In conditions of the rapid development of industry and the complexification of production processes, traditional methods of safety control become inefficient. Therefore, studies in the field of the use of computer vision technologies to control compliance with the industrial safety requirements for production facilities are critical for any industry and field of human activities. Results of the use of video analytics based on algorithms of artificial intelligence and computer vision to monitor contingencies and improve the safety of workflows have been stipulated. The analysis of the current solutions in the sphere of video analytics and their integration with production process management systems have been provided. Innovative approaches to video data analysis enabling control the compliance with safety rules, detecting non-standard events, and preventing potential accidents in real-time mode have been proposed. An extended description of the data collection preparatory process for model training and verification of its accuracy has been provided. The scientific novelty of the study is the development of a system able to identify violations occurring in conditions of a complex workflow and disturbing external factors, for example, limited visibility within the monitoring area or multiple objects within the registration area potentially causing false alarm system activations, with high accuracy. This approach helps to significantly expand the scope of application of the system for production facilities. The efficiency of the use of the developed methods for real production facilities has been demonstrated. The recommendations on the use of the study results for the development of safe technologies and productions have been formulated.
2. Sharafutdinov D.K., Badrutdinov M.N., Sibagatullin R.R. Didactic means of occupational safety during repair and reconstruction of trunk pipelines based on graphic design and information technologies. Bezopasnost truda v promyshlennosti = Occupational Safety in Industry. 2011. № 9. pp. 61–68. (In Russ.).
3. Kazikhanov B.R. Digitization and Automation in Occupational Safety Systems: Advantages, Challenges, and Prospects. Okhrana truda i tekhnosfernaya bezopasnost na obektakh promyshlennosti, transporta i sotsialnykh infrastruktur: sb. st. III Vseros. nauch.-prakt. konf. (Occupational and technosphere safety for industrial, transport, and social infrastructure facilities: collection of articles of the 3rd All-Russia Scientific and Practical Conference). Penza: Penzenskiy gosudarstvennyy agrarnyy universitet. 2024. pp. 61–64. (In Russ.).
4. Semenova A.G. Danilova E.V. Innovative technologies as effective tools to reduce industrial injuries. Innovatsii i investitsii = Innovations and investments. 2019. № 8. pp. 19–21. (In Russ.).
5. Zubkova E.V., Samarina V.P. Improving Labor Protection Management Through the Introduction of «Smart» Personal Protective Equipment. Fundamentalnye issledovaniya = Fundamental Research. 2020. № 7. pp. 36–41. (In Russ.).
6. Chao G.T., Deal C., Migliano E.N. Occupational exoskeletons: Supporting diversity and inclusion goals with technology. Journal of Vocational Behavior. 2024. Vol. 153. pp. 1–15.
7. Wang B., Wang Y., Xu F., Shi Z. Intelligence-led accident prevention and its application in petrochemical enterprises. Process Safety and Environmental Protection. 2024. Vol. 184. pp. 690–702.
8. Pazukha A.A. Artificial Intelligence for Safe Maintenance, Operation and Repair Technologies for Power Supply Devices of JSC «Russian Railways». Bezopasnost truda v promyshlennosti = Occupational Safety in Industry. 2021. № 6. pp. 46–51. (In Russ.). DOI: 10.24000/0409-2961-2021-6-46-51
9. Mühlbauer M., Kutzner K., Sommer A., Würschinger H., Hanenkamp N. An Approach to Progress Monitoring of Industrial Manual Processes Based on Camera Recordings and Object Interactions. Procedia CIRP. 2022. Vol. 107. pp. 582–587. DOI: 10.1016/j.procir.2022.05.029
10. Lv T., Zhang H.Y., Yan C.H. Double mode surveillance system based on remote audio/video signals acquisition. Applied Acoustics. 2018. Vol. 129. pp. 316–321. DOI: 10.1016/j.apacoust.2017.08.016
11. Xiao X., Zhang X., Song M., Liu X., Huang Q. NPP accident prevention: Integrated neural network for coupled multivariate time series prediction based on PSO and its application under uncertainty analysis for NPP data. Energy. 2024. Vol. 305. DOI: 10.1016/j.energy.2024.132374
12. Said Y., Alassaf Y., Ghodhbane R., Alsariera Y.A., Saidani T., Rhaiem O.B., Makhdoum M.K., Hleili M. AI-Based Helmet Violation Detection for Traffic Management System. Computer Modeling in Engineering and Sciences. 2024. Vol. 141. № 1. pp. 733–749. DOI: 10.32604/cmes.2024.052369
13. Wonghabut P., Kumphong J., Satiennam T., Ung-arunyawee R., Leelapatra W. Automatic helmet-wearing detection for law enforcement using CCTV cameras. IOP Conference Series: Earth and Environmental Science. 2018. Vol. 143. № 1. DOI: 10.1088/1755-1315/143/1/012063
14. Malik S., Muhammad K.,Waheed Y. Artificial intelligence and industrial applications-A revolution in modern industries. Ain Shams Engineering Journal. 2024. Vol. 15. № 5. DOI: 10.1016/j.asej.2024.102886
15. Xiao R., Zayed T., Meguid M.A., Sushama L. Improving failure modeling for gas transmission pipelines: A survival analysis and machine learning integrated approach. Reliability Engineering & System Safety. 2024. Vol. 241. DOI: 10.1016/j.ress.2023.109672
16. Cao Q.G., Kai L., Liu Y.J., Sun Q.H., Zhang J. Risk management and workers’ safety behavior control in coal mine. Safety Science. 2012. Vol. 50. Iss. 4. pp. 909–913. DOI: 10.1016/j.ssci.2011.08.005
17. Ullah Z., Qi L., Pires E.J.S., Reis A., Nunes R.R. A Systematic Review of Computer Vision Techniques for Quality Control in End-of-Line Visual Inspection of Antenna Parts. Computers, Materials and Continua. 2024. Vol. 80. № 2. pp. 2387–2421. DOI: 10.32604/cmc.2024.047572
18. Elharrouss O., Almaadeed N., Al-Maadeed S. A review of video surveillance systems. Journal of Visual Communication and Image Representation. 2021. Vol. 77. DOI: 10.1016/j.jvcir.2021.103116
19. Redmon J., Divvala S., Girshick R., Farhadi A. You Only Look Once: Unified, Real-Time Object Detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016. DOI: 10.1109/CVPR.2016.91
20. Sedova Zh.I. Legislation requirements for the transition to digital technologies in the activities of hazardous production facilities. Permskiy yuridicheskiy almanakh = Perm Legal Almanac. 2019. pp. 128–137. (In Russ.).