PROJECT TITLE :

Automatic Detection of Red Light Running Using Vehicular Cameras - 2017

ABSTRACT:

Red lightweight running is a very common traffic violation. Nowadays, vehicles running red traffic lights are detected by sensors mounted on the streets. But a very little proportion of all traffic lights is equipped with such sensors. For this reason, this work proposes a red lightweight running detection system that analyzes the video captured by a camera within the vehicle. The goal of the proposed algorithm is to monitor the behavior of drivers in public transportation, without any intervention in driving itself, but rather acting in an instructional method. Tests are performed using publicly offered benchmark videos and different recordings taken within the traffic of a large town. The results are compared primarily based on the execution time, accuracy and error rates. The video processing took but one tenth of the video period and therefore the accuracy was up to ninety sixpercent.