Traffic signs localisation for highways inventory from a video camera on board a moving collection van

The work presented is part of a CEC funded R&D Esprit project called AUTOCAT (Automatic Collection of road Attributes). The aim of the project was to demonstrate the automatic detection and localisation of traffic signs along the roads, in order to trigger the selective acquisition of a high resolution digital picture for sign inventory purpose. A Kalman tracker has been implemented to localise the signs (in 3D) from their apparent motion within the field of view of a wide angle camera, taking into account the camera motion. The whole image processing chain has been tuned on synthetic road-scene image sequences of a custom virtual circuit then validated in the field on the real vehicle demonstrator using the motion information of the embedded inertial navigation system. The results obtained show the successful coupling of an inertial navigation system, providing an accurate camera motion information, with a real time image processing system performing multi-target detection and tracking. It is shown how this application takes advantage of the Kalman filter implementation as an optimal estimator in the case of a moving camera analysing a static scene