A paper titled Using computer vision and street-level videos for pedestrian-vehicle tracking and behaviour analysis, authored by Roberto Ventura, Stella Roussou, Apostolos Ziakopoulos, Benedetto Barabino and George Yannis has been published in Transportation Research Interdisciplinary Perspectives. Using advanced computer vision object detection and feature extraction models, this framework integrates Kalman filtering, homography transformations, and object re-identification to achieve high accuracy. This study utilizes data from roadside video recordings from Athens, Greece. The findings show accuracy rates of 50%-70% in detecting traffic light statuses and identified a 23% discrepancy on average between manual and automated counts of illegal crossings. This paper underscores the potential of computer vision detection systems to provide reliable, real-time data that takes the road network conditions into account, ultimately contributing to safer urban traffic management and informed policy decisions.