No abstract

No abstract

No abstract

Intelligent transport systems (ITS) are part of our daily lives and are the future of modes of transport. They allow solutions to certain problems such as improving road safety and solving the problem of traffic congestion. This paper presents an effective vehicle tracking and trajectory estimation system to prevent road and highway accident. The system is composed of (i) moving-object detection, (ii) filtering of vehicle candidates, (iii) vehicle tracking, and (iv) trajectory estimation and infraction detection. First, all objects in movement are detected in the first frames. Then, the detected moving objects will be filtered by a set of appropriate processing in order to leave only the objects likely to be vehicles. Kalman filter considered as a good motion predictor will be used in vehicle tracking and trajectory estimation in order to detect offending vehicles. The tests carried out on several roads and highway scene have given very satisfactory results on detecting and tracking vehicle and detecting of continuous line crossing that can be exploited for accident prevention. In addition, Kalman filter gave good results regarding the cars tracking and provides a reliable region for eliminating the interference of shadows and decreasing the false detection rate.

No abstract