A video based real-time vehicle counting system using optimized virtual loop method

Abstract

This paper describes a computer vision system to detect and count moving vehicles on roads. The system uses a real-time traffic video surveillance camera mounted over roads and computes the total number of vehicles which passed the road. Moving vehicle image is extracted using `double difference image `algorithm and counting is accomplished by tracking vehicle movements within a tracking zone, called virtual loop. The system was tested on a video surveillance record file of a road that has a medium-level traffic volume.