Year
2022
Degree Name
Doctor of Philosophy
Department
School of Electrical, Computer and Telecommunications Engineering
Abstract
Monitoring the driver behaviour in real-time is a challenging task as there are several factors that can influence it, resulting in unpredictable mistakes during driving. These factors mainly contribute to inattentive driver state, absent mind, unreliable cornering and speeding, resulting in fatal accidents. Among the several factors affecting the driver behaviour, driver fatigue is the most serious one.
According to Transport for New South Wales Australia, around 1160 deaths were reported from 1688 accidents over the period from 2015-2020, from which approximately 290 deaths were due to driver fatigue, making it the second dangerous factor after speeding. Generally, driver fatigue is due to (a) sleep deprivation during circadian rhythms causing drowsiness, and (b) cognitive underload or overload causing tiredness and inattentiveness. The overload conditions are prompted due to poor visibility at night, heavy traffic and demanding driving tasks on complex roads. On the contrary, underload conditions are induced due to continuous driving on long monotonous highways, and negligible environmental feedback due to smart suspension or shared control systems.
In this thesis, the variations in the body posture under the effect of mental fatigue during driving are explored and studied. In particular, the thesis conducts a series of experiments to detect the underload or passive mental fatigue on long monotonous highway scenario in a simulated driving environment. The variations in the body posture are captured through a wearable motion capture sensor system, which is perceived as good alternatives to the physiological or camera-based methods.
Recommended Citation
Ansari, Shahzeb, Detecting Driver Mental Fatigue Based on Body Posture and Vehicle Parameters: A Feasible Study, Doctor of Philosophy thesis, School of Electrical, Computer and Telecommunications Engineering, University of Wollongong, 2022. https://ro.uow.edu.au/theses1/1338
FoR codes (2008)
0801 ARTIFICIAL INTELLIGENCE AND IMAGE PROCESSING, 0902 AUTOMOTIVE ENGINEERING, 0906 ELECTRICAL AND ELECTRONIC ENGINEERING, 170203 Knowledge Representation and Machine Learning
Unless otherwise indicated, the views expressed in this thesis are those of the author and do not necessarily represent the views of the University of Wollongong.