A Novel Morphological Edge Detector Based Approach for Monitoring Vehicles at Traffic Junctions

Vehicle detection and monitoring through video image processing is now considered as an attractive and flexible technique. In this paper we describe a novel approach called SMED (separable morphological edge detector), to detect and monitor vehicles in real-time. This technique is applied to the key regions (windows) in order to reduce the amount of data. This method eliminates the need of a background frame, which is an essential but unreliable technique for background based image detection methods. The SMED edge detector has been applied to detect vehicles and monitor their movements at traffic junctions in real-time by using low-cost Pentium4-based standard PCs. The results show that the proposed algorithms can be used in real-world traffic situations for on-line vehicle detection and monitoring applications