Funding Reference AdI - POSI Program
Dates 2002-12|2005-01

This project aims at developing an Automated Traffic Surveillance system with Computer Vision techniques. In a scientific and technological point of view we pretend to develop real-time algorithms for video sequence analysis of traffic scenes and explore innovative extended field of view camera systems (panoramic), with the final goal of price reduction and performance gain with respect to currently existing systems. In particular we address the applications of measuring traffic flow and detecting abnormal events on highways and critical urban areas. Traffic flow monitoring records statistical data on traffic distribution along time (number of vehicles, average velocity, average wait time on queues, etc.). We propose to develop a system that monitors a traffic region, acquires statistical data on traffic density and makes this data available on the Internet. Automatic event detection can help in speeding-up reaction to abnormal events, like accidents and serious transgressions to traffic rules. We propose to develop a system that detects abnormal events on critical traffic points, records the event history and send alarm signals to control stations.

Research Groups Computer and Robot Vision Lab (VisLab)
Project Partners Observit, Tecnologias de Visão por Computador Lda, AITEK, SRL (Italy), Brisa, Auto-estradas de Portugal, SA
ISR/IST Responsible
José Santos-Victor
Alexandre Bernardino
[1] Jose Melo, Andrew Naftel, Alexandre Bernardino, José Santos-Victor, Retrieval of Vehicle Trajectories and estimation of Lane Geometry using non-Stationary Traffic Surveillance Cameras, Proc. ACIVS 2004 - Advanced Concepts for Intelligent Vision Systems, Brussels, Belgium, 2004 - PDF
[2] Andrew Naftel, Jose Melo, Alexandre Bernardino, José Santos-Victor, Highway Lane Detection and Classification Using Vehicle Motion Trajectories, VIIP 2004 - 4th IASTED International Conference on Visualization, Imaging and Image Processing, Marbella, Spain, 2004
[3] Jose Melo, Andrew Naftel, Alexandre Bernardino, José Santos-Victor, Viewpoint Independent Detection of Vehicle Trajectories and Lane Geometry from Uncalibrated Traffic Surveillance Cameras, Proc. ICIAR - International Conference on Image Analysis and Recognition, Porto, Portugal, 2004 - PDF