Home > Engineering > Computer Engineering > Special Issue > Smart Innovations in Computer Science and Applications > Driver Drowsiness Detection and Alert System

Driver Drowsiness Detection and Alert System

Call for Papers

Volume-10 | Issue-5

Last date : 27-Oct-2026

Best International Journal
Open Access | Peer Reviewed | Best International Journal | Indexing & IF | 24*7 Support | Dedicated Qualified Team | Rapid Publication Process | International Editor, Reviewer Board | Attractive User Interface with Easy Navigation

Journal Type : Open Access

First Update : Within 7 Days after submittion

Submit Paper Online

For Author

Research Area


Driver Drowsiness Detection and Alert System


Tanmai Nilesh Jiwtode



Tanmai Nilesh Jiwtode "Driver Drowsiness Detection and Alert System" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Special Issue | Smart Innovations in Computer Science and Applications, March 2026, pp.1289-1305, URL: https://www.ijtsrd.com/papers/ijtsrd102031.pdf

Road traffic accidents represent a major global public health crisis, claiming approximately 1.35 million lives annually and causing 20-50 million non-fatal injuries according to the World Health Organization. Driver drowsiness and fatigue are identified as contributing factors in 15-30% of all road crashes across different countries, making drowsiness-related accidents a leading cause of highway fatalities second only to alcohol-impaired driving. Drowsy driving significantly impairs reaction time, attention, decision-making, and vehicle control, with severely fatigued drivers exhibiting impairment levels comparable to legally drunk drivers. Despite widespread recognition of drowsiness dangers, effective countermeasures remain limited, as drivers often fail to recognize their own drowsiness levels or overestimate their ability to continue driving safely. Traditional approaches including driver education, road design improvements, and rumble strips provide limited protection, creating urgent need for active real-time drowsiness detection systems that can warn drivers before accidents occur. This research presents a comprehensive driver drowsiness detection and alert system utilizing computer vision and machine learning techniques to monitor driver physiological and behavioral indicators in real-time, detecting drowsiness onset and issuing timely warnings to prevent accidents, and driving pattern analysis monitoring steering wheel movements, lane deviations, and speed variations revealing attention lapses. The system integrates these indicators using a decision fusion algorithm combining multiple weak signals into robust drowsiness assessment, reducing false positives while ensuring timely detection. The system was developed using Python with OpenCV for computer vision operations, dlib for facial landmark detection, TensorFlow for deep learning models, and deployed on embedded hardware (Raspberry Pi 4) with camera module enabling practical in-vehicle implementation. The dataset for training and evaluation comprised 12,500 driving session recordings from 85 drivers under controlled and naturalistic conditions, totaling over 420 hours of driving data including alert driving, mildly fatigued driving, and severely drowsy driving with ground truth annotations based on driver self-reports, expert observer ratings, and physiological measurements (EEG, ECG). Data collection occurred across various conditions including time of day (daytime, nighttime), road types (highway, urban, rural), weather conditions, and driver demographics (age 22-68, gender balanced) ensuring comprehensive representation. Experimental results demonstrated strong detection performance with 94.7% accuracy in classifying driver states (alert vs drowsy), precision of 93.8% (low false alarm rate), recall of 95.3% (low missed detection rate), and F1-score of 94.5%. Average detection latency was 1.8 seconds from drowsiness onset to alert generation, providing sufficient warning time for driver corrective action. The system achieved 89.2% accuracy on nighttime driving scenarios despite reduced visibility and 91.4% accuracy across different driver demographics. Comparison with single-indicator approaches revealed multi-modal fusion substantially improved performance: EAR-only detection achieved 86.3% accuracy, yawn-only achieved 78.5%, head pose-only achieved 81.7%, while integrated fusion achieved 94.7%, validating the multi-indicator strategy. Real-world validation through simulator-based evaluation with 45 participants demonstrated 92.4% practical accuracy, with 87% of participants rating alert timing as appropriate and 89% expressing willingness to use such a system in their personal vehicles. Subjective feedback indicated the system provided valuable safety benefits without excessive false alarms that would lead to user annoyance and system disablement.

Driver Drowsiness Detection; Computer Vision; Machine Learning; Facial Landmark Detection; Eye Aspect Ratio; Yawn Detection; Head Pose Estimation; Fatigue Monitoring; Advanced Driver Assistance Systems; Road Safety; Real-time Detection; Embedded Systems; OpenCV; dlib.


IJTSRD102031
Special Issue | Smart Innovations in Computer Science and Applications, March 2026
1289-1305
IJTSRD | www.ijtsrd.com | E-ISSN 2456-6470
Copyright © 2019 by author(s) and International Journal of Trend in Scientific Research and Development Journal. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0) (http://creativecommons.org/licenses/by/4.0)

International Journal of Trend in Scientific Research and Development - IJTSRD having online ISSN 2456-6470. IJTSRD is a leading Open Access, Peer-Reviewed International Journal which provides rapid publication of your research articles and aims to promote the theory and practice along with knowledge sharing between researchers, developers, engineers, students, and practitioners working in and around the world in many areas like Sciences, Technology, Innovation, Engineering, Agriculture, Management and many more and it is recommended by all Universities, review articles and short communications in all subjects. IJTSRD running an International Journal who are proving quality publication of peer reviewed and refereed international journals from diverse fields that emphasizes new research, development and their applications. IJTSRD provides an online access to exchange your research work, technical notes & surveying results among professionals throughout the world in e-journals. IJTSRD is a fastest growing and dynamic professional organization. The aim of this organization is to provide access not only to world class research resources, but through its professionals aim to bring in a significant transformation in the real of open access journals and online publishing.

Thomson Reuters
Google Scholer
Academia.edu

ResearchBib
Scribd.com
archive

PdfSR
issuu
Slideshare

WorldJournalAlerts
Twitter
Linkedin