Automatic Detection of Red Light Running Using Vehicular Cameras

Abstract

The red traffic light running is a very common areas with greater pedestrian flow, the type and amount of traffic violation. Nowadays, vehicles running red traffic lights are accidents, among others. The rule, in General, is the same applied detected by sensors fixed on the streets. However the very small along the main routes. Percentage of all traffic lights are equipped with such sensors. Is this reason, this work proposes the red light runner detection to be performed by the system that consists of the camera and the computer embedded in the vehicle. An algorithm is also proposed to process the recorded videos and the prototype was implemented. The prototype's goal is to monitor work vehicles without any intervention in driving, acting only in as an educational tool. Tests are performed with video recorded in the streets of Belo Horizonte during the day and with the video benchmark using the implemented prototype. The results are compared based on the execution time and accuracy. The video processing took less one tenth of the video's duration and the accuracy was about 95.8%.