Title :
Driver body information analysis for distraction state detection
Author :
Kazuhito Sato;Momoyo Ito;Hirokazu Madokoro;Sakura Kadowaki
Author_Institution :
Department of Machine Intelligence and Systems Engineering, Faculty of Systems Science and Technology, Akita Prefectural University Yurihonjo, Japan
Abstract :
For this study, we defined a "concentration state" when a driver performs only driving tasks, and a "distraction state" when a driver performs a driving task and a mental arithmetic task simultaneously. From results of these driving tests, we elucidate the characteristics of safety confirmation behaviors by near-misses according to differences between two driving conditions when approaching an intersection. Specifically, we examine the time-series variation of eye-gaze movements and face orientations before and after encountering a collision near-miss. From analyses conducted by dividing watching behaviors at the intersection approach and safety confirmation behaviors after a temporary stop, we extract behavioral patterns characterizing a "distraction state," acquiring findings to support the construction of a model for predicting risky driving.
Keywords :
"Safety","Bicycles","Face","Accidents","Conferences"
Conference_Titel :
Vehicular Electronics and Safety (ICVES), 2015 IEEE International Conference on
DOI :
10.1109/ICVES.2015.7396886