|本期目录/Table of Contents|

[1]杨莉琼,蔡利强,古松.基于机器学习方法的安全帽佩戴行为检测[J].中国安全生产科学技术,2019,15(10):152-157.[doi:10.11731/j.issn.1673-193x.2019.10.024]
 YANG Liqiong,CAI Liqiang,GU Song.Detection on wearing behavior of safety helmet based on machine learning method[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2019,15(10):152-157.[doi:10.11731/j.issn.1673-193x.2019.10.024]
点击复制

基于机器学习方法的安全帽佩戴行为检测
分享到:

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
15
期数:
2019年10期
页码:
152-157
栏目:
职业安全卫生管理与技术
出版日期:
2019-10-31

文章信息/Info

Title:
Detection on wearing behavior of safety helmet based on machine learning method
文章编号:
1673-193X(2019)-10-0152-06
作者:
杨莉琼蔡利强古松
(西南科技大学 土木工程与建筑学院,四川 绵阳 621010)
Author(s):
YANG Liqiong CAI Liqiang GU Song
(College of Civil Engineering and Architecture,Southwest University of Science and Technology,Mianyang Sichuan 621010,China)
关键词:
安全帽佩戴行为机器学习实时检测
Keywords:
safety helmet wearing behavior machine learning realtime detection
分类号:
X947
DOI:
10.11731/j.issn.1673-193x.2019.10.024
文献标志码:
A
摘要:
施工现场作业人员是否佩戴安全帽主要依靠人工检查,存在监管效率低、时效性差等问题,为了实时自动监管作业人员是否佩戴安全帽,提出1种基于机器学习的安全帽佩戴行为检测方法。首先利用深度学习YOLOv3算法检测出现场视频中的施工人员脸部位置,根据安全帽与人脸的关系估算出安全帽潜在区域;然后对安全帽潜在区域图像进行增强处理,使用HOG(方向梯度直方图)提取样本的特征向量;再利用SVM(机器学习的支持向量机)分类器对脸部上方是否有安全帽进行判断,进而实现对施工人员安全帽佩戴行为的实时检测与预警。以某高铁站施工现场为例进行验证,研究数据表明在施工通道和塔吊作业区域,该方法可实时有效检测出工人未佩戴安全帽的行为,识别率达90%。
Abstract:
Whether the construction site operators wear safety hats mainly depends on manual inspection,which has some problems,such as low supervision efficiency and poor timeliness.In order to supervise whether the workers wear the safety helmet in realtime and automatically,a detection method for the wearing behavior of safety helmet based on the machine learning was put forward.Firstly,the face position of worker in the field video was detected by using the deep learning YOLOv3 algorithm,and the potential area of safety hamlet was estimated according to the relationship between safety hamlet and personnel face.Secondly,the enhancement processing was carried out on the image of potential area of safety hamlet,and the characteristic vector of sample was extracted by using the histogram of oriented gradients (HOG).Finally,the support vector machine of machine learning (SVM) classifier was applied to judge whether the safety hamlet was above the face,thus realize the realtime detection and earlywarning on the wearing behavior of safety helmet of the workers.The verification was carried out by taking the construction site of a certain highspeed railway station as an example,and the results showed that in the areas of construction passage and tower crane operation,the behavior of without wearing the safety hamlet of the workers could be detected in realtime and effectively by using this method,and the recognition rate reached 90%.

