An Image Processing Based Approach for Real-Time Road Traffic Applications

Traffic engineers require various types of road traffic data to manage the traffic. The current sensors (inductive loops and axle sensors etc.) cannot collect all the data that are of interest to traffic engineers. Most important of all, if the data is to be collected at a different location, the installation of these equipments, which needs to be buried beneath the road, creates serious traffic disturbances. In order to overcome the above problems, many researchers have used vision-based system for collecting and analysing road traffic data. However, these techniques have not yielded good results due to various problems such as inefficiency of background updating, selection of a threshold value, change in ambient lighting etc. In this paper we describe a novel neural network and window-based image processing technique for road traffic applications. We use morphological edge detection techniques to detect vehicles. Once the vehicles have been detected, a back-propagation neural network is used for calculating various traffic parameters. This novel method has been implemented on a Pentium-based microcomputer system and the results are reported online in real-time. We also have compared our system with traditional image processing based systems and the results indicate that our proposed system provides better results than the traditional image processing based systems