DC Field | Value | Language |
dc.contributor.author | CHACHOUA, AMani | - |
dc.contributor.author | DJABER, ROfaida | - |
dc.date.accessioned | 2024-10-03T09:29:34Z | - |
dc.date.available | 2024-10-03T09:29:34Z | - |
dc.date.issued | 2024 | - |
dc.identifier.uri | https://repository.esi-sba.dz/jspui/handle/123456789/706 | - |
dc.description | Supervisor : Pr. Sidi Mohammed BENSLIMANE Co-supervisor : Dr. Rabab BOUSMAHA | en_US |
dc.description.abstract | The status of the driver is critical, as a significant number of vehicular accidents are
attributed to driver inattention or drowsiness. Implementing a drowsiness detection system
in vehicles can greatly reduce the incidence of such accidents. Given that accidents
can occur from just a momentary lapse in attention, it is imperative to have a driver
monitoring system that operates in real-time. This detection system should be capable of
being deployed on an embedded device while maintaining high accuracy.
In this thesis, we introduce a novel approach to real-time drowsiness detection using
deep learning techniques. Our approach is designed to be implemented on a low-cost
embedded board, ensuring both cost-effectiveness and high performance. The primary
contribution of this thesis is the creation of a real-time driver drowsiness detection system
that leverages computer vision and artificial intelligence on an embedded device. This
system aims to enhance road safety by continuously monitoring the driver’s state and
providing timely alerts to prevent accidents caused by drowsiness. ***
Le statut du conducteur est critique, car un nombre important d’accidents de la route
sont attribu´es `a l’inattention ou `a la somnolence du conducteur. La mise en oeuvre d’un
syst`eme de d´etection de somnolence dans les v´ehicules peut r´eduire consid´erablement
l’incidence de tels accidents. ´Etant donn´e que des accidents peuvent survenir `a la suite
d’un simple manque d’attention momentan´e, il est imp´eratif de disposer d’un syst`eme de
surveillance du conducteur qui fonctionne en temps r´eel. Ce syst`eme de d´etection doit
pouvoir ˆetre d´eploy´e sur un appareil embarqu´e tout en conservant une grande pr´ecision.
Dans cette th`ese, nous introduisons une nouvelle approche de d´etection de la somnolence
en temps r´eel `a l’aide de techniques d’apprentissage profond. Notre approche est
con¸cue pour ˆetre mise en oeuvre sur une carte embarqu´ee `a faible coˆut, garantissant `a
la fois rentabilit´e et hautes performances. La principale contribution de cette th`ese est
la cr´eation d’un syst`eme de d´etection de la somnolence du conducteur en temps r´eel qui
exploite la vision par ordinateur et l’intelligence artificielle sur un appareil embarqu´e.
Ce syst`eme vise `a am´eliorer la s´ecurit´e routi`ere en surveillant en permanence l’´etat du
conducteur et en fournissant des alertes opportunes pour pr´evenir les accidents caus´es
par la somnolence. | en_US |
dc.language.iso | en | en_US |
dc.subject | Driver Monitoring System | en_US |
dc.subject | Drowsiness Detection | en_US |
dc.subject | Deep Learning | en_US |
dc.subject | Artificial Intelligence | en_US |
dc.subject | Computer Vision | en_US |
dc.subject | Embedded System | en_US |
dc.title | Real-time Driver Drowsiness Detection System Using Deep Learning | en_US |
dc.type | Thesis | en_US |
Appears in Collections: | Ingénieur
|