Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{199521,
        author = {Maddineni jyothish prakash ranga and Kovvuri karthik  varma and Mallidi Pavan kumar and Israelin  Insulata.J},
        title = {Driver Drowsiness Detection System Using Behavioural Analysis and Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {15056-15061},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199521},
        abstract = {Driver drowsiness is a leading cause of road traffic accidents worldwide, contributing to thousands of fatalities and injuries every year. This paper presents the design and implementation of a real-time Driver Drowsiness Detection System that integrates computer vision with deep learning to monitor driver alertness continuously. The system employs OpenCV Haar cascade classifiers for facial and ocular region detection from live webcam video streams, and a custom Convolutional Neural Network (CNN) to classify each detected eye as "Open" or "Closed." A time-based PERCLOS (Percentage of Eye Closure) mechanism triggers an audible alarm when eye closure persists for three or more consecutive seconds. Yawning detection is incorporated as an additional behavioral indicator using a dedicated dataset. The entire pipeline is deployed as a Streamlit web application enabling browser-accessible, real-time monitoring. Evaluation on a diverse test set demonstrates strong classification accuracy, near real-time frame processing rates, and reliable alarm response. The system requires no specialized hardware, making it an affordable and scalable safety solution for passenger vehicles, fleet management, and public transportation.},
        keywords = {Driver Drowsiness Detection, Convolutional Neural Network, Computer Vision, Haar Cascade, PERCLOS, Eye State Classification, Yawning Detection, Road Safety, Stream lit, Fatigue Monitoring, Deep Learning, OpenCV.},
        month = {April},
        }