International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Helmet and Vest Detection System for Industrial Safety |
|---|---|
| ABSTRACT | Construction sites are very dangerous places and workers get hurt very often because of not wearing proper safety equipments like helmet and safety vest. From many many years back, the checking of safety gears was done by humans only which is very slow process and also not so accurate. This problem become more bigger when construction sites are very large and there is only few supervisors to check hundreds of workers. So the need of automatic system was felt very strongly. This project is made to solve this problem by using computer vision and deep learning techniques. The dataset of construction workers images is collected from Roboflow platform and YOLOv8 small model is used for training purpose. The model is trained for 50 epochs with batch size of 16 and image size 640x640 on GPU. After training the model is connected with Flask web application and MongoDB database is used for storing all datas. The system detect helmet and safety vest separately and give compliance status as full, partial or non compliant. Admin dashboard is also made to see all users statistics and violations. The results show good accuracy and the system is working properly for construction safety monitoring purpose. |
| AUTHOR | DHANANJAYA K H, DR. RAGHAVENDRA S P PG Student, Dept. of MCA, Jawaharlal Nehru New College of Engineering, Shivamogga, Karanataka, India Assistant Professor, Dept. of MCA., Jawaharlal Nehru New College of Engineering, Shivamogga, Karanataka, India |
| VOLUME | 184 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1405095 |
| pdf/95_Helmet and Vest Detection System for Industrial Safety.pdf | |
| KEYWORDS | |
| References | 1. Ahmed, R., Hassan, M., & Lee, S. (2022). Deep convolutional neural networks for real-time safety helmet detection in construction environments. Automation in Construction, 138(2), 104230–104245. 2. Ali, K., Zhang, Y., & Zhou, Q. (2023). Lightweight YOLO-based model for PPE detection in edge computing environments. IEEE Access, 11(1), 55678–55690. 3. Banerjee, S., Roy, D., & Ghosh, A. (2024). Real-time helmet detection using hybrid deep learning and computer vision techniques. Expert Systems with Applications, 235(3), 120145–120160. 4. Cao, J., Liu, Z., & Wang, P. (2022). Multi-scale feature fusion for safety helmet detection in complex scenes. Neurocomputing, 489(1), 234–248. 5. Chatterjee, A., Singh, R., & Paul, S. (2023). Attention-guided YOLO framework for construction worker safety monitoring. Applied Soft Computing, 134(2), 109987–110002. 6. Das, P., Mukherjee, S., & Dutta, S. (2021). Deep learning-based PPE compliance detection system for smart construction sites. Journal of Ambient Intelligence and Humanized Computing, 12(6), 6789–6802. 7. Fu, H., Chen, G., & Li, X. (2024). Improved YOLOv7 architecture for safety helmet detection with occlusion handling. Pattern Recognition Letters, 176(1), 45–53. 8. Gupta, V., Sharma, P., & Kumar, N. (2022). Automated PPE detection using transfer learning and deep neural networks. Multimedia Tools and Applications, 81(14), 19875–19892. 9. He, Y., Sun, J., & Zhao, L. (2023). Real-time helmet detection based on efficient deep learning models for surveillance systems. Sensors, 23(9), 4567–4582. 10. Jiang, X., Wu, H., & Lin, Y. (2021). Deep learning-based object detection framework for PPE compliance monitoring. Journal of Safety Research, 79(4), 145–156. 11. Khan, A., Ullah, I., & Park, H. (2024). Vision transformer-based PPE detection in industrial environments. IEEE Transactions on Industrial Electronics, 71(5), 4987–4998. 12. Li, H., Zhang, T., & Xu, D. (2022). Safety helmet detection using enhanced feature pyramid networks. Computer Vision and Image Understanding, 221(2), 103456–103470. 13. Liu, Y., Chen, Q., & Fang, Z. (2023). Robust PPE detection under varying illumination using deep learning. Image and Vision Computing, 132(1), 104678–104690. 14. Mehta, R., Shah, K., & Patel, D. (2021). Intelligent safety monitoring system using YOLO-based helmet detection. Procedia Computer Science, 189(1), 215–222. 15. Nguyen, T., Pham, Q., & Tran, D. (2024). Deep learning approach for real-time PPE detection in smart cities. Sustainable Cities and Society, 101(3), 103987–104002. 16. Patel, S., Joshi, M., & Trivedi, H. (2022). Detection of construction worker safety equipment using deep neural networks. International Journal of Computer Vision, 130(8), 2123–2140. 17. Reddy, V., Kumar, S., & Ramesh, B. (2023). Real-time PPE detection using optimized YOLOv6 architecture. Engineering Applications of Artificial Intelligence, 120(2), 105876–105890. 18. Singh, T., Verma, A., & Kaur, G. (2021). Automated detection of helmet usage using deep learning techniques. Safety Science, 143(1), 105412–105425. 19. Wang, L., Zhou, M., & Deng, Y. (2022). Lightweight deep learning model for safety helmet detection in embedded systems. IEEE Transactions on Neural Networks and Learning Systems, 33(10), 5678–5690. 20. Zhang, Q., Li, S., & Huang, J. (2024). Multi-task learning for simultaneous helmet and vest detection in construction sites. Knowledge-Based Systems, 284(1), 110234–110248. |
