Design and Implementation of Industrial Accident Detection Model Based on YOLOv4
Source abstract
Abstract
Korea’s industrial accident rate ranks high among Organization for Economic Co-operation and Development countries. Moreover, large-scale accidents have recently occurred. Accordingly, the requirements for management and supervision in industrial sites are increasing; in this context, the “Act on Punishment of Serious Accidents, etc.” has been enacted. Aiming to prevent such industrial accidents, various data collected by devices such as sensors and closed-caption televisions (CCTVs) are utilized to track workers and detect hazardous substances, gases, and fires at industrial sites. In this study, an industrial area requiring such technology is selected. A hazardous situation event is derived, and a dataset is built using CCTV data. A violation corresponding to a hazardous situation event is detected and a warning is provided. The events incorporate requirements extracted from industrial sites, such as those concerning collision risks and the wearing of safety equipment. The precision of the event violation detection exceeds 95% and the response and delay times are under 20 ms. Thus, this system is believed to be used at industrial sites and for other intelligent industrial safety prevention solutions.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Marine and Coastal Research · Technology and Data Analysis · Innovation in Digital Healthcare Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Science and Engineering, Paichai University, 155-40 Baejae-ro, Daejeon 35345, Republic of Korea
Funding
Ministry of Education (MOE)
References (52)
Show source-provided references
1. Occupational safety and health in construction: A review of applications and trends10.2486/indhealth.2016-0108 ↗
2. Friend, M.A., and Kohn, J.P. (2023). Fundamentals of Occupational Safety and Health, Bernan Press. [8th ed.].
3. (2023, March 22). Industrial Accident Status. Available online: https://www.index.go.kr/unity/potal/main/EachDtlPageDetail.do?idx_cd=1514.
4. Analysis of industrial accidents causing through jamming or crushing accidental deaths in the manufacturing industry in South Korea: Focus on non-routine work on machinery10.1016/j.ssci.2020.104998 ↗
5. Characteristics of occupational accidents in the manufacturing industry of South Korea10.1016/S0169-8141(96)00064-9 ↗
6. (2023, April 24). Fatal Occupational Injuries per 100,000 Workers by Economic Activity—Annual. Available online: https://www.ilo.org/shinyapps/bulkexplorer36/?lang=en&id=INJ_FATL_ECO_RT_A.
7. (2023, April 24). GDP (Current US Dollar). Available online: https://data.worldbank.org/indicator/NY.GDP.MKTP.CD.
8. (2023, March 03). [Quarterly] Status of Occupational Accidents at the End of December 2022. Available online: https://www.kosha.or.kr/kosha/data/industrialAccidentStatus.do?mode=view&articleNo=438399.
9. Kwon, J. (2009). A Study on Measures to Promote Industrial Accident Prevention in Workplaces with Less than 50 Employees. [Master’s Thesis, Korea University].
10. Trends in burden of work-related upper limb amputation in South Korea, 2004–2013: A nationwide retrospective cohort study10.1136/bmjopen-2019-032793 ↗
11. Development of Disaster Safety Program for Small-sized Workplaces and Its Introduction to Occupational Safety&Health Act: Focusing on Fire, Explosion and Chemical Spill
12. Unions, Health and Safety Committees, and Workplace Accidents in the Korean Manufacturing Sector10.1016/j.shaw.2016.02.005 ↗
13. Comparison of fatal occupational injuries in construction industry in the United States, South Korea, and China10.1016/j.ergon.2019.02.011 ↗
14. The Fourth Industrial Revolution and Its Impact on Occupational Health and Safety, Worker’s Compensation and Labor Conditions10.1016/j.shaw.2019.09.005 ↗
15. Kang, S.Y., Min, S., Won, D., Kang, Y.J., and Kim, S. (2021). Suggestion of an Improved Evaluation Method of Construction Companies’ Industrial Accident Prevention Activities in South Korea. Int. J. Environ. Res. Public Health, 18.10.3390/ijerph18168442 ↗
16. Cost assessment model for sustainable health and safety management of high-rise residential buildings in Korea10.1080/13467581.2021.1902334 ↗
17. Kang, S.Y., Min, S., Kim, W.S., Won, J.H., Kang, Y.J., and Kim, S. (2022). Types and Characteristics of Fatal Accidents Caused by Multiple Processes in Workplace: Based on Actual Cases in South Korea. Int. J. Environ. Res. Public Health, 19.10.3390/ijerph19042047 ↗
18. Study on the Risk Assessment of Fall Accidents at Construction Sites Through the Analysis of Accident Cases
19. The effect of subcontractor status on occupational injury and disease incidence: A cross-sectional study using the 9th Occupational Safety and Health Company Survey10.1007/s00420-022-01858-4 ↗
20. A Study on Disclosure Items of Safety and Health Management System for Major Injury Prevention
21. Choi, J., Lim, S., Park, S., Roh, H., Jin, H., and Lee, C. (2022). The Serious Accidents Punishment Act of South Korea and Its Impact on the Shipping Industry: Toward Sustainability. Sustainability, 14.10.3390/su14148936 ↗
22. Criminal Justice in a Time of Ecological Crisis: Can the Serious Accidents Punishment Act in Korea Be Enforced to Punish ‘Ecocide’?10.36889/IJCJ.2022.005 ↗
23. (2021, September 04). DarkLabel. Available online: https://github.com/darkpgmr/DarkLabel.
24. (2019, April 24). Yolo_mark. Available online: https://github.com/AlexeyAB/Yolo_mark.
25. (2023, April 21). CVAT.ai. Available online: https://github.com/opencv/cvat.
26. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 24–27). Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA. Available online: https://openaccess.thecvf.com/content_cvpr_2014/html/Girshick_Rich_Feature_Hierarchies_2014_CVPR_paper.html.10.1109/CVPR.2014.81 ↗
27. Girshick, R. (2015, January 7–13). Fast R-CNN. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile. Available online: https://openaccess.thecvf.com/content_iccv_2015/html/Girshick_Fast_R-CNN_ICCV_2015_paper.html.10.1109/ICCV.2015.169 ↗
28. Ren, S., He, K., Girshick, R., and Sun, J. (2015, January 10–12). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. Proceedings of the Advances in Neural Information Processing Systems 28 (NIPS), Montreal, QC, Canada. Available online: https://proceedings.neurips.cc/paper/2015/hash/14bfa6bb14875e45bba028a21ed38046-Abstract.html.
29. He, K., Gkioxari, G., Dollar, P., and Girshick, R. (2017, January 22–29). Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy. Available online: https://openaccess.thecvf.com/content_iccv_2017/html/He_Mask_R-CNN_ICCV_2017_paper.html.10.1109/ICCV.2017.322 ↗
30. Redmon, J., Divvala, S., Giorshick, R., and Farhadi, A. (July, January 26). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA. Available online: https://www.cv-foundation.org/openaccess/content_cvpr_2016/html/Redmon_You_Only_Look_CVPR_2016_paper.html.10.1109/CVPR.2016.91 ↗
31. Redmon, J., and Farhadi, A. (2017, January 21–26). YOLO9000: Better, Faster, Stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA. Available online: https://openaccess.thecvf.com/content_cvpr_2017/html/Redmon_YOLO9000_Better_Faster_CVPR_2017_paper.html.10.1109/CVPR.2017.690 ↗
32. Redmon, J., and Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv.
33. Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv.
34. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 11–14). SSD: Single Shot MultiBox Detector. Proceedings of the Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands.10.1007/978-3-319-46448-0_2 ↗
35. Hyperspectral image classification using wavelet transform-based smooth ordering10.1142/S0219691319500504 ↗
36. Guariglia, E. (2019). Primality, Fractality, and Image Analysis. Entropy, 21.10.3390/e21030304 ↗
37. A survey of modern deep learning based object detection models10.1016/j.dsp.2022.103514 ↗
38. 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 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Virtual. Available online: https://openaccess.thecvf.com/content_CVPRW_2020/html/w28/Wang_CSPNet_A_New_Backbone_That_Can_Enhance_Learning_Capability_of_CVPRW_2020_paper.html.10.1109/CVPRW50498.2020.00203 ↗
39. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition10.1109/TPAMI.2015.2389824 ↗
40. Liu, S., Qi, L., Qin, H., Shi, J., and Jia, J. (2018, January 18–22). Path Aggregation Network for Instance Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA. Available online: https://openaccess.thecvf.com/content_cvpr_2018/html/Liu_Path_Aggregation_Network_CVPR_2018_paper.html.10.1109/CVPR.2018.00913 ↗
41. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018, January 18–22). MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA. Available online: https://openaccess.thecvf.com/content_cvpr_2018/html/Sandler_MobileNetV2_Inverted_Residuals_CVPR_2018_paper.html.10.1109/CVPR.2018.00474 ↗
42. Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., and Tian, Q. (November, January 27). CenterNet: Keypoint Triplets for Object Detection. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea. Available online: https://openaccess.thecvf.com/content_ICCV_2019/html/Duan_CenterNet_Keypoint_Triplets_for_Object_Detection_ICCV_2019_paper.html.10.1109/ICCV.2019.00667 ↗
43. Dataset Construction and Model Learning for Manufacturing Worker Safety Management
44. (2023, April 24). Disability Awareness in the Workplace. Available online: https://www.kead.or.kr/en/dsawnswplc/cntntsPage.do?menuId=MENU1391.
45. (2023, April 24). Purpose of Clean Workplace Creation Project. Available online: https://clean.kosha.or.kr/content.do.
46. (2022, March 14). Data Quality Management Guidelines for AI Learning Version 2.0. Available online: https://www.nia.or.kr/site/nia_kor/ex/bbs/View.do?cbIdx=26537&bcIdx=24250&parentSeq=2425.
47. The Challenges of Data Quality and Data Quality Assessment in the Big Data Era10.5334/dsj-2015-002 ↗
48. Picard, S., Chapdelaine, C., Cappi, C., Gardes, L., Jenn, E., Lefevre, B., and Soumarmon, T. (2020, January 12–15). Ensuring Dataset Quality for Machine Learning Certification. Proceedings of the 2020 IEEE International Symposium on Software Reliability Engineering Workshops (ISSRE), Coimbra, Portugal.10.1109/ISSREW51248.2020.00085 ↗
49. Budach, L., Feuerpfeil, M., Ihde, N., Nathansen, A., Noack, N., Patzlaff, H., Naumann, F., and Harmouch, H. (2022). The Effects of Data Quality on Machine Learning Performance. arXiv.
50. Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollar, P., and Zitnick, C.L. (2014, January 6–12). Microsoft COCO: Common Objects in Context. Proceedings of the European Conference on Computer Vision (ECCV), Zurich, Switzerland.10.1007/978-3-319-10602-1_48 ↗
51. (2017, December 01). The JSON Data Interchange Syntax. Available online: https://www.ecma-international.org/wp-content/uploads/ECMA-404_2nd_edition_december_2017.pdf.
52. Vicente, S., Carreira, J., Agapito, L., and Batista, J. (2014, January 24–27). Reconstructing PASCAL VOC. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, OH, USA. Available online: https://openaccess.thecvf.com/content_cvpr_2014/html/Vicente_Reconstructing_PASCAL_VOC_2014_CVPR_paper.html.10.1109/CVPR.2014.13 ↗