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{198822,
        author = {Tanushree Chintaman Pagare and Sneha Samir jadhav and Akshada Jagdish Kakade},
        title = {Human Detection Monitoring in Decoiler Area Using Raspberry Pi 5B},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {15353-15355},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198822},
        abstract = {Industrial safety in decoiler zones remains a critical challenge, where unauthorized human presence near high-speed rotating machinery poses severe injury risks. This paper presents an intelligent real-time human detection and monitoring system deployed on a Raspberry Pi 5 (BCM2712, Cortex-A76 @ 2.4 GHz) for use at steel plant decoiler entry points. The system integrates YOLOv8n-based person detection with polygon region-of-interest (ROI) zone monitoring and biometric face recognition to identify, track, and log all personnel entering the restricted zone. A risk-scoring engine aggregates detection signals to issue GRANT, WARN, or DENY access decisions via GPIO-controlled actuators. Evaluated over 150 controlled trials, the system achieves 94.7% face recognition accuracy, 89.6% PPE detection [email protected], and 93.3% overall decision accuracy at a mean latency of 312 ms—well within real-time requirements. The fully edge-deployed pipeline consumes approximately 8 W, requiring no cloud infrastructure, and logs all events to an SQLite database accessible via a Flask web dashboard.},
        keywords = {Decoiler Zone Safety, Edge AI, Face Recognition, Human Detection, Industrial Monitoring, Raspberry Pi 5, Real-Time Vision, YOLOv8.},
        month = {April},
        }