AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Journal of Intelligent Construction Article
PDF (32.1 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Research Article | Open Access

A YOLO-based intelligent detection algorithm for risk assessment of construction sites

Ruiyang Feng, Yu Miao, Junxing Zheng( )
School of Civil and Hydraulic Engineering, Huazhong University of Science and Technology, Wuhan 430074, China
Show Author Information

Abstract

Construction safety accidents have become increasingly frequent in recent years, leading to numerous casualties and substantial property losses. These incidents are often attributed to inadequate supervision on construction sites and workers’ low safety awareness. Traditional manual management methods, which are labor-intensive and resource-consuming, are no longer effective. Therefore, this study proposes a novel single-stage model based on YOLOv8s, designed for two primary purposes: detecting workers’ personal protective equipment and monitoring and recognizing when workers enter hazardous areas. The model provides real-time feedback on detection results to reduce the incidence of construction accidents. Additionally, a brief design for distance calculation was introduced. The model was trained for 200 iterations on a Roboflow dataset comprising 103,500 annotated images. Experimental results showed that YOLOv8s outperformed YOLOv8n, YOLOv5s, and YOLOv5n in detection performance, achieving a mean average precision with the intersection over union (IoU) threshold set to 50% (mAP50) of 84.0%, precision of 85.0%, and recall of 60.5% across 9 detection classes. By leveraging artificial intelligence technology, this study aims to offer an effective method for enhancing construction site safety, which can be further improved with additional images and a more robust network architecture.

Keywords

YOLOv8construction safetyobject detectiondeep learning

References

[1]

J. J. Chen, J. N. Zhu, Z. Li, et al. YOLOv7-WFD: A novel convolutional neural network model for helmet detection in high-risk workplaces. IEEE Access, 2023, 11: 113580–113592.
Crossref Google Scholar
[2]

X. H. Zhou, S. L. Shen, Y. S. Xu, et al. Analysis of production safety in the construction industry of China in 2018. Sustainability, 2019, 11: 4537.
Crossref Google Scholar
[3]

Y. LeCun, Y. Bengio, G. Hinton. Deep learning. Nature, 2015, 521: 436–444.
Crossref Google Scholar
[4]
M. R. Minar, J. Naher. Recent advances in deep learning: An overview. 2018, arXiv:1807.08169, arXiv.org e-print archive. https://arxiv.org/abs/1807.08169 (accessed 2024-02-05
[5]

A. Krizhevsky, I. Sutskever, G. E. Hinton. ImageNet classification with deep convolutional neural networks. Commun ACM, 2017, 60: 84–90.
Crossref Google Scholar
[6]

Y. Lecun, L. Bottou, Y. Bengio, et al. Gradient-based learning applied to document recognition. Proc IEEE, 1998, 86: 2278–2324.
Crossref Google Scholar
[7]
K. Simonyan, A. Zisserman. Very deep convolutional networks for large-scale image recognition. In: Proceedings of the 3rd International Conference on Learning Representations, San Diego, USA, 2015.
[8]
J. Redmon, S. Divvala, R. Girshick, et al. You only look once: Unified, real-time object detection. In: Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, 2016.
Crossref
[9]
W. B. Lan, J. W. Dang, Y. P. Wang, et al. Pedestrian detection based on YOLO network model. In: Proceedings of 2018 IEEE International Conference on Mechatronics and Automation (ICMA), Changchun, China, 2018: pp 1547–1551.
Crossref
[10]
D. Reis, J. Kupec, J. Hong, et al. Real-time flying object detection with YOLOv8. 2023, arXiv:2305.09972, arXiv.org e-print archive. https://arxiv.org/abs/2305.09972 (accessed 2024-02-05
[11]

J. Y. Li, Z. F. Su, J. H. Geng, et al. Real-time detection of steel strip surface defects based on improved YOLO detection network. IFAC-PapersOnLine, 2018, 51: 76–81.
Crossref Google Scholar
[12]

Y. C. Du, N. Pan, Z. H. Xu, et al. Pavement distress detection and classification based on YOLO network. Int J Pavement Eng, 2021, 22: 1659–1672.
Crossref Google Scholar
[13]

Y. D. Zhang, Z. C. Dong, S. H. Wang, et al. Advances in multimodal data fusion in neuroimaging: Overview, challenges, and novel orientation. Inf Fusion, 2020, 64: 149–187.
Crossref Google Scholar
[14]

S. H. Wang, M. E. Celebi, Y. D. Zhang, et al. Advances in data preprocessing for biomedical data fusion: An overview of the methods, challenges, and prospects. Inf Fusion, 2021, 76: 376–421.
Crossref Google Scholar
[15]
D. Thakur, P. Pal, A. Jadhav, et al. YOLOv8-based helmet and vest detection system for safety assessment. In: Proceedings of 2023 International Conference on Network, Multimedia and Information Technology (NMITCON), Bengaluru, India, 2023: pp 1–10.
Crossref
[16]
K. Patel, V. Patel, V. Prajapati, et al. Safety helmet detection using YOLO v8. In: Proceedings of the 2023 3rd International Conference on Pervasive Computing and Social Networking (ICPCSN), Salem, India, 2023: pp 22–26.
Crossref
[17]

