Abstract: Many automobile accidents are related to drivers lacking required levels of vigilance to properly control their vehicles. In this paper we present a system that monitors the activity of parts of the face, in particular the eyes, in order to predict expressions of somnolence. The input to the system is a sequence of images of the face of a car driver, captured by a video camera. The system makes an assessment based on the movement and position of the eyes and eyelids. The system is tested in a car simulation environment. The results will be presented.
Abstract: A research project on stress assessment is
running at Delft University of Technology since 1992. One of the aims of the project is to develop an instrument for automated stress assessment. The underlying system is based on the analysis of facial expressions, voice analysis and the analysis of physiological signals such as heart rate and blood pressure. Analysis of these multi-medial data takes place in parallel and are based on Artificial Intelligence technology. In each of the parallel subsystems, corresponding to sensor, image and sound data, the functionality is split up into a number of layers: filtering and reduction layer, preprocessing layer, processor layer, application layer and output layer. The results of the analysis are combined by a central interpreter, resulting in an overall stress measure. In this paper the stress assessment is used to monitor vigilancelevels of car drivers with a focus on voice analysis.