TY - CHAP
T1 - Real-Time Driver Fatigue Monitoring with a Dynamic Bayesian Network Model
AU - Bani, Issam
AU - Akrout, Belhassan
AU - Mahdi, Walid
N1 - Publisher Copyright:
© 2019, Springer Nature Switzerland AG.
PY - 2019
Y1 - 2019
N2 - In this chapter, our objective is to detect the driver fatigue state. To this end, we have integrated the most relevant causes and effects of fatigue in a dynamic Bayesian network. We used the following as the main causes of drowsiness: sleep quality, road environment, and driving duration. On the other hand, we added as consequences real-time facial expressions, such as blinking, yawning, gaze, and head position. The result obtained changes over time and it is repeatedly included in the model to calculate fatigue level. In comparison with a realistic simulation, this model is very effective at detecting driver fatigue.
AB - In this chapter, our objective is to detect the driver fatigue state. To this end, we have integrated the most relevant causes and effects of fatigue in a dynamic Bayesian network. We used the following as the main causes of drowsiness: sleep quality, road environment, and driving duration. On the other hand, we added as consequences real-time facial expressions, such as blinking, yawning, gaze, and head position. The result obtained changes over time and it is repeatedly included in the model to calculate fatigue level. In comparison with a realistic simulation, this model is very effective at detecting driver fatigue.
KW - Driver fatigue
KW - Dynamic Bayesian network
KW - Facial expressions
KW - Hypovigilance
UR - http://www.scopus.com/inward/record.url?scp=85105052895&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-11800-6_8
DO - 10.1007/978-3-030-11800-6_8
M3 - Chapter
AN - SCOPUS:85105052895
T3 - Advances in Predictive, Preventive and Personalised Medicine
SP - 69
EP - 77
BT - Advances in Predictive, Preventive and Personalised Medicine
PB - Springer Science and Business Media B.V.
ER -
