一种基于树莓派的口罩自动检测装置  

Automatic Mask Detection Device based on Raspberry Pie

作　　者：张丽艳[1] 赵艺璇 李林[1] ZHANG Liyan;ZHAO Yixuan;LI Lin(School of Computer and Communication Engineering,Dalian Jiaotong University,Dalian 116028,China)

机构地区：[1]大连交通大学计算机与通信工程学院,辽宁大连116028

出　　处：《大连交通大学学报》2022年第1期111-114,共4页Journal of Dalian Jiaotong University

基　　金：辽宁省教育厅高等学校科学研究计划资助项目(JDL2020029)。

摘　　要：应用树莓派设计了一种可以自动识别顾客是否佩戴口罩的仿真装置.首先,超声波传感器检测到有人经过时,调用树莓派摄像头进行拍照;照片从客户端传输到服务端计算机,树莓派LED闪烁1s作为提示.运用SSD目标检测算法进行人脸是否佩戴口罩的检测;最后,服务端将检测结果反馈给客户端,如检测到人脸佩戴口罩,舵机会按正反顺序各旋转90°,模拟控制门的开和关,检测到未佩戴口罩舵机不转动表示装置始终呈关闭状态.经测试,SSD模型mAP值达到97.21%,装置可以实现较好的检测效果.Raspberry Pi is used to design an automatic door simulation device that can automatically identify whether customers wear masks.When the ultrasonic sensor detects someone passing by,it calls the Raspberry Pi camera to take a picture,the picture is transmitted from the client to the server computer,and the Raspberry Pi LED flashes for 1 second as a reminder.The SSD target detection algorithm is use to detect whether the face is wearing a mask.Finally,the server will feedback the detection result to the client.If someone is detected without wearing a mask,the servo does not rotate,indicating that the automatic door is always closed.After testing,the mAP value of the SSD model reaches 97.21%,and the device can achieve a better detection effect.

关 键 词：树莓派 客户端 服务端 SSD模型 MAP 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]