International Journal of Advanced Culture Technology

The International Promotion Agency of Culture Technology (국제문화기술진흥원)
권호 표지
DOI QR코드

DOI QR Code

A study on Detecting the Safety helmet wearing using YOLOv5-S model and transfer learning

  • Kwak, NaeJoung (Dept. of Cyber and Security, Baejae Univ.) ;
  • Kim, DongJu (Postech Institute of Artificial Intelligence, POSTECH)
  • Received : 2022.02.23
  • Accepted : 2022.03.08
  • Published : 2022.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Occupational safety accidents are caused by various factors, and it is difficult to predict when and why they occur, and it is directly related to the lives of workers, so the interest in safety accidents is increasing every year. Therefore, in order to reduce safety accidents at industrial fields, workers are required to wear personal protective equipment. In this paper, we proposes a method to automatically check whether workers are wearing safety helmets among the protective equipment in the industrial field. It detects whether or not the helmet is worn using YOLOv5, a computer vision-based deep learning object detection algorithm. We transfer learning the s model among Yolov5 models with different learning rates and epochs, evaluate the performance, and select the optimal model. The selected model showed a performance of 0.959 mAP.

Keywords

Acknowledgement

This work was supported by Institute of Information & communications Technology Planning & Evaluation(IITP) grant funded by the Korea government(MSIT) (No.2021-0-01972)

References

  1. S. H. Moon, "A Study on ICT Conversion and Change of Industrial Society," JCCT, Vol. 7, No. 4, pp.653-658, 2021.
  2. S. J. Moon, S. K. Cho, M. S. Jung, S. H. Park, "How to Respond to Complex Disasters on Future Megacities at the Government Level," JCCT, Vol. 7, No.1, pp.211-215, 2021.
  3. M. H., Kim, H. S. Kong, "The Effects of Apartment Facility Maintenance on the Residential Satisfaction of Residents," JCCT, Vol. 6, No. 3, pp. 175-183, 2020.
  4. Rules on OSH(Occupational Safety and Health) standards, Chapter 4.
  5. Y. W. Kim and K. S. Park, "A theoretical study on the shock-absorbing characteristics of safety helmet," Journal of the Ergonomics Society of Korea, Vol. 9, No. 1, pp.29-33, 1990.
  6. M. W. Park, N. Elsafty and Z. Zhu, "Hardhat-wearing Detection for Enhancing On-site Safety of Construction Workers," J. Constr. Eng. Manag. Vol. 141, No. 9, 2015.
  7. N.J. Kwak, D.J. Kim, "Object detection technology trend and development direction using deep learning," IJACT, Vol.8, No. 4, pp.119-128, 2020.
  8. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You only Look Once : Unified, Realtime Object Detection," Proc. the IEEE Conf. on Comp. Vision and Pattern Recognition, pp.779-788, 2015.
  9. G. Liu, S. H. Lee, "Municipal waste classification system design based on Faster-RCNN and YoloV4 mixed model," IJACT, Vol.9, No. 3, pp.305-314, 2021.
  10. https://github.com/ultralytics/yolov5
  11. S. Ren, K. He, R. Girshick, J. Sun, "Faster R-CNN: Towards Real-time Object Detection with Region Proposal Networks," IEEE Trans. Pattern. Anal. Mach. Intell, Vol. 39, pp.1137-1149, 2017. https://doi.org/10.1109/TPAMI.2016.2577031
  12. J. Dai, Y. Li, K. He, J. Sun, "R-FCN: Object Detection via Region-based Fully Convolutional Networks," Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems, Barcelona, Spain, pp. 379-387, 2016.
  13. W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C. Y. Fu, A. C. Berg, "SSD: Single Shot MultiBox Detector," In Computer Vision-ECCV 2016, Lecture Notes in Computer Science; Springer: Cham, Switzerland, 2016.
  14. Q. Fang, H. Li, X. Luo, L. Ding, H. Luo,T. M. Rose, "An, W. Detecting non-hardhat-use by a deep learning method from far-field surveillance videos," Autom. Constr. Vol. 85, pp. 1-9, 2018. https://doi.org/10.1016/j.autcon.2017.09.018
  15. J. Wu, N. Cai, W. Chen, H. Wang, G. Wang, "Automatic detection of hardhats worn by construction personnel: A deep learning approach and benchmark dataset," Autom. Constr., Vol. 106, 102894.
  16. J. Mistry, A. K. Misraa, M. Agarwal, A. Vyas, V. M. Chudasama, and K. P. Upla, "An automatic detection of helmeted and non- helmeted motorcyclist with license plate extraction using convolutional neural network." Proc. of 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA), IEEE, pp. 1-6, 2017.
  17. J. Park, S. Jeon, J. Jeon, and J. Kim, "A study on deep learning based personal protective equipment detection," in Proc. 2020 The Korean Inst. of Broadcast and Media Eng. Summer Conf., pp. 650-651, online, Jul. 2020.
  18. M. Tan, R. Pang, Q. V. Le, "EfficientDet: Scalable and Efficient Object Detection," arXiv preprint arXiv:1911.09070v4, 2020.
  19. B. Liu, Y. Wei, Y. Zhang, and Q. Yang, "Deep neural networks for high dimension, low sample size data." Proc. of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI-17, Melbourne, pp. 2287-2293, 2017.
  20. L. Shao, F. Zhu, and X. Li, "Transfer learning for visual ategorization: A survey." IEEE Transactions on Neural Networks and Learning Systems, Vol. 26, No. 5, pp. 1019-1034, 2015. https://doi.org/10.1109/TNNLS.2014.2330900
  21. Kaggle Helmet Dataset, https://www.kaggle.com/vodan37/yolo-helmethead
  22. M. Everingham, L. Van Gool, C. K. Williams, J. Winn, and A. Zisserman, "The pascal visual object classes (voc) challenge." International Journal of Computer Vision, Vol. 88, No. 2, pp. 303-338, 2010. https://doi.org/10.1007/s11263-009-0275-4