[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 J X,WU X C,WANG S H,et al.Research on Mask W earing Detection of Natural Population ba<x>sed 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卷
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:
Research on Mask W earing Detection of Natural Population ba<x>sed 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 J X WU X C WANG S H et al.
Zhengzhou University School of Network Space Security College;

关键词:
Keywords:
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 net- work 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.

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 ba<x>sed 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 ba<x>sed On Multi-scale Feature Fusion-ncig2020[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