|本期目录/Table of Contents|

[1]李千登,王廷春,崔靖文,等.基于深度学习算法的叉车危险操作行为检测[J].中国安全生产科学技术,2020,16(5):155-159.[doi:10.11731/j.issn.1673-193x.2020.05.024]
 LI Qiandeng,WANG Tingchun,CUI Jingwen,et al.Detection on dangerous operation behavior of forklift based on deep learning algorithm[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2020,16(5):155-159.[doi:10.11731/j.issn.1673-193x.2020.05.024]
点击复制

基于深度学习算法的叉车危险操作行为检测
分享到:

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

卷:
16
期数:
2020年5期
页码:
155-159
栏目:
职业安全卫生管理与技术
出版日期:
2020-05-30

文章信息/Info

Title:
Detection on dangerous operation behavior of forklift based on deep learning algorithm
文章编号:
1673-193X(2020)-05-0155-05
作者:
李千登王廷春崔靖文穆波
(1.中国石油化工股份有限公司青岛安全工程研究院,山东 青岛 266104;
2.应急管理部化学品登记中心,山东 青岛 266104)
Author(s):
LI Qiandeng WANG Tingchun CUI Jingwen MU Bo
(1.SINOPEC Research Institute of Safety Engineering,Qingdao Shandong 266104,China;
2.Registration Center for Chemicals of Ministry of Emergency Management,Qingdao Shandong 266104,China)
关键词:
叉车危险行为深度学习算法图像检测系统开发
Keywords:
forklift dangerous behavior deep learning algorithm image detection system development
分类号:
X924.4
DOI:
10.11731/j.issn.1673-193x.2020.05.024
文献标志码:
A
摘要:
随着物流仓储行业快速发展及叉车数量的不断增多,针对叉车作业过程中存在的人员碰撞、挤压、坠落等潜在风险,迫切需要对危险行为进行及时检测和预警。为解决人员值守易漏报误报及传统方法检测精度低的问题,建立基于图像特征识别的叉车检测深度学习模型和算法。通过采集、处理现场视频图像素材,完成模型的训练及性能评价,建立相应的报警规则和报警阈值,搭建测试环境并进行仿真测试,开发相应的软件系统。结果表明:模型检测速率为130 ms/帧,人员靠近叉车准确率为85.6%,叉车举升人员准确率为83.7%,达到良好的实践效果。
Abstract:
With the rapid development of logistics and warehousing industry,the number of forklifts increases rapidly.Aiming at the potential risk of personnel collision,extrusion and downfall during the operation process of forklifts,the timely detection and earlywarning of dangerous behavior is urgently required.In order to solve the problem of prone underreporting and false alarm in the personnel on duty and the low detection accuracy of traditional methods,the deep learning model and algorithm of forklift detection based on the image characteristics recognition were established.Through collecting and processing the field video image material,the training and performance evaluation of the model were completed,and the corresponding alarm rules and threshold values were determined.The testing environment was established,then the simulation tests were carried out,and the corresponding software system was developed.The results showed that the detection rate of the model was 130 milliseconds per frame,the accuracy of personnel close to forklift was 85.6%,and the accuracy of forklift lifting personnel was 83.7%,which achieved good practice effect.

参考文献/References:

[1]高海鹏,李建忠,王俊彤.叉车安全事故成因分析及预防措施[J].特种设备安全技术,2018(4):48-50. GAO Haipeng,LI Jianzhong,WANG Juntong.Cause analysis and preventive measures of forklift safety accident[J].Special Equipment Safety Technology,2018(4):48-50.
[2]河北省安全生产监督管理局.厂内叉车常见安全隐患[J].劳动保护,2018(11):58-59.
[3]国家市场监督管理总局.质检总局关于2015年全国特种设备安全状况情况的通报[EB/OL].(2016-04-05)[2020-03-15].http://www.samr.gov.cn/sj/qtsj/tzsb/201902/t20190228_291555.html.
[4]黄帅.基于联合仿真的平衡重式叉车横向稳定性控制研究[D].合肥:合肥工业大学,2017.
[5]夏光,张洋,唐希雯,等.平衡重式叉车防侧翻分层控制研究[J].中国机械工程,2019,30(17):2066-2075. XIA Guang,ZHANG Yang,TANG Xiwen,et al.Research on anti-rollover hierarchical control of counterbalanced forklift[J].China Mechanical Engineering,2019,30(17):2066-2075.
[6]孙铮,肖本贤.线控转向电动叉车控制系统多故障检测和隔离[J].电子测量与仪器学报,2019,33(8):108-116. SUN Zheng,XIAO Benxian.Electric steering-by-wire forklift control system multiple faults detection and isolation[J].Journal of Electronic Measurement and Inst Rumentation,2019,33(8):108-116.
[7]夏光,杜克,谢海,等.基于侧倾分级的叉车横向稳定性变论域模糊控制[J].机械工程学报,2019,55(12):157-167. XIA Guang,DU Ke,XIE Hai,et al.Variable universe fuzzy control for the lateral stability of forklift based on the roll classification[J].Journal of Mechanical Engineering,2019,55(12):157-167.
[8]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.
[9]苏贵民.基于交通视频和深度学习的车辆检测和跟踪[J].交通与港航,2018,5(4):72-76,88. SU Guimin.Vehicle detection and tracking based on traffic video and deep learning [J].Transportation and Harbor Navigation,2018,5(4):72-76,88.
[10]李千登,王廷春,郝文亮,等.钻井作业典型违章行为视频监控智能分析技术研究[J].工业安全与环保,2019,45(12):46-49. LI Qiandeng,WANG Tingchun,HAO Wenliang,et al.Research on the typical violation intelligent video analysis technology of drilling operation[J].Industrial Safety and Environmental Protection,2019,45(12):46-49.
[11]张红瑞.基于视频图像处理的车辆违章行为检测方法研究[D].兰州:西北师范大学,2018.
[12]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[13]伍伟明.基于Faster R-CNN的目标检测算法的研究[D].广州:华南理工大学,2018.
[14]詹炜,INOMJON R,崔万新,等.基于候选区域的深度学习目标检测算法综述[J].长江大学学报(自然科学版),2019,16(5):108-115. ZHAN Wei,INOMJON R,CUI Wanxin,et al.A review of deep learning target detection algorithms based on candidate regions[J].Journal of Yangtze University(Natural Science Edition),2019,16(5):108-115.
[15]OUYANG W,WANG X.Joint deep learning for pedestrian detection [C]//Proceedings of the 2013 IEEE International Conference on Computer Vision.IEEE,2013:257.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期: 2019-10-12
* 基金项目: 国家重点研发计划项目(2018YFC0809300);山东省重大科技创新工程项目(2018YFJH0802)
作者简介: 李千登,博士研究生,高级工程师,主要研究方向为石油石化行业安全管理信息化。
更新日期/Last Update: 2020-06-10