基于轻量级OpenPose的井下人员行为检测算法研究
Detection algorithm of underground personnel behavior based on lightweight OpenPose
阮进林 1高鹏 1孙源 1赵明辉2
作者信息
- 1. 国能神东煤炭集团公司保德煤矿,山西 忻州 036600
- 2. 同济大学 电子与信息工程学院,上海 201804;中煤科工集团上海有限公司,上海 200030
- 折叠
摘要
为了能够有效识别煤矿井下工作人员的不安全行为,设计了一种基于轻量级OpenPose算法的井下人员行为智能检测算法.使用轻量级OpenPose网络结构获取红外相机数据中的人体骨骼关键点坐标,然后分别选取不同的骨骼点构建不同的检测算法对摔倒、攀爬以及推搡姿态进行检测.试验结果表明,算法速度达到30 f/s,姿态识别整体准确率为86.35%.将行为检测模型部署到工控机并结合报警器,实现了不安全行为的精准实时检测和及时报警提示.
Abstract
In order to effectively identify the unsafe behavior of underground coal miners,we designed an underground personnel behavior intelligent detection system based on lightweight OpenPose algorithm.The lightweight OpenPose network was used to obtain the coordinates of key points of human skeleton from infrared camera data,and then different recognition algorithms were designed to detect fall,climb and push postures.Experimental results showed that,the algorithm achieved a speed of 30 f/s and the overall accuracy was 86.35%.After deploying the detection model to industrial computers and integrating it with alarms,accurate real-time detection and timely alarm notifications for unsafe behaviors was achieved.
关键词
轻量级OpenPose/骨骼点/姿态检测/工控机/红外摄像机Key words
lightweight OpenPose/bone points/posture detection/IPC/infrared camera引用本文复制引用
出版年
2024
NETL
NSTL
万方数据