[1]薛均晓,武雪程,王世豪,等.基于改进YOLOv4的自然人群口罩佩戴检测研究[J].郑州大学学报(工学版),2022,43(04):16-22.[doi:10.13705/j.issn.1671-6833.2022.04.020]
　XUE Junxiao,WU Xuecheng,WANG Shihao,et al.A Method on Mask Wearing Detection of Natural Population Based on Improved YOLOv4[J].Journal of Zhengzhou University (Engineering Science),2022,43(04):16-22.[doi:10.13705/j.issn.1671-6833.2022.04.020]
点击复制

基于改进YOLOv4的自然人群口罩佩戴检测研究()
分享到：

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

卷:
43
期数:
2022年04期
页码:
16-22
栏目:
出版日期:
2022-07-03

文章信息/Info

Title:
A Method on Mask Wearing Detection of Natural Population Based on Improved YOLOv4
作者:
薛均晓; 武雪程; 王世豪; 田萌萌; 石磊
郑州大学网络空间安全学院;

Author(s):
XUE Junxiao; WU Xuecheng; WANG Shihao; TIAN Mengmeng; SHI Lei
School of Cyber Science and Engineering,Zhengzhou University,Zhengzhou 450002,China
关键词:
Keywords:
deep learning; mask wearing detection; YOLOv4; coordinate attention mechanism; neural network
分类号:
TP39
DOI:
10.13705/j.issn.1671-6833.2022.04.020
文献标志码:
A
摘要:
针对自然场景下的口罩佩戴检测任务中目标较小、易受口罩样式颜色、佩戴者肤色以及天气等多种因素影响的这些特点，我们在原YOLOv4网络的基础上引入了协调注意力机制，进一步加强对于浅层次特征的利用进而更好地捕获小物体——口罩；为了提取到更深层次的特征，本文对YOLOv4的网络结构进行改进，提升感受野，同时增强对深层次特征的表示能力；引入DIOU-NMS方法缓解目标存在遮拦而被错误抑制的现象.实验结果表明，本文算法平均精度均值达到了95.81%，相较于原YOLOv4算法平均精度均值提升了4.62%.改进后的YOLOv4算法具有良好的准确性，能够满足疫情防控场景下的实际需求，完成在自然场景下全面准确的口罩佩戴检测任务
Abstract:
The mask wearing detection in natural scenes is often affected by various factors such as the style and color of the mask,the skin color of the wearer,and the weather.In this study,based on the original YOLOv4,the coordinate attention mechanism was introduced to improve the utilization of the backbone network for spatial information of shallow feature maps and better capture small objects-masks.At the same time,it could enrich the semantic information of shallow feature maps and strengthen the long-distance dependencies to more accurately locate and identify object regions.This paper improved the network structure of YOLOv4 to enhance the capacity and depth of the overall network,so as to expand the receptive fields and improved the robustness of the algorithm.The introduction of DIoU-NMS could alleviate the phenomenon that the object was blocked and incorrectly suppressed.DIoU-NMS could perform NMS from the two aspects of IoU and center point distance of bounding boxes,so that the selection of the IoU threshold was not so harsh.The experimental results showed that the average precision of the improved YOLOv4 was 95.81%,which was 4.62% higher than the average precision of the original YOLOv4.The improved YOLOv4 had exciting performance and could complete the task of comprehensive and accurate mask wearing detection in natural scenarios.

参考文献/References:

[1] REN S Q, HE K M, GIRSHICK R, et al. Faster RCNN: towards real-time object detection with region proposal networks [ J] . IEEE transactions on pattern analysis and machine intelligence, 2017, 39 ( 6 ) : 1137-1149.

 [2] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection [C] / / 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 779 -788.
 [3] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C] / / 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 7263-7271.
 [4] REDMON J, FARHADI A. YOLOv3: an incremental improvement[EB / OL] . ( 2018 - 04 - 08) [ 2021 - 11 - 01] . https: / / arxiv. org / abs/ 1804. 02767.
 [5] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection[EB / OL] . (2020- 04- 23) [ 2021 - 11 - 01] . https: / / arxiv. org / abs/ 2004. 10934. 
[6] WANG C Y, MARK LIAO H Y, WU Y H, et al. CSPNet: a new backbone that can enhance learning capability of CNN [ C] / / 2020 IEEE / CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2020: 390-391. 
[7] LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation[ C] / / 2018 IEEE / CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 8759-8768.
 [8] HOU Q B, ZHOU D Q, FENG J S. Coordinate attention for efficient mobile network design [ C ] / / 2021 IEEE / CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 13713 -13722.
 [9] 张坚鑫, 郭四稳, 张国兰, 等. 基于多尺度特征融 合的火灾检测模型[ J] . 郑州大学学报( 工学版) ,2021, 42(5) : 13-18. 
ZHANG J X, GUO S W, ZHANG G L, et al. Fire detection model based on multi-scale feature fusion[ J] . Journal of Zhengzhou university ( engineering science) , 2021, 42(5) : 13-18. 
[10] 薛均晓, 程君进, 张其斌, 等. 改进轻量级卷积神 经网络的复杂场景口罩佩戴检测方法[ J] . 计算机 辅 助 设 计 与 图 形 学 学 报, 2021, 33 ( 7 ) : 1045 -1054.
 XUE J X, CHENG J J, ZHANG Q B, et al. Improved efficient convolutional neural networks for complex scene mask-wearing detection [ J] . Journal of computer-aided design & computer graphics, 2021, 33( 7) : 1045-1054. 
[11] 李润川, 张行进, 陈刚, 等. 基于多特征融合的心 搏类型识 别 研 究 [ J] . 郑 州 大 学 学 报 ( 工 学 版) , 2021, 42(4) : 7-12.
 LI R C, ZHANG X J, CHEN G, et al. Research on heartbeat type recognition based on multi-feature fusion [ J ] . Journal of Zhengzhou university ( engineering science) , 2021, 42(4) : 7-12. 
[12] LOSHCHILOV I, HUTTER F. SGDR: stochastic gradient descent with warm restarts[EB / OL] . ( 2017- 05- 03 ) [ 2021 - 11 - 01 ] . https: / / arxiv. org / abs/ 1608. 03983v5.
 [13] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector [ C] / / European conference on computer vision. Cham: Springer, 2016: 21-37.

相似文献/References:

[1]赵俊杰,王金伟.基于SmsGAN的对抗样本修复[J].郑州大学学报(工学版),2021,42(01):50.[doi:10.13705/j.issn.1671-6833.2021.01.008]
　ZHAO Junjie,WANG Jinwei,Recovery of Adversarial Examples Based on SmsGAN[J].Journal of Zhengzhou University (Engineering Science),2021,42(04):50.[doi:10.13705/j.issn.1671-6833.2021.01.008]
[2]张坚鑫,郭四稳,张国兰,等.基于多尺度特征融合的火灾检测模型[J].郑州大学学报(工学版),2021,42(05):13.[doi:10.13705/j.issn.1671-6833.2021.05.016]
　Zhang Jianxin,Guo Si Jing,Zhang Guolan,et al.Fire Detection Model Based on Multi-scale Feature Fusion[J].Journal of Zhengzhou University (Engineering Science),2021,42(04):13.[doi:10.13705/j.issn.1671-6833.2021.05.016]

更新日期/Last Update: 2022-07-03