Driver's State Monitoring By Function Of Facial Expression Detection For Autonomous Driving
Some driver may be angry when a traffic congestion happens. Anger is thought as crucial risk factor which may
result in severe traffic accidents. Driver’s psychosomatic state adaptive driving support safety function may play effective
role to reduce that kind of traffic accidents. Consequently, detection technology of anger is highly expected. This research
firstly clarified root cause of traffic incidents experiences by means of executing Internet survey. From statistical analysis of
the traffic incidents experiences, major psychosomatic state just before traffic incidents were identified as haste, distraction,
drowsiness and anger. This research focused anger of a driver while driving. By means of using Kohonen neural network,
this research created a technology to detect angry state of a driver in high accuracy. Recently autonomous driving of vehicle
is said to be introduced into commercial market in the near future. A novel driver’s psychosomatic state adaptive driving
support safety function is proposed in cooperation with an autonomous driving unit to reduce the number of traffic accidents.
Index Terms—Traffics incidents, anger, Driver, Kohonen Neural Network, driver’s state monitoring.