TY - JOUR
T1 - Driver Distraction Detection Methods
T2 - A Literature Review and Framework
AU - Kashevnik, Alexey
AU - Shchedrin, Roman
AU - Kaiser, Christian
AU - Stocker, Alexander
PY - 2021/4/20
Y1 - 2021/4/20
N2 - Driver inattention and distraction are the main causes of road accidents, many of which result in fatalities. To reduce road accidents, the development of information systems to detect driver inattention and distraction is essential. Currently, distraction detection systems for road vehicles are not yet widely available or are limited to specific causes of driver inattention such as driver fatigue. Despite the increasing automation of driving due to the availability of increasingly sophisticated assistance systems, the human driver will continue to play a longer role as supervisor of vehicle automation. With this in mind, we review the published scientific literature on driver distraction detection methods and integrate the identified approaches into a holistic framework that is the main contribution of the paper. Based on published scientific work, our driver distraction detection framework contains a structured summary of reviewed approaches for detecting the three main distraction detection approaches: manual distraction, visual distraction, and cognitive distraction. Our framework visualizes the whole detection information chain from used sensors, measured data, computed data, computed events, inferred behavior, and inferred distraction type. Besides providing a sound summary for researchers interested in distracted driving, we discuss several practical implications for the development of driver distraction detection systems that can also combine different approaches for higher detection quality. We think our research can be useful despite - or even because of - the great developments in automated driving.
AB - Driver inattention and distraction are the main causes of road accidents, many of which result in fatalities. To reduce road accidents, the development of information systems to detect driver inattention and distraction is essential. Currently, distraction detection systems for road vehicles are not yet widely available or are limited to specific causes of driver inattention such as driver fatigue. Despite the increasing automation of driving due to the availability of increasingly sophisticated assistance systems, the human driver will continue to play a longer role as supervisor of vehicle automation. With this in mind, we review the published scientific literature on driver distraction detection methods and integrate the identified approaches into a holistic framework that is the main contribution of the paper. Based on published scientific work, our driver distraction detection framework contains a structured summary of reviewed approaches for detecting the three main distraction detection approaches: manual distraction, visual distraction, and cognitive distraction. Our framework visualizes the whole detection information chain from used sensors, measured data, computed data, computed events, inferred behavior, and inferred distraction type. Besides providing a sound summary for researchers interested in distracted driving, we discuss several practical implications for the development of driver distraction detection systems that can also combine different approaches for higher detection quality. We think our research can be useful despite - or even because of - the great developments in automated driving.
KW - automated vehicles
KW - Automotive applications
KW - data systems
KW - distraction detection
KW - driver distraction
KW - driver monitoring
KW - driving distraction
KW - intelligent transportation
KW - vehicle driving
UR - http://www.scopus.com/inward/record.url?scp=85107225291&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2021.3073599
DO - 10.1109/ACCESS.2021.3073599
M3 - Review article
AN - SCOPUS:85107225291
SN - 2169-3536
VL - 9
SP - 60063
EP - 60076
JO - IEEE Access
JF - IEEE Access
M1 - 9405644
ER -