Gowtham Varma Sagi
Nadiminti Venkata Ramana Murty
Yatish Nayan
N.V.S. Sai Pavan
B. Tanmai Kumar
- Student Department of Computer Science and Engineering, Gayatri Vidya Parishad College for Degree and PG Courses (A), Visakhapatnam Andhra Pradesh India
- Professor Department of Computer Science and Engineering, Gayatri Vidya Parishad College for Degree and PG Courses (A), Visakhapatnam Andhra Pradesh India
- Student Department of Computer Science and Engineering, Gayatri Vidya Parishad College for Degree and PG Courses (A), Visakhapatnam Andhra Pradesh India
- Student Department of Computer Science and Engineering, Gayatri Vidya Parishad College for Degree and PG Courses (A), Visakhapatnam Andhra Pradesh India
- Student Department of Computer Science and Engineering, Gayatri Vidya Parishad College for Degree and PG Courses (A), Visakhapatnam Andhra Pradesh India
Abstract
The well being of a worker in the industrial sector is important and can be a life threatening, if fully not equipped with PPE (Personal Protective Equipment). PPE grants the workers the safety from different life threatening situations like goggles protect from strong flash lighting generated by certain industrial equipment, helmet protect the head when heavy objects fall on the worker. However, many workers fail to properly equip their Personal Protective Equipment, leading to numerous problems and accidents This project main motive is to detect the PPE which is worn by the workers in the industrial sector using CV and Deep Learning to minimize the risk and safeguarding the worker protection. The framework monitors the environment and identifies the objects like helmet, goggles, vest, boots etc and informs the supervisor using the YOLOv8 algorithm which implements faster detection and improved accuracy when detecting smaller objects.
Keywords: Deep learning, Computer Vision, YOLOv8, PPE, Industrial sectors
[This article belongs to International Journal of Industrial and Product Design Engineering(ijipde)]
References
- Shreya Shetye, Srishti Shetty, Srushti Shinde, Chaithanya Madhu and Amrita Mathur, ”Computer Vision for Industrial Safety and Productivity”, in IEEE International Conference on Communication System, Computing and IT Applications (CSCITA 2023)
- Megha Nain, Shilpa Sharma and Sandeep Chaurasia,” Safety and Compliance Management System Using Computer Vision and Deep Learning” in IOP Conf. Series: Materials Science and Engineering
- Hao Wu and Jinsong Zhao, “An intelligent vision-based approach for helmet identification for work safety” in Computers in Industry 100 (2018) 267–277.
- Das, P., Abhi, S. H., Suhreed, F. I. Z., Uddin, J., Jahan, S., Zaman, R., & Kashem, M. A. An Intelligent Industrial Safety and Health Monitoring System for Industry 4.0.
- Sowmya, T., SrinivasaRao, G., Sruthi, C., Tanuja, I., Bhavya, I., & Priya, M. S. (2023). SMART HELMET FOR MINING WORKERS. Journal of Engineering Sciences, 14(04).
- Chhillar, S., Sharma, P., & Singh, R. (2023). Safety Management with Application of Internet of Things, Artificial Intelligence, and Machine Learning for Industry 4.0 Environment. In Handbook of Smart Manufacturing (pp. 329-342). CRC Press.
- Mazumder, F. T., Goswami, P., Toha, T. R., Mondol, A., & Alam, S. M. M. (2022, October). Towards Developing a Smart Air Quality Monitoring and Security System to Ensure Workplace Health and Safety. In Proceedings of International Conference on Fourth Industrial Revolution and Beyond 2021 (pp. 291-303). Singapore: Springer Nature Singapore.
- Aslam, S., & Muqeem, F. (2022, March). Internet of Things Platform for Real Time Automated Safety System Based on Multi Sensor Network and Bluetooth Module. In 2022 5th Conference on Cloud and Internet of Things (CIoT) (pp. 239-246). IEEE.
- Mahbub, M., Rouf, M. A., & Saym, M. M. (2020, December). Industrial Plant Environment Surveillance and Safety Assurance System Based on IoT. In 2020 2nd International Conference on Sustainable Technologies for Industry 4.0 (STI) (pp. 1-4). IEEE.
| Volume | 02 |
| Issue | 01 |
| Received | May 21, 2024 |
| Accepted | June 6, 2024 |
| Published | July 2, 2024 |