15th European Conference on Artificial Intelligence
|July 21-26 2002 Lyon France|
Stefania Bandini, Davide Bogni, Sara Manzoni
The aim of the paper is to highlight the importance of alarm correlation in traffic monitoring and control systems, and to propose a knowledge-based solution for developing a module of a traffic monitoring and control system. The Alarm Correlation Module (MCA) integrated with the System for Automatic MOnitoring of Traffic (SAMOT) will be described. The aims of the MCA are to analyze, filter and correlate traffic flow anomalies detected by Video Image Processing (VIP) boards, to create adequate image sequences to be shown on operators Close-Circuit TVs and to display adequate messages in Variable Message Panels to keep motorists informed. Thus, the MCA provides SAMOT with an automatic processing tool that, based on traffic operators' experience and knowledge, supports operators in the interpretation of traffic situations and in the event-driven control of traffic anomalies. The MCA knowledge base implements a model of traffic flow concerning the most relevant traffic patterns and taking into account time and space dependence of detected traffic anomalies. The MCA integrated in SAMOT is a successful example of the knowledge-based approach applied to traffic monitoring and control. The MCA has been developed in collaboration with the SAMOT provider (Project Automation S.p.A.) and the Italian highway company (Societa' Autostrade S.p.A.). After a 6 months trial period, the system is now installed and functioning on two of the most crowded Italian highways (i.e. A7 and A10).
Citation: Stefania Bandini, Davide Bogni, Sara Manzoni: Alarm Correlation in Traffic Monitoring and Control Systems: A Knowledge-Based Approach. In F. van Harmelen (ed.): ECAI2002, Proceedings of the 15th European Conference on Artificial Intelligence, IOS Press, Amsterdam, 2002, pp.638-642.