This paper aims to investigate the physio-emotional state of the driver in the vehicle cabin using a multimodal approach, comprising context, motion, visual, and audio data, collected beforehand. Driver behavior monitoring is implemented upon the data gained from different types of sensors, including accelerometer, magnetometer, gyroscope, GPS, front-facing camera, microphone, and information retrieved from third-party services. This data is intended to fully describe driver behavior and aid advanced driver assistant systems to fully classify and recognize dangerous driving behavior, and generate alerts on how to eliminate emergency situations. The emotional state of the driver is determined as six basic emotions, including sadness, fear, disgust, anger, surprise, and happiness. This work eventually presents driving style classification, dividing drivers into three groups: normal, ecological, urban, risky, and aggressive driving. This classification may potentially recognize aggressive vehicle drivers on public roads, and, therefore, undertake measures to reduce the risk of traffic accident occurrence.
A Multimodal Approach to Psycho-Emotional State Detection of a Vehicle Driver
Lect. Notes in Networks, Syst.
Proceedings of SAI Intelligent Systems Conference ; 2021 ; Amsterdam September 02, 2021 - September 03, 2021
2021-08-03
12 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Psycho-physical tests in driver selection
Engineering Index Backfile | 1946
Multimodal Detection of Driver Distraction
NTIS | 2017
|Multimodal driver state modeling through unsupervised learning
Elsevier | 2022
|