Lightweight Design of Hardhat Wearing Detection Based on Deep Learning
Publication: ICCREM 2023
ABSTRACT
Hardhat is of vital importance to construction workers to prevent brain injuries. The hardhat wearing detection based on the deep learning network is efficient, but it is hard to be deployed and uneconomic. Aiming at the real-time monitoring and high practicability of construction workers’ hardhat detection, this paper proposes a lightweight detection algorithm of hardhat. First, based on YOLOv4 to form a new network structure. Second, the structure with a large calculation volume is replaced by the lightweight module BIFPNs3. Finally, use the Hard-Swish activation function suitable for embedded devices. The experimental results show that the average detection accuracy of YOLO-Ghost-BiFPNs3 network model is 91.1%. Compared with the lightweight network YOLOv4 Tiny, the detection speed increased by 52.17%. Our algorithm has greatly reduced the network parameters and computational complexity compared with YOLOv4, and is better deployed in embedded devices with limited memory and computational resources.
Get full access to this article
View all available purchase options and get full access to this chapter.
REFERENCES
Amudhan, A.N., and Sudheer, A.P. (2022). “Lightweight and computationally faster hypermetropic convolutional neural network for small size object detection.” Image and Vision Computing, 119, 104396.
Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). “Yolov4: Optimal speed and accuracy of object detection.” arXiv, 2004, 10934.
Fan, Z., Peng, C., Dai, L., Cao, F., Qi, J., and Hua, W. (2020). “A deep learning-based ensemble method for helmet-wearing detection.” PeerJ Computer Science, 6, e311.
Fang, J., and Li, X. (2022) “Object detection related to irregular behaviors of substation personnel based on improved YOLOv4.” Applied Sciences, 12(9), 4301.
Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014). “Rich feature hierarchies for accurate object detection and semantic segmentation.” Proceedings of the IEEE conference on computer vision and pattern recognition, 580-587.
Girshick, R. (2015). “Fast R-CNN.” Proceedings of the IEEE international Conference on Computer Vision, 1440-1448.
Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., and Xu, C. (2020). “Ghostnet: More features from cheap operations.” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,1580-1589.
Hayat, A., and Morgado-Dias, F. (2022). “Deep learning-based automatic safety helmet detection system for construction safety.” Applied Sciences, 12(16), 8268.
Jiang, Z., Zhao, L., Li, S., and Jia, Y. (2020). “Real-time object detection method based on improved YOLOv4-tiny.” arXiv, 2011, 04244.
Ku, B., Kim, K., and Jeong, J. (2022). “Real-time ISR-YOLOv4 based small object detection for safe shop floor in smart factories.” Electronics, 11(15), 2348.
Li, K., Qin, L., Li, Q., Zhao, F., Xu, Z., and Liu, K. (2022) “Improved edge lightweight YOLOv4 and its application in on-site power system work.” Global Energy Interconnection, 5(2), 168-180.
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016). “Ssd: Single shot multibox detector.” Computer Vision–ECCV 2016: 14th European Conference, Proceedings, Part I 14, 21-37.
Liu, Y., Zhang, D., Zhao, L., and Ma, T. (2022). “Improved YOLOv4 safety helmet detection algorithm.” 2022 4th International Conference on Advances in Computer Technology, Information Science and Communications (CTISC), 1-5.
Liu, X., and Zhang, Z. (2021). “A vision-based target detection, tracking, and positioning algorithm for unmanned aerial vehicle.” Wireless Communications and Mobile Computing, 2021, 5565589.
Park, M.W., Elsafty, N., and Zhu, Z. (2015). “Hardhat-wearing detection for enhancing on-site safety of construction workers.” Journal of Construction Engineering and Management, 141(9), 04015024.
Ren, S., He, K., Girshick, R., and Sun, J. (2015). “Faster R-CNN: Towards real-time object detection with region proposal networks.” Advances in Neural Information Processing Systems, 91-99.
Sharma, S., Susmitha, A.V.V., Van, L.D., and Tseng, Y.C. (2021). “An edge-controlled outdoor autonomous UAV for colorwise safety helmet detection and counting of workers in construction sites.” 2021 IEEE 94th Vehicular Technology Conference (VTC2021-Fall), 1-5.
Wang, J., Zhu, G., Wu, S., and Luo, C. (2021). “Worker’s helmet recognition and identity recognition based on deep learning.” Open Journal of Modelling and Simulation, 9(2), 135-145.
Wang, H., Hu, Z., Guo, Y., Yang, Z., Zhou, F., and Xu, P. (2020). “A real-time safety helmet wearing detection approach based on CSYOLOv3.” Applied Sciences, 10(19), 6732.
Wu, H., and Zhao, J. (2018). “An intelligent vision-based approach for helmet identification for work safety.” Computers in Industry, 100, 267-277.
Yang, Y., and Li, D. (2022) “Improved lightweight helmet wearing detection algorithm for YOLOv5.” Computer Engineering Applications, 58(9), 201-207.
Information & Authors
Information
Published In
ICCREM 2023
Pages: 982 - 992
History
Published online: Nov 30, 2023
ASCE Technical Topics:
- Algorithms
- Artificial intelligence and machine learning
- Business management
- Computer programming
- Computing in civil engineering
- Construction engineering
- Construction management
- Employment
- Engineering fundamentals
- Labor
- Mathematics
- Model accuracy
- Models (by type)
- Neural networks
- Occupational safety
- Parameters (statistics)
- Personnel management
- Practice and Profession
- Project management
- Public administration
- Public health and safety
- Safety
- Statistics
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.