Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Advances in Computer, Signals and Systems
  4. Vol 8, Issue 4, 2024

A Safety Helmet Detection Method Using Adjusted YOLOv8

Download as PDF

DOI: 10.23977/acss.2024.080402 | Downloads: 10 | Views: 67

Author(s)

Minghao Yang 1, Feng Rao 2, Lili Wang 2, Mingsong Bai 1, Xiqing Zang 1

Affiliation(s)

1 Beijing Research Institute of Automation for Machinery Industry, Beijing, 100120, China
2 RIAMB (Beijing) Technology Development Co., Ltd., Beijing, 100120, China

Corresponding Author

Lili Wang

ABSTRACT

Safety production is of paramount importance in protecting the safety, health of workers and assets. Safety helmets play a crucial role across various industries, directly impacting the wearer's life safety. In response to the prevalent issue of many workers not wearing safety helmets, coupled with high cost and risks associated with manual safety helmet detection, current automated methods are difficult to detect safety helmet usage at a large scale, complex on-site environments. This paper proposes a safety helmet detection method based on adjusting YOLOv8. Adjustments to the backbone network of YOLOv8 were replaced by DenseNet121 and appropriate data augmentation methods were designed. This method achieved an accuracy of 96.81% in the Safety Helmet Wearing Dataset. Compared to the original YOLO v8 algorithm, it achieved a 0.74% performance improvement. Our method enhances the accuracy of safety helmet detection, provided important technical support to ensure production safety.

KEYWORDS

Safety helmet detection, YOLOv8, DenseNet, safety helmet wearing dataset

CITE THIS PAPER

Minghao Yang, Feng Rao, Lili Wang, Mingsong Bai, Xiqing Zang, A Safety Helmet Detection Method Using Adjusted YOLOv8. Advances in Computer, Signals and Systems (2024) Vol. 8: 6-11. DOI: http://dx.doi.org/10.23977/acss.2024.080402.

REFERENCES

[1] Lihong Wei, Panpan Liu, Haihui Ren and Dong Xiao. (2024) Research on helmet wearing detection method based on deep learning. Scientific reports, 14(1): 7010.
[2] Kishor Shrestha, Pramen P. Shrestha, Dinesh Bajracharya, and Evangelos A. Yfantis. (2015) Hard-hat detection for construction safety visualization [J]. Journal of Construction Engineering, 2015(1): 1-8.
[3] Xiaohui Liu and Xining Ye. (2014) Skin color detection and Hu moments in helmet recognition research. Journal of East China University of Science and Technology, 3: 365-370.
[4] Junsu Jia, Qingjie Bao and Huiming Tang. (2016) Method for detecting safety helmet based on deformable part model. Application Research of Computers, 33(3): 953-956.
[5] Huang S, Huang J, Kong Y. Attention Guided YOLOv3 for Wearing Safety Helmet Detection[C]//ICCIP 2020: 2020 the 6th International Conference on Communication and Information Processing. 2020.DOI:10.1145/3442555.3442566.
[6] Xitian Long, Wenpeng Cui and Zhe Zheng. (2019) Safety helmet wearing detection based on deep learning. IEEE 3rd information technology, networking, electronic and automation control conference (ITNEC). IEEE, 2019: 2495-2499.
[7] Guang Han, Mengcheng Zhu, Xuechen Zhao and Hua Gao. (2021) Method based on the cross-layer attention mechanism and multiscale perception for safety helmet-wearing detection. Computers and Electrical Engineering, 95: 107458.
[8] Qi Fang, Heng Li, Xiaochun Luo, Lieyun Ding, Hanbin Luo, Timothy M. Rose and Wangpeng An. (2018) Detecting non-hardhat-use by a deep learning method from far-field surveillance videos. Automation in construction, 85: 1-9.
[9] Mingyuan Zhang, Zhiying Cao, Xuefeng Zhao and Zhen Yang. (2019) On the identification of the safety helmet wearing manners for the construction company workers based on the deep learning theory. Journal of Safety and Environment, 19(02): 535-541.
[10] Yijia Zhang, Fusu Xiao and Zheming Lu. (2022) Helmet wearing state detection based on improved YOLOv5s. Sensors, 22(24): 9843.
[11] Yuejing Qian and Bo Wang. (2023) A new method for safety helmet detection based on convolutional neural network. PLoS one, 18(10): e0292970.
[12] Bingyan Lin. (2024) Safety Helmet Detection Based on Improved YOLOv8. IEEE Access.
[13] Ultralytics. (2023) Yolov8. https://github.com/ultralytics/ultralytics
[14] Ultralytics. (2020) Yolov5. https://github.com/ultralytics/yolov5
[15] Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár and C. Lawrence Zitnick. (2014) Microsoft coco: Common objects in context. ECCV 2014, 2014: 740-755.
[16] Gao Huang, Zhuang Liu, Laurens van der Maaten and Kilian Q. Weinberger. (2017) Densely connected convolutional networks. CVPR 2017, 2017: 4700-4708.
[17] Benyang Deng, Xiaochun Lei and Miao Ye. (2020) Safety helmet detection method based on YOLO v4. CIS 2020, 2020: 155-158.
[18] Songbo Chen, Wenhu Tang, Tianyao Li, Huling Zhu, Ye Ouyang and Wenbo Wang. (2020) Detection of safety helmet wearing based on improved faster R-CNN. IJCNN 2020, 2020: 1-7.
[19] Zongzhe Lyu, Hui Xu, Xiao Yang, Yong Wang and Weijian Wang. (2023) Small object detection algorithm of YOLOv5 for safety helmet. Journal of Computer Applications, 43(6): 1943.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 19516
Visits: 297447

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.