RESUMO
Unobtrusive monitoring of driver mental states has been regarded as an important element in improving the safety of existing transportation systems. While many solutions exist relying on camera-based systems for e.g., drowsiness detection, these can be sensitive to varying lighting conditions and to driver facial accessories, such as eye/sunglasses. In this work, we evaluate the use of physiological signals derived from sensors embedded directly into the steering wheel. In particular, we are interested in monitoring driver stress levels. To achieve this goal, we first propose a modulation spectral signal representation to reliably extract electrocardiogram (ECG) signals from the steering wheel sensors, thus allowing for heart rate and heart rate variability features to be computed. When input to a simple logistic regression classifier, we show that up to 72% accuracy can be achieved when discriminating between stressful and non-stressful driving conditions. In particular, the proposed modulation spectral signal representation allows for direct quality assessment of the obtained heart rate information, thus can provide additional intelligence to autonomous driver monitoring systems.
Assuntos
Condução de Veículo , Algoritmos , Eletrocardiografia , Coração , Frequência CardíacaRESUMO
To develop a suitable automobile design as per each driver's characteristics and state, it is important to understand the brain function in acquiring driving skills. Reportedly, the brain structures of professionals, such as athletes and musicians, and those who have received training in special skills, undergo changes with training. However, the development process of the brain in terms of acquiring driving skills has not yet been clarified. In this study, we evaluated the effects of driving training on the brain and observed an increase in the volume of the right cerebellum after short-term training (3 days). The right cerebellum is responsible for controlling the right hand and right foot, which are important for driving. Drivers train to control a vehicle smoothly at high speeds at gymkhana and pylon slalom courses, which are often used in motor sports. The brain structure was analyzed before and after training using magnetic resonance imaging. Voxel-based morphometry was used to assess possible structural changes. First, the lap times after training were clearly shortened and vehicle dynamics were more stable, indicating that the drivers' skill level clearly improved. Second, brain structural analysis revealed a volumetric increase in the right cerebellum. The cerebellum is involved in the process of learning sensory motor skills, such as smooth steering and pedal operations, driving course shape, and vehicle size perception. These results suggest a new inner model for driving operation and support the hypothesis that motor learning affects the cerebellum during vehicle driving training.