A computer vision system for the detection and classification of vehicles at urban road intersections

This paper presents a real-time vision system to compute traffic parameters by analyzing monocular image sequences from pole-mounted video cameras at urban crossroads. The system is flexible with respect to road geometry and camera position, permitting data collection from several monitored crosses. It uses a combination of segmentation and motion information to localize and track moving objects on the road plane, utilizing background subtraction and a feature-based tracking methodology. For each detected vehicle, the system is able to describe its path, to estimate its speed and to classify it into seven categories. The classification task relies on a model-based matching technique refined by a feature-based one. Experimental results demonstrate robust, real-time vehicle detection, tracking and classification over several hours of videos taken under different illumination conditions. The system is presently under trial in Trento, a one hundred thousand people town in northern Italy