[1]毛晓波,徐向阳,李楠,等.基于改进SSD和Jetson Nano的口罩佩戴检测门禁系统[J].郑州大学学报(工学版),2021,42(06):87-94.[doi:10.13705/j.issn.1671-6833.2021.06.002]
　Mao Xiaobo,Xu Xiangyang,Li Nan,et al.The Mask Wear Detection Access Control System ba＜x＞sed on Improved SSD and Jetson Nano[J].Journal of Zhengzhou University (Engineering Science),2021,42(06):87-94.[doi:10.13705/j.issn.1671-6833.2021.06.002]
点击复制

基于改进SSD和Jetson Nano的口罩佩戴检测门禁系统()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
42卷
期数:
2021年06期
页码:
87-94
栏目:
出版日期:
2021-11-10

文章信息/Info

Title:
The Mask Wear Detection Access Control System ba＜x＞sed on Improved SSD and Jetson Nano
作者:
毛晓波; 徐向阳; 李楠; 魏刘倩; 刘玉玺; 董梦超; 焦淼鑫
郑州大学电气工程学院;郑州大学机械与动力工程学院;

Author(s):
Mao Xiaobo; Xu Xiangyang; Li Nan; Wei Liuqian; Liu Yuxi; Dong Mengchao; Jiao Miaoxin;
School of Electrical Engineering, Zhengzhou University; School of Mechanical and Power Engineering, Zhengzhou University;

关键词:
Keywords:
DOI:
10.13705/j.issn.1671-6833.2021.06.002
文献标志码:
A
摘要:
为了减少疫情期间人们未佩戴口罩造成的交叉感染机会，设计了一款新颖的门禁系统，快速检测进出口行人是否佩戴口罩，以控制闸机的开合。采用改进的目标检测算法SSD，将原始的VGG特征提取网络替换为MobileNet-V3，取得了78%的MAP；将该模型移植到Jetson Nano开发板上，加装高清显示器，播放系统中的公益广告或者商业广告，并搭配可折叠的平行四边形档板，构成一个完整的多功能门禁系统。以MobileNet-V3为特征提取网络的SSD算法的检测速度为12FPS，与以VGG为特征提取网络的原始SSD算法相比，检测速度提高了6倍，具有良好的应用价值。
Abstract:
In order to reduce the chance of cross infection caused by people not wearing masks during the epidemic period, a novel access control system is designed to quickly detect whether the pedestrians at the entrance and exit wear masks to control the opening and closing of the gate. Using the improved ob＜x＞ject detection algorithm SSD, the original VGG feature extraction network is replaced by mobilenet-v3, and 78% map is obtained the model is transplanted to the Jetson Nano development board, with high-definition display, playing public service or commercial advertisements in the system, and with folding parallelogram baffle, forming a complete multi-functional access control system. The detection speed of SSD algorithm ba＜x＞sed on mobilenet-v3 feature extraction network is 12FPS. Compared with the original SSD algorithm ba＜x＞sed on VGG feature extraction network, the detection speed is increased by 6 times, which has good application value
更新日期/Last Update: 2021-12-17