基于YOLO检测模型口罩人脸快速识别技术在无人值守井站的应用  

Application of face mask rapid recognition technology based on YOLO detection model in unattended well station

作　　者：李可欣 Li Kexin(Wuhan Polytechnic University,Wuhan Hubei 404000)

机构地区：[1]武汉轻工大学,湖北武汉430000

出　　处：《石化技术》2022年第7期83-84,48,共3页Petrochemical Industry Technology

摘　　要：近年来随着无人值守井站在行业内逐渐普及,大大提高了采油巡查的效率,但无人值守井站也面临着一定的安全问题,不法分子为获取利益逃避追责,往往采用蒙面或者戴口罩的方式伪装后对采油设施进行破坏,传统的监控设施无法对不法分子进行准确识别定位。为了消除这一安全隐患,笔者提出了基于YOLO(You Only Look Once)检测模型的人脸快速识别技术,解决嵌入式设备上人脸识别检测算法的检测精度低和检测速度慢的问题,实现了佩戴口罩情况下的人脸快速识别,为无人值守井站的安全提供了有力的保障,在一定程度上降低了石油公司的运营成本。In recent years as the unattended well station growing popularity in the industry greatly improve the efficiency of oil production inspections,but unattended well station is faced with certain safety issues,criminals escape liability for interests,often used after masked or wear mouth-muffle disguise to destruction of production facilities,traditional monitoring facilities are not in a position to accurately identify criminals. In order to solve this hidden danger,the author proposes a face recognition technology based on YOLO detection model,which solves the problems of low detection accuracy and slow detection speed of face recognition detection algorithm on embedded devices,and realizes fast face recognition under the condition of wearing masks. It provides a strong guarantee for the safety of unattended well station and reduces the operating cost of oil company.

关 键 词：无人值守井站 安全隐患 YOLO检测模型 口罩人脸快速识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TE48[自动化与计算机技术—计算机科学与技术]