Estimation of driver's mental workload using visual information and heart rate variability

Most of the traffic accidents have been caused by driver's inattention. Therefore, driver monitoring is one of the most important challenges in order to prevent traffic accidents. Some studies for evaluating mental workload during driving have been reported; however driver's mental state should be estimated quantitatively for the future. This paper proposes an estimation method of driver's mental workload using physiological information. We defined mental workload as NASA-TLX score, and used the multiple linear regression to quantify driver's mental workload. As a result, higher accuracy was achieved by considering driver's aggression.