中国科技核心期刊
美国化学文摘社（CAS）数据库
美国EBSCO学术数据库
日本科学技术振兴机构数据库(JST)
基于YOLOv11的井下人员不安全行为识别方法研究
蒋东升 1，2，朱权洁 1，2*，郝英楠 1，2，陈昱翔 1，2
- 作者单位：
- （1. 华北科技学院应急技术与管理学院；2. 防灾科技学院文化与传播学院）
基金项目：
- 中央高校基本科研业务费项目（3142021002）；廊坊市科技支撑计划项目（2024013001）；华北科技学院校级教育科学研究课题（HKJYZX202401）；2023 年度河北省高校创新创业教育教学改革研究与实践项目
详细信息：
- 作者简介：
- 蒋东升（2000—），男，硕士研究生，研究方向为矿山灾害监测预警；E‑mail：jiang18355083580@163. com*
- 通讯作者：
- PDF下载
Research on underground personnel unsafe behavior recognition based on YOLOv11
- English Author：
Jiang Dongsheng1,2, Zhu Quanjiel1,2, Hao Yingnan1,2, Chen Yuxiang1,2
- Unit：
- (1. School of Emergency Technology and Management, North China Institute of Science and Technology; 2. School of Culture and Communication, Institute of Disaster Prevention)
- 摘要
- 在线预览
- 参考文献
摘要:
井下工作环境复杂，安全隐患众多，而传统监管方式局限性大且难以做到全方位实时监管，因此基于机器学习的井下人员不安全行为识别研究迫在眉睫。提出一种基于YOLOv11的井下人员不安全行为识别方法和模型。将人员不安全行为划分为物品防护类、危险区域类和危险行为类3种；然后，根据行为划分组建数据集，并使用Albumentations进行数据增强，通过光线亮度调节，增加噪声等方式模拟井下环境变化以提升模型的泛化性和鲁棒性；使用一种半自动标注的方式进行数据标注，并对模型进行训练。结果表明：经过Albumentations进行数据增强，同时使用半自动标注的方法，在不需要大量人工标注的情况下可获得较好识别效果。
关键词:
YOLOv11；不安全行为；行为识别；数据增强；Albumentations；半自动标注
Abstract:
The underground working environment is complex and full of safety hazards, while traditional supervision methods are limited and incapable of providing comprehensive real-time monitoring. Therefore, research on recognizing unsafe behaviors of underground personnel using machine learning has become increasingly urgent. This study proposes a recognition method and model for underground personnel's unsafe behaviors based on YOLOv11. Unsafe behaviors are categorized into 3 types: protective equipment-related, hazardous area-related, and dangerous behavior-related. A dataset was constructed according to these categories. The Albumentations was used for data augmentation, simulating underground environmental variations by adjusting lighting conditions, adding noise, and more, to enhance model generalization and robustness. Finally, a semi-automatic labeling method was adopted for data annotation, and the model was trained. The results show that the model, after data augmentation with Albumentations and using semi-automatic labeling, achieved good performance without requiring extensive manual annotation.
Keywords:
YOLOv11; unsafe behavior; behavior recognition; data augmentation; Albumentations; semi-automatic annotation
