Automatic region of interest tracking for visual characterization of the driver's behaviour

Recent studies on driver behaviour have shown that perception - mainly visual but also proprioceptive perception plays a key role in the "driver-vehicle-road" system and so considerably affects the driver's decision making. The framework of research work presented here is the behaviour analysis and studies low-cost system (BASIL) based on the real time visual analysis tool called EyeAccessPilot (EAP) system. This system, dedicated to driver's behaviour analysis, collects synchronously all the available embedded information: the visual perception via 2D eye's direction, the trajectory followed, accelerations... In this framework, a new development is presented here in order to allow the analysis of focusing area of a driver in driving situations, via the automatic detection of Regions of Interest. This post-processing tool considers video sequence acquired with the EyeAcessPilot system. As the displacement of the head is effective during driving phase and is not measured, the aim of this work is to track automatically defined Regions Of Interest (ROI) all along the stored video sequence. This automatic tracker is based on detection of singular points in images.