Deep Learning-Based Automatic Safety Helmet Detection System for Construction Safety
Source abstract
Abstract
Worker safety at construction sites is a growing concern for many construction industries. Wearing safety helmets can reduce injuries to workers at construction sites, but due to various reasons, safety helmets are not always worn properly. Hence, a computer vision-based automatic safety helmet detection system is extremely important. Many researchers have developed machine and deep learning-based helmet detection systems, but few have focused on helmet detection at construction sites. This paper presents a You Only Look Once (YOLO)-based real-time computer vision-based automatic safety helmet detection system at a construction site. YOLO architecture is high-speed and can process 45 frames per second, making YOLO-based architectures feasible to use in real-time safety helmet detection. A benchmark dataset containing 5000 images of hard hats was used in this study, which was further divided in a ratio of 60:20:20 (%) for training, testing, and validation, respectively. The experimental results showed that the YOLOv5x architecture achieved the best mean average precision (mAP) of 92.44%, thereby showing excellent results in detecting safety helmets even in low-light conditions.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Occupational Health and Safety Research · Traffic and Road Safety · Infrastructure Maintenance and Monitoring
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Madeira Interactive Technologies Institute, University of Madeira, 9000-082 Funchal, Portugal
Interactive Technologies Institute (ITI/LARSyS and ARDITI), 9020-105 Funchal, Portugal
References (44)
Show source-provided references
1. Mobile passive Radio Frequency Identification (RFID) portal for automated and rapid control of Personal Protective Equipment (PPE) on construction sites10.1016/j.autcon.2013.08.009 ↗
2. Bureau of Labor Statistics (2022, March 30). Industries at a Glance, Available online: https://www.bls.gov/iag/tgs/iag23.htm.
3. Fault tree analysis of unreasonably wearing helmets for builders
4. Comparison of unintentional fatal occupational injuries in the Republic of Korea and the United States10.1136/ip.2003.004895 ↗
5. International Labour Organization (ILO) (2022, March 30). World Statistic. Available online: www.ilo.org/moscow/areas-of-work/occupational-safety-and-health/WCMS_249278/lang--en/index.htm.
6. (2022, March 30). Ministry of Housing and Urban-Rural Development of the People’s Republic of China, Available online: https://www.mohurd.gov.cn/wjfb/201903/t20190326_239913.html.
7. (2022, March 30). Statistics—Work-Related Fatal Injuries in Great Britain, Available online: https://www.hse.gov.uk/statistics/fatals.htm.
8. OSHA (2022, March 30). Occupational Safety and Health Administration Commonly Used Statistics, OSHA Data and Statistics., Available online: www.osha.gov/oshstats/commonstats.html.
9. U.S (2022, March 30). Department of Health and Human Services, Worker Deaths by Falls. A Summary of Surveillance Findings and Investigative Case Reports, No. September 2000., Available online: www.cdc.gov/niosh.
10. Zhai, H. (2016, January 24–25). Research on image recognition based on deep learning technology. Proceedings of the 2016 4th International Conference on Advanced Materials and Information Technology Processing (AMITP 2016), Guilin, China.10.2991/amitp-16.2016.53 ↗
11. Real-Time Alarming, Monitoring, and Locating for Non-Hard-Hat Use in Construction10.1061/(ASCE)CO.1943-7862.0001629 ↗
12. Escorcia, V., Dávila, M.A., Golparvar-Fard, M., and Niebles, J.C. (2012, January 21–23). Automated vision-based recognition of construction worker actions for building interior construction operations using RGBD cameras. Proceedings of the Construction Research Congress 2012: Construction Challenges in a Flat World, West Lafayette, IN, USA.10.1061/9780784412329.089 ↗
13. Xie, Z., Liu, H., Li, Z., and He, Y. (2018, January 14–16). A convolutional neural network based approach towards real-time hard hat detection. Proceedings of the 2018 IEEE International Conference on Progress in Informatics and Computing, Suzhou, China.10.1109/PIC.2018.8706269 ↗
14. Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems10.1109/LWC.2017.2757490 ↗
15. Choi, J., Chun, D., Kim, H., and Lee, H.-J. (2019, January 27–28). Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea.10.1109/ICCV.2019.00059 ↗
16. Wu, Y., Meng, Z., Palaiahnakote, S., and Lu, T. Compressing YOLO network by compressive sensing. Proceedings on the 4th Asian Conference on Pattern Recognition, ACPR2017, Nanjing, China.10.1109/ACPR.2017.11 ↗
17. TDFSSD: Top-Down Feature Fusion Single Shot MultiBox Detector10.1016/j.image.2020.115987 ↗
18. Deep Learning-Based Safety Helmet Detection in Engineering Management Based on Convolutional Neural Networks10.1155/2020/6640687 ↗
19. Real-time personal protective equipment monitoring system10.1016/j.comcom.2012.01.005 ↗
20. Automatic detection of hardhats worn by construction personnel: A deep learning approach and benchmark dataset10.1016/j.autcon.2019.102894 ↗
21. Waranusast, R., Bundon, N., Timtong, V., Tangnoi, C., and Pattanathaburt, P. (2013, January 27–29). Machine vision techniques for motorcycle safety helmet detection. Proceedings of the in International Conference Image and Vision Computing New Zealand, Wellington, New Zealand.10.1109/IVCNZ.2013.6726989 ↗
22. Doungmala, P., and Klubsuwan, K. (2016, January 8–10). Helmet wearing detection in Thailand using haar like feature and circle hough transform on image processing. Proceedings of the 2016 IEEE International Conference on Computer and Information Technology (CIT), Nadi, Fiji.10.1109/CIT.2016.87 ↗
23. Phuc, L.T.H., Jeon, H., Truong, N.T.N., and Hak, J.J. (2019). Applying the Haar-cascade Algorithm for Detecting Safety Equipment in Safety Management Systems for Multiple Working Environments. Electronics, 8.10.3390/electronics8101079 ↗
24. Rubaiyat, A.H., Toma, T.T., Kalantari-Khandani, M., Rahman, S.A., Chen, L., Ye, Y., and Pan, C.S. (2016, January 13–16). Automatic detection of helmet uses for construction safety. Proceedings of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence Workshops, WIW 2016, Omaha, NE, USA.10.1109/WIW.2016.045 ↗
25. Park, M.-W., Palinginis, E., and Brilakis, I. (2012, January 21–23). Detection of construction workers in video frames for automatic initialization of vision trackers. Proceedings of the Construction Research Congress 2012: Construction Challenges in a Flat World, West Lafayette, IN, USA.10.1061/9780784412329.095 ↗
26. Zhu, Z., Park, M.-W., and Elsafty, N. (2015, January 7–10). Automated monitoring of hardhats wearing for onsite safety enhancement. Proceedings of the 5th International Construction Specialty Conference, Vancouver, CB, Canada.