K. Kim, K. Kim, S. Jeong. Application of YOLO v5 and v8 for recognition of safety risk factors at construction sites. Sustainability, 2023, 15: 15179.
Crossref Google Scholar
[18]
S. Chourasia, R. Bhojane, L. Heda. Safety helmet detection: A comparative analysis using YOLOv4, YOLOv5, and YOLOv7. In: Proceedings of 2023 International Conference for Advancement in Technology (ICONAT), Goa, India, 2023: pp 1–8.
Crossref
[19]
N. D. T. Yung, W. K. Wong, F. H. Juwono, et al. Safety helmet detection using deep learning: Implementation and comparative study using YOLOv5, YOLOv6, and YOLOv7. In: Proceedings of 2022 International Conference on Green Energy, Computing and Sustainable Technology (GECOST), Miri Sarawak, Malaysia, 2022: pp 164–170.
Crossref
[20]

M. Park, D. Q. Tran, J. Bak, et al. Small and overlapping worker detection at construction sites. Autom Constr, 2023, 151: 104856.
Crossref Google Scholar
[21]

H. B. Li, D. C. Wu, W. M. Zhang, et al. YOLO-PL: Helmet wearing detection algorithm based on improved YOLOv4. Digit Signal Process, 2024, 144: 104283.
Crossref Google Scholar
[22]

J. J. Bao, S. H. Li, G. L. Wang, et al. Improved YOLOv8 network and application in safety helmet detection. J Phys: Conf Ser, 2023, 2632: 012012.
Crossref Google Scholar
[23]

Z. Wang, Y. Liu, S. Y. Duan, et al. An efficient detection of non-standard miner behavior using improved YOLOv8. Comput Electr Eng, 2023, 112: 109021.
Crossref Google Scholar
[24]

L. J. Li, P. Zhang, S. P. Yang, et al. YOLOv5-SFE: An algorithm fusing spatio–temporal features for detecting and recognizing workers’ operating behaviors. Adv Eng Inform, 2023, 56: 101988.
Crossref Google Scholar
[25]

Y. F. Ni, J. Huo, Y. Hou, et al. Detection of underground dangerous area based on improving YOLOV8. Electronics, 2024, 13: 623.
Crossref Google Scholar
[26]

Z. P. Zhang, P. R. Chen, Y. J. Huang, et al. Railway obstacle intrusion warning mechanism integrating YOLO-based detection and risk assessment. J Ind Inf Integr, 2024, 38: 100571.
Crossref Google Scholar
[27]
J. Terven, D. Cordova-Esparza. A comprehensive review of YOLO architectures in computer vision: From YOLOv1 to YOLOv8 and YOLO-NAS. 2023, arXiv:2304.00501, arXiv.org e-print archive. https://arxiv.org/abs/2304.00501 (accessed 2024-02-05
Crossref
[28]
R. Girshick, J. Donahue, T. Darrell, et al. Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition, Washington, USA, 2014: pp 580–587.
Crossref
[29]
R. Girshick. Fast R-CNN. In: Proceedings of 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 2015: pp 1440–1448.
Crossref
[30]
T. Y. Lin, P. Dollár, R. Girshick, et al. Feature pyramid networks for object detection. In: Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, USA, 2017: pp 936–944.
Crossref
[31]
K. M. He, G. Gkioxari, P. Dollár, et al. Mask R-CNN. In: Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017: pp 2980–2988.
[32]

T. Y. Lin, P. Goyal, R. Girshick, et al. Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell, 2020, 42: 318–327.
Crossref Google Scholar
[33]
W. Liu, D. Anguelov, D. Erhan, et al. SSD: Single shot MultiBox detector. In: Proceedings of the 14th European Conference, Amsterdam, The Netherlands, 2016.
Crossref
[34]

L. X. Du, R. Y. Zhang, X. T. Wang. Overview of two-stage object detection algorithms. J Phys: Conf Ser, 2020, 1544: 012033.
Crossref Google Scholar
[35]
Z. Ge, S. T. Liu, F. Wang, et al. YOLOX: Exceeding YOLO series in 2021. 2021, arXiv:2107.08430. arXiv.org e-print archive. https://arxiv.org/abs/2107.08430 (accessed 2024-02-05
[36]
C. J. Feng, Y. J. Zhong, Y. Gao, et al. TOOD: Task-aligned one-stage object detection. In: Proceedings of 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, Canada, 2021.
Crossref
[37]
C. Q. Lyu, W. W. Zhang, H. A. Huang, et al. RTMDet: An empirical study of designing real-time object detectors. 2022, arXiv:2212.07784. arXiv.org e-print archive. https://arxiv.org/abs/2212.07784 (accessed 2024-02-05
[38]
Z. H. Zheng, P. Wang, W. Liu, et al. Distance-IoU loss: Faster and better learning for bounding box regression. In: Proceedings of the 34th AAAI Conference on Artificial Intelligence, Palo Alto, USA, 2020: pp 12993–13000.
Crossref
[39]
X. Li, W. H. Wang, L. J. Wu, et al. Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection. In: Proceedings of the 34th International Conference on Neural Information, Red Hook, USA, 2020.
[40]
A. Bochkovskiy, C. Y. Wang, H. Y. M. Liao. YOLOv4: Optimal speed and accuracy of object detection. 2020, arXiv:2004.10934. arXiv.org e-print archive. https://arxiv.org/abs/2004.10934 (accessed 2024-02-05
[41]
R. Padilla, S. L. Netto, E. A. B. da Silva. A survey on performance metrics for object-detection algorithms. In: Proceedings of 2020 International Conference on Systems, Signals and Image Processing (IWSSIP), Niteroi, Brazil, 2020: pp 237–242.
Crossref
[42]

