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{168927,
        author = {Vedant Borgaonkar and Mahadev Dudhat and Prasad Misal and Prof. Priyanka Kinage},
        title = {A Survey: Personal Protective Equipment Detection},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {5},
        pages = {2345-2350},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=168927},
        abstract = {In industrial environments, real-time object identification has become crucial for automating various tasks, including the monitoring of Personal Protective Equipment (PPE) usage. Ensuring the proper application of PPE in hazardous areas is essential for enhancing worker safety. Typically, PPE usage is monitored through video streams from security cameras, and when an employee is detected without the required PPE, automatic visual or auditory warnings are triggered to raise awareness. However, most existing solutions rely on cloud-based systems, which require substantial network bandwidth and a reliable internet connection to transmit video data for analysis. This centralized architecture introduces challenges related to network reliability, bandwidth consumption, and privacy.This paper proposes a real-time PPE detection system based on deep learning and edge computing to overcome these limitations. By leveraging Convolutional Neural Networks (CNNs) and deploying the system on low-cost hardware, such as Raspberry Pi and Intel Neural Compute Stick, PPE detection can be conducted locally, reducing bandwidth usage and enhancing system reliability and worker privacy. The proposed system is tested with various deep learning models, evaluating the trade-offs between detection accuracy and processing speed, leading to practical recommendations for real-time deployment in industrial environments.},
        keywords = {Personal Protective Equipment, PPE detection, Deep Learning, Edge Computing, Worker Safety, CNN, YOLO, Raspberry Pi.},
        month = {October},
        }