Deep Learning-based Driver Drowsiness Detection and Real-time Alert System

Author(s)	Dr. M. Thejovathi, M. Srinidhi, Akshitha Jain, V. Akshaya
Country	India
Abstract	The Deep Learning–based Driver Drowsiness Detection and Real-Time Alert System aims to enhance road safety by continuously monitoring driver fatigue and issuing timely alerts to prevent accidents caused by drowsy driving. The system uses a real-time webcam feed to capture the driver’s face and eye movements, where OpenCV and Haar Cascade classifiers detect facial features and extract the eye region. These eye images are then processed using a Convolutional Neural Network (CNN) built with TensorFlow and Keras to classify the eye state as open or closed. When both eyes remain closed for a predefined duration, an audible alert is triggered through Pygame to warn the driver. The model is lightweight, non-intrusive, and cost-effective, offering a proactive safety mechanism compared to traditional reactive systems like airbags and seat belts. By integrating computer vision with deep learning, the system provides an efficient, real-time solution to reduce accidents caused by driver fatigue.
Keywords	Driver Drowsiness Detection, Deep Learning, CNN, OpenCV, Haar Cascade, Real-Time Alert System, Road Safety, TensorFlow, Computer Vision.
Field	Engineering
Published In	Volume 7, Issue 4, April 2026
Published On	2026-04-06
DOI	https://doi.org/10.70528/IJLRP.v7.i4.2079
Short DOI	https://doi.org/hbv76v

About IJLRP Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijlrp.com

International Journal of Leading Research Publication