Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
A Robust Method for Driver Drowsiness Detection and Analysis using Pertinent Elements
Ist Teil von
2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), 2023, p.1-5
Ort / Verlag
IEEE
Erscheinungsjahr
2023
Link zum Volltext
Quelle
IEEE Electronic Library (IEL)
Beschreibungen/Notizen
Effective sleepiness detection techniques are required in the current situations to improve road safety due to the rising frequency of traffic incidents linked to driver fatigue. In the current world of traffic where people use their own vehicle for travelling long distances, almost 30% of the driver sleepiness causes accidents, and each year about 1 lakh similar incidents are happening. In order to overcome this problem, we can use technology that constantly keeps track of the driver and alerts him periodically whenever the driver feels drowsy or is inattentive while driving. This project can be implemented in two ways, one is using IOT approach, where sensors come into play, and the second approach is Machine Learning model. We have implemented the machine learning model of the project where we have used SVM classifier model to detect face and imutils library for facial landmark detection (eyes and mouth). Then we have developed an algorithm that calculates the Eye Aspect Ratio (EAR) and Mouth Aspect Ratio (MAR). When the driver's eyes are being closed (EAR<0.25) for a long interval of time (>5secs) or driver yawning (MAR>0.75), then we will be generating strong beeps that alerts the driver.