Multiday evaluation of adaptive traffic signal system based on license plate recognition detector data

Abstract

This study evaluates the performance of an adaptive traffic signal control system (ATSCS) based on license plate recognition (LPR) detector data. The LPR detector data can provide abundant individual vehicle-based information for comprehensive, detailed evaluation of traffic signal control. Several measurements including travel time delay, cumulative travel time frequency diagram, Purdue coordination diagram, 95th percentile travel time, and buffer index are applied to reveal the various aspects of traffic signal control performance. A before and after comparison was conducted in the eastbound direction of a road segment, in which the ATSCS was deployed in October 2016 while the time-of-day traffic signal planning was used previously. Results show the improvement in traffic condition in the morning and evening peaks after the deployment of the ATSCS. However, the traffic condition at midnight worsened on certain days after the deployment of the ATSCS.