ITraffic

In order to support safe and efficient driving, it is important to classify the behaviours of vehicles and to understand their interactions on typical traffic scenarios. Until recent years, this task was performed by human operators at traffic control centers, but the huge increase on the number of available cameras requires automatic traffic surveillance systems In the last decades, one of the most important efforts in ITS research has been the development of visual surveillance systems that could help reduce the number of traffic incidents and traffic jams in urban and highway scenarios. Although the large number of systems based on different types of sensors and their relative performance, vision based systems are very useful to collect very rich information about road traffic. Brisa has recently built a Operational Coordinate Center (CCO) and is in the process of installing more than four hundred traffic surveillance cameras as part of his Traffic Telematic System (STR). The primary goal of the project was the detection and tracking of potentially anomalous traffic events along the highway roads. By anomalous events we mean the detection of vehicles that stopped on the highway, vehicles driving in lane's opposite direction and also vehicle that are constantly switching between lanes. The system should be able to identify each vehicle and track its behaviour, and to recognize dangerous situations or events that might results from a chain of such behaviours. The system should be robust to illumination changes and small camera movements, being able to robustly track vehicles against occlusions and crowded events. The promising results obtained with the project BRISA I gave us the opportunity to embrace a solid partnership for R&D through the creation of a ISR-BRISA R&D Laboratory totally funded by BRISA on a annual contract basis, renewable, with the purpose of developing solutions for a wide range of research challenges that needs to be addressed on ITS.