are based on three scenarios, and the results show that the vehicle's movement patterns before entering the crosswalk, patterns of changes in speed of vehicles approaching to pedestrians, and so on. Through these results from the proposed analytical system, decision-makers can gain a better understanding of how the vehicles and pedestrians behave near the crosswalk by visualizing their interactions. Further, these insights would be reflected to improve the road environment safer. In order to validate the feasibility and applicability of the proposed system, we apply it to various crosswalks in Osan city, South Korea.
在过去的十年中，道路交通事故和死亡人数保持在大致相同的水平。保护弱势道路使用者（VRU）的策略之一是分析导致交通事故的因素，然后部署安全设施。然而，目前运行的大多数交通安全系统依赖于历史数据，这是事后的方法。因此，有必要提前预防事故，并在事故发生之前主动做出响应。在这项研究中，我们提出了一个使用多维联机分析处理（OLAP）的潜在行人风险分析框架，称为 SafetyCube，它使决策者能够通过仔细检查车辆和行人之间的交互行为来了解情况。首先，我们从整个城市的十字路口部署的闭路电视（CCTV）中收集与交通相关的对象（例如车辆和行人）的行为特征，并将其在数据仓库中长时间积累，以构建数据立方体模型。然后，我们通过使用 OLAP 操作在多维角度进行全面分析，从而改变抽象级别。我们的分析实验基于三个场景，结果表明车辆在进入十字路口之前的行驶模式、接近行人的车辆速度变化模式等。通过该分析系统的结果，决策者可以通过可视化它们的交互来更好地了解车辆和行人在十字路口附近的行为方式。此外，这些见解将反映在改善道路环境安全方面。为了验证所提出系统的可行性和适用性，我们将其应用于韩国乌山的各种十字路口。
