AI-BASED INTELLIGENT DRIVER MONITORING AND ACCIDENT PREVENTION SYSTEM USING MULTI-SENSOR FUSION
DOI:
https://doi.org/10.63458/ijerst.v4i1.145Keywords:
Artificial Intelligence, Driver Monitoring, Computer Vision, loT, Embedded Systems, Road SafetyAbstract
Road accidents caused by driver fatigue, distraction, impaired driving, and delayed emergency response continue to be a major challenge in intelligent transportation systems. This paper presents an AI-Based Intelligent Driver Monitoring and Accident Prevention System Using Multi-Sensor Fusion, which integrates computer vision, embedded systems, and IoT technologies to improve vehicle safety through continuous driver monitoring. The proposed system employs a camera-based facial analysis algorithm to detect driver fatigue by analyzing eye movement and facial behavior in real time. A multi-sensor framework incorporating an MQ-3 alcohol sensor, MPU6050 motion sensor, and MAX30102 health monitoring sensor continuously evaluates the driver's physical condition and vehicle status. Sensor data are processed using a Raspberry Pi to identify unsafe conditions and execute immediate safety actions such as activating warning alarms, restricting vehicle operation, and initiating emergency response procedures. A GSM communication module transmits alert messages with location information to emergency contacts, while cloud connectivity enables remote monitoring and data logging. Experimental evaluation demonstrates that the integrated multi-sensor approach improves detection reliability, minimizes response time, and enhances overall road safety. The proposed system provides a scalable, low-cost, and intelligent framework suitable for next-generation smart vehicles and advanced driver assistance systems.
References
J. Kim, et al., “AI-integrated autonomous driver monitoring framework combining facial landmark detection with adaptive vehicle control mechanisms,” 2025.
L. Zhang, et al., “Transformer-based driver attention recognition architecture for cognitive fatigue detection,” 2025.
A. Kumar and P. Sharma, “Hybrid CNN-LSTM model for fatigue detection using sequential eye and mouth state analysis,” 2024.
R. Mehra and S. Kulkarni, “Raspberry Pi-based fatigue detection system using OpenCV facial landmark detection and blink frequency monitoring,” 2024.
S. Lee, et al., “Intelligent in-cabin driver monitoring system with infrared imaging for low-light fatigue detection,” 2024.
H. Singh, et al., “Deep learning-based driver inattention detection using hybrid CNN-LSTM for temporal fatigue modeling,” 2023.
M. Torres, et al., “Multimodal driver monitoring framework combining facial expression analysis with steering behavior tracking,” 2023.
Y. Chen, et al., “Edge-computing-based vehicle safety platform for embedded driver monitoring,” 2023.
M. S. Hossain, et al., “IoT-enabled intelligent vehicle safety framework integrating driver monitoring with cloud analytics,” 2022.
K. Verma, et al., “Real-time drowsiness detection using geometric eye feature extraction and supervised classifiers,” 2022.
P. Garcia, et al., “Multimodal driver monitoring integrating wearable physiological sensors with computer vision-based fatigue detection,” 2022.
Dasgupta, et al., “Smart accident detection and emergency alert system using accelerometer sensors with GSM/GPS modules,” 2021.
R. Mehta, et al., “Computer vision-based driver fatigue detection using Haar cascade classifiers and eye closure analysis,” 2021.
S. Abtahi, et al., “Video-based driver fatigue analysis focusing on blink duration and temporal eye dynamics,” 2020.
T. Soukupová and J. Čech, “Eye Aspect Ratio (EAR) for real-time blink detection using facial landmark coordinates,” 2020.
Downloads
Published
How to Cite
Issue
Section
ARK
License
Copyright (c) 2026 M.B.Ramesh, R.Saranraj, C.Sedhuraman, M.Senthilvelan
This work is licensed under a Creative Commons Attribution 4.0 International License.
License Statement
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
Authors retain copyright of their articles and grant International Journal of Engineering Research in Science and Technology (IJERST) the right of first publication.
This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
The journal encourages open access and supports the global exchange of knowledge.