27. Du, S., Shehata, M., and Badawy, W. (2011, January 11-13). Hard hat detection in video sequences based on face features, motion and color information. Proceedings of the 2011 3rd international conference on computer research and development, Shanghai, China.
28. Hard-Hat Detection for Construction Safety Visualization10.1155/2015/721380 ↗
29. Li, K., Zhao, X., Bian, J., and Tan, M. (August, January 31). Automatic Safety Helmet Wearing Detection. Proceedings of the 2017 IEEE 7th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, Honolulu, HI, USA.10.1109/CYBER.2017.8446080 ↗
30. Wang, Z., Wu, Y., Yang, L., Thirunavukarasu, A., Evison, C., and Zhao, Y. (2021). Fast Personal Protective Equipment Detection for Real Construction Sites Using Deep Learning Approaches. Sensors, 21.10.3390/s21103478 ↗
31. Geng, R., Ma, Y., and Huang, W. (2021, January 23–25). An improved helmet detection method for YOLOv3 on an unbalanced dataset. Proceedings of the 2021 3rd International Conference on Advances in Computer Technology, Information Science and Communication, CTISC, Shanghai, China.10.1109/CTISC52352.2021.00066 ↗
32. Deep learning for site safety: Real-time detection of personal protective equipment10.1016/j.autcon.2020.103085 ↗
33. SSD: Single shot multibox detector10.1007/978-3-319-46448-0_2 ↗
34. Method based on the cross-layer attention mechanism and multiscale perception for safety helmet-wearing detection10.1016/j.compeleceng.2021.107458 ↗
35. Detecting safety helmet wearing on construction sites with bounding-box regression and deep transfer learning10.1111/mice.12579 ↗
36. (2022, March 30). Hard Hat Workers Dataset|MakeML—Create Neural Network with Ease. Available online: https://makeml.app/datasets/hard-hat-workers.
37. Kumar, D., and Ramakrishnan, A.G. (2012, January 22–25). Power-law transformation for enhanced recognition of born-digital word images. Proceedings of the 2012 International Conference on Signal Processing and Communications (SPCOM), Bangalore, India.10.1109/SPCOM.2012.6290009 ↗
38. Redmon, J., and Farhadi, A. (2018). YOLOv3: An incremental improvement. arXiv.
39. Nepal, U., and Eslamiat, H. (2022). Comparing YOLOv3, YOLOv4 and YOLOv5 for Autonomous Landing Spot Detection in Faulty UAVs. Sensors, 22.10.3390/s22020464 ↗
40. Wang, C.-Y., Liao, H.-Y.M., Wu, Y.-H., Chen, P.-Y., Hsieh, J.-W., and Yeh, I.-H. (2020, January 14–19). CSPNet: A new backbone that can enhance learning capability of CNN. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA.10.1109/CVPRW50498.2020.00203 ↗
41. Wang, K., Liew, J.H., Zou, Y., Zhou, D., and Feng, J. (November, January 27). PANet: Few-shot image semantic segmentation with prototype alignment. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea.10.1109/ICCV.2019.00929 ↗
42. Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., and Savarese, S. (2019, January 15–20). Generalized intersection over union: A metric and a loss for bounding box regression. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2019, Long Beach, CA, USA. Available online: https://giou.stanford.edu/.10.1109/CVPR.2019.00075 ↗
43. Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019, January 8–14). PyTorch: An imperative style, high-performance deep learning library. Proceedings of the 33rd Conference on Neural Information Processing Systems, Vancouver, BC, Canada.
44. Neubeck, A., and Van Gool, L. (2006, January 20–24). Efficient non-maximum suppression. Proceedings of the 18th International Conference on Pattern Recognition (ICPR’06), Hong Kong, China.10.1109/ICPR.2006.479 ↗