A multi-sensor surveillance system for public transport environments

J-L Bruyelle¹ and S.A. Velastin²

¹INRETS, Arcueil, France,
²Kingston University, Kingston, UK

To improve safety and security, public transport camera networks get bigger and bigger. However, operators are only able to monitor a few cameras at any given time. It is therefore highly desirable to automate the monitoring tasks through computer vision. Although considerable work has been carried out in the field of image processing to detect events and measure flows, effective implementation of these tasks in a real-world network has not been fully realized. We describe an approach, consisting of small, localized computers dedicated to local image processing of one or two cameras only. These processors are interconnected through a computer network. This talk describes the implementation of this system, as well as four computer vision applications that have been implemented on it. Two of them are linked to security purposes and deal with intrusions and abnormal stationarities. The two others are related to passenger flow measurements and perform counting of passengers and queue length measurement. They have all been intensively tested in real life conditions within several types of network such as an airport and underground railways. Results from trial results show the efficiency of the tested solutions.

Paper presented at Measuring Behavior 2005 , 5^th International Conference on Methods and Techniques in Behavioral Research, 30 August - 2 September 2005, Wageningen, The Netherlands.

© 2005 Noldus Information Technology bv