Multi-Type Traffic Conflict Identification at Signalized Intersections Based on LiDAR Point Cloud

Abstract

Traffic conflicts have been widely used for proactive road safety evaluation, and this study develops methods to automatically identify different types of traffic conflict based on LiDAR point cloud data. With 10 h of data collected from a signalized intersection in Harbin, China, trajectories of motorized vehicles, bicycles, and pedestrians were extracted, and methods to handle the issues of trajectory discontinuity, type identification error, and same object with different trajectories were developed. Traffic conflicts between right-turn vehicles and through vehicles, between right-turn vehicles and left-turn vehicles, and between right-turn vehicles and pedestrians were considered, and detailed procedures for calculating the conflict indicators (i.e., time to collision [TTC] and post encroachment time [PET]) of different types were proposed. The identified traffic conflicts were also compared with the ones that were identified manually. A total of 5,352 and 1,366 traffic conflicts were identified by PET ≤ 4 s and TTC ≤ 4 s, respectively. The majority were during the through phase, and traffic conflicts between right-turn vehicles and through vehicles were the most common, followed by conflicts between right-turn vehicles and vulnerable road users (i.e., cyclists and pedestrians).The proposed automatic method considers the actual sizes of involved road users and thus leads to more accurate conflict indicator calculation, with an average accuracy over 90%.