基于计算机视觉的工业厂区人员安全警戒系统  

Personnel Safety Warning System in Industrial Plant Based on Computer Vision

作　　者：顾成伟 丁勇[1] 李登华[2] GU Cheng-wei;DING Yong;LI Deng-hua(College of Science,Nanjing University of Science and Technology,Nanjing 210094,China;Nanjing Water Conservancy Research Institute,Nanjing 210024,China)

机构地区：[1]南京理工大学理学院,江苏南京210094 [2]南京水利科学研究院,江苏南京210024

出　　处：《计算机与现代化》2023年第9期20-26,共7页Computer and Modernization

基　　金：浙江省水利厅科技计划项目(RB2035);国家自然科学基金资助项目(51979174)。

摘　　要：针对工业厂区起重机械作业安全事故频发,提出一种基于计算机视觉的工业厂区人员安全警戒系统,采用计算平台和目标检测算法相结合的方式对现场作业监控视频中的人员目标实时检测和输出相应控制指令。目标检测算法以YOLOv5网络为基础,在该网络结构中嵌入注意力机制,将基于空间和通道混合注意力机制模块添加到BottleneckCSP模块中,可提高对小目标人员的检测的准确度。此外,还引入人员跟踪算法对检测结果进行修正融合,可降低人员处于遮挡情形时的漏检率。改进后的算法在自建数据集中进行实验,相较原YOLOv5网络,改进后的算法在mAP上提升了3.414个百分点,检测速度可达到40.3 FPS,具有较好的检测效果。最后将算法模型部署到计算平台中并在现场行进警戒系统的搭建和测试,测试统计结果显示对普通人员和领航人员的检测准确率分别为94.4%和95.1%,具有良好的检测性能,可以稳定执行相应自动安全警戒操作。In view of the frequent safety accidents of hoisting machinery in industrial plants,this paper proposes a personnel safety alert system in industrial plants based on computer vision,which uses a combination of computing platform and target de⁃tection algorithm to detect the personnel targets in the field operation monitoring video in real time and output corresponding con⁃trol instructions.The target detection algorithm is based on YOLOv5 network,and the attention mechanism is embedded in the network structure.The space and channel based hybrid attention mechanism module is added to BottleneckCSP module,which can improve the accuracy of small target detection.In addition,a person tracking algorithm is introduced to modify and fuse the detection results,which can reduce the missed detection rate when the person is in the occlusion situation.The improved algo⁃rithm is tested in the self built dataset.Compared with the original YOLOv5 network,the improved algorithm is 3.414 percentage point higher on the mAP,and the detection speed can reach 40.3 FPS,which has a good detection effect.Finally,the algorithm model is deployed to the computing platform,and is built and tested on the scene.The test statistics showe that the detection ac⁃curacy of ordinary personnel and navigators is 94.4%and 95.1%,respectively,which has good detection performance and can stably perform corresponding automatic security alert operations.

关 键 词：起重机械 人员安全警戒系统 目标检测 目标跟踪 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]