Vehicle Classification For Automatic Traffic Density Estimation

Abstract

Automatic traffic light control at intersection has recently become one of the most active research areas related to the development of intelligent transportation systems (ITS). Due to the massive growth in urbanization and traffic congestion, intelligent vision based traffic light controller is needed to reduce the traffi c delay and travel time especially in developing countries as the current automatic time based control is not realistic while sensor-based tra ffic light controller is not reliable in developing countries. Vision based traffi c light controller depends mainly on traffic congestion estimation at cross roads, because the main road junctions of a city are these roads where most of the road-beds are lost. Most of the previous studies related to this topic do not take unattended vehicles into consideration when estimating the tra ffic density or traffi c flow. In this study we would like to improve the performance of vision based traffi c light control by detecting stationary and unattended vehicles to give them higher weights, using image processing and pattern recognition techniques for much e ffective and e ffecient tra ffic congestion estimation.