H. D. Zhu, H. R. Wei, B. Q. Li, et al. A review of video object detection: Datasets, metrics and methods. Appl Sci, 2020, 10: 7834.
Crossref Google Scholar
[43]
J. W. Wang, C. Xu, W. Yang, et al. A normalized Gaussian wasserstein distance for tiny object detection. 2022, arXiv:2110.13389. arXiv.org e-print archive. https://arxiv.org/abs/2110.13389 (accessed 2024-02-05
[44]

S. J. Ji, Q. H. Ling, F. Han. An improved algorithm for small object detection based on YOLO v4 and multi-scale contextual information. Comput Electr Eng, 2023, 105: 108490.
Crossref Google Scholar
[45]
J. Redmon, A. Farhadi. YOLO9000: Better, faster, stronger. In: Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, USA, 2017: pp 7263–7271.
Crossref
[46]
J. Redmon, A. Farhadi. YOLOv3: An incremental improvement. 2018, arXiv:1804.02767, arXiv.org e-print archive. https://doi.org/10.48550/arXiv.1804.02767 (accessed 2024-02-05
[47]
G. Jocher. YOLOv5 by Ultralytics on https://github.com/ultralytics/yolov5, 2020.
[48]
C. Y. Wang, A. Bochkovskiy, H. Y. M. Liao. Scaled-YOLOv4: Scaling Cross Stage Partial Network. In: Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, USA, 2021: pp 13029–13038
Crossref
[49]

Y. J. Ma, D. H. Yu, T. Wu, et al. PaddlePaddle: An open-source deep learning platform from industrial practice. Front Data Comput, 2019, 1: 105–115.
Crossref Google Scholar
[50]
Z. Ge, S. T. Liu, F. Wang, et al. YOLOX: Exceeding YOLO series in 2021. 2021, arXiv:2107.08430, arXiv.org e-print archive. https://doi.org/10.48550/arXiv.2107.08430 (accessed 2024-02-05
[51]
C. Y. Wang, I. H. Yeh, H. Y. M. Liao. You Only Learn One Representation: Unified network for multiple tasks. 2021, arXiv:2105.04206, arXiv.org e-print archive. https://doi.org/10.48550/arXiv.2105.04206 (accessed 2024-02-05
[52]
X. Huang, X. X. Wang, W. Y. Lv, et al. PP-YOLOv2: A practical object detector. 2021, arXiv:2104.10419, arXiv.org e-print archive. https://doi.org/10.48550/arXiv.2104.10419 (accessed 2024-02-05
[53]
C. Y. Li, L. L. Li, H. L. Jiang, et al. YOLOv6: A single-stage object detection framework for industrial applications. 2022, arXiv:2209.02976, arXiv.org e-print archive. https://doi.org/10.48550/arXiv.2209.02976 (accessed 2024-02-05
[54]
C. Y. Wang, A. Bochkovskiy, H. Y. M. Liao. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. 2022, arXiv:2207.02696, arXiv.org e-print archive. https://doi.org/10.48550/arXiv.2207.02696 (accessed 2024-02-05
Crossref
[55]
X. Z. Xu, Y. Q. Jiang, W. H. Chen, et al. DAMO-YOLO: A report on real-time object detection design. 2022, arXiv:2211.15444, arXiv.org e-print archive. https://doi.org/10.48550/arXiv.2211.15444 (accessed 2024-02-05
[56]
S. L. Xu, X. X. Wang, W. Y. Lv, et al. PP-YOLOE: An evolved version of YOLO. 2022, arXiv:2203.16250, arXiv. org e-print archive. https://doi.org/10.48550/arXiv.2203.16250 (accessed 2024-02-05
[57]
Deci AI. Super-gradients on https://zenodo.org/record/7789328. 2021. (accessed 2024-02-05
Journal of Intelligent Construction
Volume 2 Issue 4,
December 2024
Article number: 9180037
DOI: 10.26599/JIC.2024.9180037
Cite this article:
Feng R, Miao Y, Zheng J. A YOLO-based intelligent detection algorithm for risk assessment of construction sites. Journal of Intelligent Construction, 2024, 2(4): 9180037. https://doi.org/10.26599/JIC.2024.9180037

3032

Views

680

Downloads

0

Crossref

Altmetrics
Received: 07 February 2024
Revised: 12 May 2024
Accepted: 19 May 2024
Published: 13 September 2024
© The Author(s) 2024. Published by Tsinghua University Press.

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
Return