Left-turn queue spillback identification based on single-section license plate recognition data

Abstract

Left-turn queue spillback occurs when the queue of left-turn or adjacent through traffic exceeds the channelized section's capacity, resulting in discharge flow breakdown and inefficient use of green time. License plate recognition (LPR) systems, which offer lane-based data on individual vehicle discharging, present an ideal data source for the identification of queue spillback. Therefore, this paper proposes a method for left-turn queue spillback identification using single-section LPR data. The proposed method involves defining 10 types of left-turn spillbacks based on the queuing status of the left-turn and adjacent through lanes. Then, a lightweight algorithm is proposed to estimate lane-based queue lengths. At last, a rule-based identification algorithm is developed to specify spillback types by considering the left-turn phasing, estimated queue lengths, and lane capacity. The empirical experiment demonstrates a promising accuracy of 87.28%. Additionally, simulations with five left-turn phasing schemes further validate the proposed method, averaging nearly 90% accuracy in identifying spillbacks.