Vision-based monitoring system for detecting red signal crossing

Abstract

Red light running is a leading cause of urban crashes that often results in injury and death. The main reason for this is when the automobile driver fails to stop at the intersections when the signal light is red, and runs over other road users. In this research a computer vision-based low cost system is proposed for continuously monitoring the vehicles crossing the intersections when the signal light is "red" with the help of video cameras placed at the intersections, and penalizing careless drivers accordingly. This monitoring system finds application at all busy intersections. By using this setup people would be more conscious of getting penalty tickets which in turn will discourage them from running red lights. This research is intended to provide a support tool for the law enforcement agencies to proactively ensure that intersections are engineered to discourage red light running. © 2007 Springer.