参考文献/References:

[1]毕林,谢伟,崔君.基于卷积神经网络的矿工安全帽佩戴识别研究[J].黄金科学技术,2017,25(4):73-80. BI Lin,XIE Wei,CUI Jun.Identification research on the miner’s safety helmet wear based on convolutional neural network [J].Gold Science and Technology,2017,25(4):73-80.
[2]徐波,魏利军.基于视频分析技术的违章作业智能监控系统应用研究[J].中国安全生产科学技术,2014,10(S1),79-83. XU Bo,WEI Lijun.Study on application of intelligent monitoring system for work against regulations based on video analysis technology [J].Journal of Safety Science and Technology,2014,10(S1),79-83.
[3]施辉,陈先桥,杨英.改进YOLOv3的安全帽佩戴检测方法[J].计算机工程与应用,2019,55(11):213-220. SHI Hui,CHEN Xianqiao,YANG Ying.Safety helmet wearing detection method of improved YOLOv3 [J].Computer Engineering and Applications,2019,55(11):213-220.
[4]冯国臣,陈艳艳,陈宁,等.基于机器视觉的安全帽自动识别技术研究[J].机械设计与制造工程,2015,44(10):39-42. FENG Guochen,CHEN Yanyan,CHEN Ning,et al.Research on automatic identification technology of the safety helmet based on machine vision [J].Machine Design and Manufacturing Engineering,2015,44(10):39-42.
[5]刘晓慧,叶西宁.肤色检测和Hu矩在安全帽识别中的应用[J].华东理工大学学报(自然科学版),2014,40(3):365-370. LIU Xiaohui,YE Xining.Skin color detection and humoments in helmet recognition research [J].Journal of East China University of Science and Technology(Natural Science Edition),2014,40(3):365-370.
[6]PARK M W,ELSAFTY N,ZHU Z H.Hardhat-wearing detection for enhancing on-site safety of construction workers[J].Journal of Construction Engineering and Management,2015,141(9):1-16.
[7]MNEYMNEH B E,ABBAS M,KHOURY H.Automated hardhat detection for construction safety applications[J].Procedia Engineering,2017,196:895-902.
[8]王忠玉.智能视频监控下的安全帽佩戴检测系统的设计与实现[D]. 北京: 北京邮电大学,2018.
[9]涂思羽,彭平安,蒋元建.基于深度学习的井下环境异常工况智能识别技术研究[J].中国安全生产科学技术,2018,14(11):58-63. TU Siyu,PENG Pingan,JIANG Yuanjian.Research on intelligent recognition technology of abnormal operating conditions in underground environment based on deep learning method [J].Journal of Safety Science and Technology,2018,14(11):58-63.
[10]REN S Q,HE K,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks [J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2015,39(6):1137-1149.
[11]EVERINGHAM M,ESLAMI S M A,VAN G L,et al.The pascal visual object classes challenge:a retrospective [J].International Journal of Computer Vision,2015,111(1):98-136.
[12]徐渊,许晓亮,李才年,等.结合SVM分类器与HOG特征提取的行人检测[J].计算机工程,2016,42(1):56-60,65. XU Yuan,XU Xiaoliang,LI Cainian,et al.Pedestrian detection combining with SVM classifier and HOG feature extraction [J].Computer Engineering,2016,42(1):56-60,65.
[13]GUO J,CHENG J,PANG J X,et al.Real-time hand detection based on multi-stage HOG-SVM classifier [J].IEEE International Conference on Image Processing,2013(1).
[14]韩豫,张泾杰,孙昊,等.基于图像识别的建筑工人智能安全检查系统设计与实现[J].中国安全生产科学技术,2016,12(10):142-148. HAN Yu,ZHANG Jingjie,SUN Hao,et al.Design and implementation of intelligent safety inspection system for construction workers based on image recognition [J].Journal of Safety Science and Technology,2016,12(10):142-148.

相似文献/References:

[1]鞠欣亮.有限元在安全帽设计中的应用[J].中国安全生产科学技术,2012,8(7):143.
 JU Xin liang.Application of finite element analysis in the design of safety helmet[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2012,8(10):143.

备注/Memo

备注/Memo:
收稿日期: 2019-09-03
* 基金项目: 北京市科委项目(Z171100002117001);四川省教育厅科研项目(18zd1137);西南科技大学博士基金项目(13zx7146)
作者简介: 杨莉琼,博士,讲师,主要研究方向为建筑安全管理、建筑信息化。
更新日期/Last Update: 2019-11-05