Driver Fatigue Detection using Machine Learning
Year: 2024
Type: article
Abstract: Since driver weariness plays a significant role in traffic accidents, developing trustworthy detection technologies is crucial to improving road safety. In order to track and evaluate driver fatigue levels in real time, this study presents a machine learning (ML) based method. The device records a live video stream and uses computer vision algorithms to detect facial traits like head posture, eye closure rate, and frequency of yawning. Based on these factors, a Convolutional Neural Network (CNN) model is trained to identify drowsiness indicators and send out timely notifications to avert possible mishaps. The suggested method offers an effective and non-intrusive way to reduce fatigue-related accidents on the road, and it shows potential for integration into contemporary automobiles. Our findings show that the system has the potential to greatly improve road safety by recognizing fatigue symptoms with high accuracy.
Authors: Kharat, Tushar, Meshram, Samyank, Kadam, Karan, Kardile, Atharva, Navle, Dr. Mahesh
Institution: Zeal College of Engineering and Research, Pune
Language: English
Subfield: Experimental and Cognitive Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W6893069858
FWCI:
Cites:
Cited by:
Related to: