Using Combined Artificial Intelligence Models to Monitor Construction Safety
DOI:
https://doi.org/10.52575/2687-0932-2024-51-4-887-895Keywords:
computer vision, combined models, construction site, tracking, safety helmet, labor discipline, safety precautions, Yolo8Abstract
The article presents the formulation of problems, their conditions, limitations and solutions aimed at identifying violations of labor discipline (absence from the workplace) and safety precautions (failure to wear a safety helmet) at a construction site. The study shows that it is only possible to ensure high accuracy of identification and tracking of people, as well as classification of safety helmets they are wearing when an AI architecture of the solution is built that is based on a combi-nation of neural network architectures and production rules that reflect the conditions of the tasks. This combination potentially allows obtaining the highest characteristics of detection and recogni-tion accuracy, which is demonstrated by specific examples.
Downloads
References
ГОСТ Р 59276-2020. Системы искусственного интеллекта. Способы обеспечения доверия. Общие положения. https://docs.cntd.ru/document/1200177291
Гусев А.В. 2023. Автоматизация формирования выборок изображений естественных сцен для обучения и тестирования нейронных сетей. Экономика. Информатика. 50(3):624–632. DOI:10.52575/2687-0932-2023-50-3-624-632
Кузина О. Н. 2023. Модель управления производительностью труда в строительстве методами искусственного интеллекта. Научно-технический вестник Поволжья. 3: 68–73.
Aharon N., Orfaig R., Bobrovsky B.-Z., 2022. BoT-SORT: Robust Associations Multi-Pedestrian Tracking. Computer Vision and Pattern Recognition. https://arxiv.org/abs/2206.14651
Alikhanov J., Obidov O., 2024. LITE: A Paradigm Shift in Multi-Object Tracking with Efficient ReID Feature Integration. https://arxiv.org/html/2409.04187v1
Du Y., Zhao Z., Song Y., Zhao Y., Su F., Gong T., Meng H., 2022. StrongSORT: Make DeepSORT Great Again. Computer Vision and Pattern Recognition. https://arxiv.org/abs/2202.13514.
Maggiolino G., Ahmad A., Cao J., Kitani K., 2023. Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification. Computer Vision and Pattern Recognition. https://arxiv.org/abs/2302.11813.
Otgonbold M.-E., Gochoo M., Alnajjar F., Ali L., Tan T.-H., Hsieh J.-W., Chen P.-Y., 2022. SHEL5K: An Extended Dataset and Benchmarking for Safety Helmet Detection. Sensors, 22(6), 2315. DOI: 10.3390/s22062315.
Siyeon Kim, Seok Hwan Hong, Hyodong Kim, Meesung Lee, Sungjoo Hwang. 2023. Small object detection (SOD) system for comprehensive construction site safety monitoring, Automation in Construction, Vol. 156. DOI: 10.1016/j.autcon.2023.105103.
Yunusov N., Islam B.M.S., Abdusalomov A., Kim, W. 2024. Robust Forest Fire Detection Method for Surveillance Systems Based on You Only Look Once Version 8 and Transfer Learning Approaches. Processes, 12, 1039. DOI: 10.3390/pr12051039
Abstract views: 8
Share
Published
How to Cite
Issue
Section
Copyright (c) 2024 Economics. Information Technologies
This work is licensed under a Creative Commons Attribution 4.0 International License.
