A Discrete Tracking Based-on Region for Red-light Running Detection

Red-light running problem has been recognized as a significant safety problem in Indonesia as well as throughout the world. This is a frequent and highly dangerous driving act. Reducing this risk behavior depends on understanding its prevalence, as well as the drivers involved. However, it should also improve the infrastructure system in order to be an intelligent system. In this study, modeling and simulations are made to measure the speed of each vehicle that will pass through the intersection to predict the possibility of vehicles violating traffic lights. The detection of vehicle IDs used discrete tracking algorithm base on region. The result showed that the position data and time detection sensor used successfully to determine the average speed, the distance from the intersection and acceleration of the movement of vehicles. From the predicted results, a vehicle violates traffic lights reached 82.68%.