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{201701,
        author = {Harshwardhan Mangesh Sawant and Yash Prashant Patil and Monitkumar Vijay Solanki and Gaurav Asaram Patil and Ujwal Shantaram Chaudhari and Dr. Surekha Hitendra Patil},
        title = {Offline Real-Time Drowsiness Detection Using ESP32-CAM and Mobile Edge AI},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {5751-5756},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=201701},
        abstract = {Road accidents caused by driver fatigue represent a significant public health challenge worldwide, with drowsiness contributing to thousands of crashes annually. This paper presents a practical solution combining the affordability of ESP32-CAM hardware with the processing capability of widely available Android smartphones. The proposed system operates entirely offline through local WiFi communication, eliminating cloud dependency while maintaining real-time performance. Mounted on the vehicle dashboard, the ESP32-CAM continuously streams driver video to a companion Android application that performs fatigue analysis using lightweight computer vision techniques. Key contributions include: (1) complete hardware-software integration using commodity components, (2) on-device machine learning inference achieving 90.2% accuracy at 12 frames-per-second and (3) immediate hardware feedback through ESP32-controlled buzzer and LED alerts. The battery-powered design supports over eight hours of continuous monitoring.},
        keywords = {Driver Drowsiness Detection, ESP32-CAM, Mobile Edge AI, Eye Aspect Ratio, MediaPipe FaceMesh, Support Vector Machine, Real-time Monitoring, Offline Processing, Android Edge Computing, Fatigue Detection},
        month = {May},
        }