Industrial Safety Gear Detection And Attendance Monitoring System

The Industrial Safety Gear Detection and Attendance Monitoring System provides a practical solution for automating safety compliance and access control in industrial environments. By combining facial recognition with PPE detection, the system ensures that only authorized and properly equipped individuals are allowed entry. This reduces manual supervision, minimizes human error, and strengthens overall workplace safety. The integration of AI-based processing with hardware control enables real-time decision-making and efficient system operation. The modular architecture, consisting of perception, logic, and control layers, allows flexibility for future improvements and scalability. Additionally, the inclusion of logging and cloud storage ensures proper record-keeping, making the system reliable for auditing and monitoring purposes. Overall, the system demonstrates how intelligent automation can enhance both security and safety standards in industries. With its cost-effective design and capability to operate in real-time conditions, it serves as a strong foundation for developing more advanced smart safety systems in the future.

1.     Y. Li, H. Wei, Z. Han, J. Huang, and W. Wang, “Deep Learning-Based Safety Helmet Detection in Engineering Management Based on Convolutional Neural Networks,” Advances in Civil Engineering, Central South University, Changsha, China, Volume 2020, pp. 1-10, September 2020. 2.     W. Fang, L. Wang, and P. Ren, “Tinier-YOLO: A Real- Time Object Detection Method for Constrained Environments,” IEEE Access, Jiangnan University, Wuxi, China, Volume 7, pp. 137 920–137 930, 3.      December 2019. 4.     A. Aboah, B. Wang, U. Bagci, and Y. Adu-Gyamfi, “Real-Time Multi-Class Helmet Violation Detection Using Few-Shot Data Sampling Technique and YOLOv8,” arXiv preprint, Northwestern University and University of Missouri-Columbia, USA, arXiv:2304.08256, April 2023. 5.     Z. Liu, L. Zhang, and T. Zhao, “Automatic Detection of Safety Helmet Wearing Based on Improved YOLOv5 Algorithm,” Sensors, Shandong University of Science and Technology, Qingdao, China, Volume 22, Article No. 8501, 2022. 6.     R. Rubaiyat, A. Shrestha, K. Waranusast, and J. Li, “Helmet Detection on Construction Sites Using Computer Vision and Deep Learning,” Journal of Safety Research, Chiang Mai University, Thailand, Volume 77, pp. 1-10, 2021. 7.     Y. Zhao, H. Fang, and Y. Luo, “Improving Safety Compliance on Construction Sites Using CNN-Based PPE Detection,” Automation in Construction, Tongji University, Shanghai, China, Volume 138, Article No. 104250, 2022. 8.     J. Terven and D. Cordova-Esparza, "A Comprehensive Review of YOLO: From YOLOv1 to YOLOv8 and Beyond," arXiv preprint, arXiv:2304.00501, April 2023. (Essential for justifying the choice of YOLOv8). 9.      M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. C. Chen, "MobileNetV2: Inverted Residuals and Linear Bottlenecks," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4510-4520, 2018. (Relevant for the lightweight facial embedding extraction logic). 10.  V. Bazarevsky, Y. Kartynets, A. Vakunov, K. Raveendran, and M. Grundmann, "Blazeface: Sub- millisecond Neural Face Detector on Mobile GPUs," arXiv preprint, arXiv:1907.05047, 2019. (Supports the rationale for real-time face localization at entry points).