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{201417,
        author = {Akshaya S. V and Renjini L and Krishna Rajeev and Vijithra V},
        title = {Ai Driver Error Detection System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {no},
        pages = {97-102},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=201417},
        abstract = {Road accidents caused by driver drowsiness, distraction, and fatigue remain a significant safety concern. This paper presents an AI-based driver error detection system designed to proactively monitor driver behavior and enhance road safety. The proposed system utilizes a dashboard-mounted camera to capture real- time facial expressions, eye movements, and head orientation. Computer vision techniques, including Haar Cascade classifiers for face and eye detection and Convolutional Neural Networks (CNN) for behavior classification, are employed to analyze driver alertness. Key behavioral parameters such as eye closure duration (PERCLOS) and blink frequency are extracted and evaluated to detect drowsiness and distraction. Upon identification of unsafe conditions, the system generates immediate audio and visual alerts to restore driver attention. Additionally, a data logging module records unsafe driving events for further analysis and performance evaluation. The proposed approach provides a non-intrusive, real-time monitoring solution that improves driver safety and supports the development of intelligent driver assistance systems.},
        keywords = {.},
        month = {May},
        }