Abstract
Car operation requires advanced brain function. Currently, evaluation of the motor vehicle driving ability of people with higher brain dysfunction is medically unknown and there are few evaluation criteria. The increase in accidents by elderly drivers is a social problem in Japan, and a method to evaluate whether elderly people can drive a car is needed. Under these circumstances, a system to evaluate brain dysfunction and driving ability of elderly people is needed. Gaze estimation research is a rapidly developing field. In this paper, we propose the gaze calculation method by eye and head angles. We used the eye tracking device (TalkEyeLite) made by Takei Scientific Instruments Cooperation. For our image processing technique, we estimated the head angle using the template matching method. By using the eye tracking device and the head angle estimate, we built a system that can be used during actual on-road car operation. In order to evaluate our proposed method, we tested the system on Japanese drivers during on-road driving evaluations at a driving school. The subjects were one instructor of the car driving school and eight general drivers (three 40–50 years old and five people over 60 years old). We compared the gaze range of the eight general subjects and the instructor. As a result, we confirmed that one male in his 40s and one elderly driver had narrower gaze ranges.
Highlights
In recent years, car accidents have occurred due to elderly people and patients with higher brain dysfunction
Since gaze range greatly contributed to car accidents, we evaluated driving ability focusing on gaze range in in which this paper
Inby order to extend the range headWe angle estimation can performed, proposed head angle estimate using markers, and we evaluated of this method; the
Summary
Car accidents have occurred due to elderly people and patients with higher brain dysfunction. The methods for evaluating the driving ability of patients with higher brain dysfunction include off-road assessment by neuropsychological examination and on-road evaluation in an actual vehicle. We proposed a system that combined RGB-D sensor and an electrooculogram (EOG) sensor to estimate the gaze [11,12] This proposed system did not have high enough accuracy to use for car driving evaluation (average error of eyeball angle is over 10 degrees). Eye movement is acquired using an eye tracking device (TalkEyeLite [13]), and the head angle is estimated by image processing technology using the TalkEyeLite’s view camera. We calculated the gaze range of nine subjects and considered the car driving ability using the gaze range
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
