基于YOLOv4-tiny改进的轻量级口罩检测算法

朱杰; 王建立; 王斌

doi:10.37188/CJLCD.2021-0059

您当前的位置：

首页 >

文章列表页 >

基于YOLOv4-tiny改进的轻量级口罩检测算法

目标检测与跟踪 | 更新时间：2021-11-08

- 基于YOLOv4-tiny改进的轻量级口罩检测算法
- Lightweight mask detection algorithm based on improved YOLOv4-tiny
- 液晶与显示 2021年36卷第11期页码：1525-1534
- 作者机构：
  
  1.中国科学院长春光学精密机械与物理研究所, 吉林长春 130033
  2.中国科学院大学, 北京 100049
- 作者简介：
  
  [ "朱杰(1996-)，男，贵州毕节人，硕士研究生，2018年于中国科学技术大学获得学士学位，主要从事计算机视觉方面的研究。E-mail:zhujie181@mails.ucas.ac.cn" ]
  [ "王建立(1971-)，男，山东曲阜人，博士，研究员，2002年于中国科学院长春光学精密机械与物理研究所获得博士学位，主要从事地基空间目标光电探测技术、光电精密跟踪控制技术、光电精密测量误差补偿技术、大口径望远镜总体技术、大型军用光电系统总体集成技术等方面的研究。E-mail: wangjianli@ciomp.ac.cn" ]
- 基金信息：
  
  国家自然科学基金(11703024)
- DOI：10.37188/CJLCD.2021-0059
  中图分类号： TP391.41
- 收稿日期：2021-03-01，
  
  修回日期：2021-03-26，
  
  纸质出版日期：2021-11
- 稿件说明：
移动端阅览
朱杰, 王建立, 王斌. 基于YOLOv4-tiny改进的轻量级口罩检测算法[J]. 液晶与显示, 2021,36(11):1525-1534.

Jie ZHU, Jian-li WANG, Bin WANG. Lightweight mask detection algorithm based on improved YOLOv4-tiny[J]. Chinese journal of liquid crystals and displays, 2021, 36(11): 1525-1534.
朱杰, 王建立, 王斌. 基于YOLOv4-tiny改进的轻量级口罩检测算法[J]. 液晶与显示, 2021,36(11):1525-1534. DOI： 10.37188/CJLCD.2021-0059.

Jie ZHU, Jian-li WANG, Bin WANG. Lightweight mask detection algorithm based on improved YOLOv4-tiny[J]. Chinese journal of liquid crystals and displays, 2021, 36(11): 1525-1534. DOI： 10.37188/CJLCD.2021-0059.

摘要

新冠疫情防控期间，为防止病毒扩散，需要在机场、车站等公共场所对人流的口罩佩戴情况实施管控。为了高效地监测人流的口罩佩戴情况，提出了一种基于YOLOv4-tiny改进的轻量级口罩检测算法。在YOLOv4-tiny的骨干网络之后引入空间金字塔池化结构，对输入特征层进行多尺度池化并融合，同时大幅增强网络的感受野。结合路径聚合网络，分两条路径将不同尺度的特征层相互融合、反复增强，以提升特征层对目标的表达能力。使用标签平滑策略优化了网络损失函数，以抑制网络训练过程中的过拟合问题。实验结果表明，该算法在口罩目标和人脸目标上的检测精度分别达到了94.7%和85.7%，相比于YOLOv4-tiny分别提高了4.3%和7.1%，实时检测速度达到76.8 FPS (on GeForce GTX 1050Ti)，满足了多种场景下口罩检测任务的检测精度与实时性要求。

Abstract

During the period of 2019-nCoV controlling

to prevent the spread of the virus

it is necessary to regulate the coverage of mask wearing in densely populated places such as airports and stations. In order to effectively monitor the coverage of mask wearing of crowd

this paper proposes a lightweight mask detection algorithm based on improved YOLOv4-tiny. Following the backbone network of YOLOv4-tiny

a spatial pyramid pooling structure is introduced to pool and fuse the input features at multi-scale

which makes the receptive field of the network enhanced. Then

combined with the path aggregation network

multi-scale features are fused and enhanced repeatedly in two paths to improve the expressive ability of feature maps. Finally

label smoothing is utilized to optimize the loss function for modifying the over-fitting problem in the training process. The experimental results show that the proposed algorithm achieves 94.7% AP and 85.7% AP on mask target and face target respectively (at real-time speed of 76.8 FPS on GeForce GTX 1050ti)

which is 4.3% and 7.1% higher than that of YOLOv4-tiny. The proposed algorithm meets the accuracy and real-time requirements of mask detection tasks in various scenes.

关键词

Keywords

references

REDMON J, DIVVALA S, GIRSHICK R, et al . You only look once: unified, real-time object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas: IEEE, 2016: 779-788.

REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Honolulu: IEEE, 2017: 6517-6525.

REDMON J, FARHADI A. Yolov3: an incremental improvement[J]. arXiv : 1804.02767, 2018.

BOCHKOVSKIY A, WANG C Y, LIAO H Y M. Yolov4: optimal speed and accuracy of object detection[J]. arXiv : 2004.10934, 2020.

WANG C Y, BOCHKOVSKIY A, LIAO H Y M. Scaled-YOLOv4: scaling cross stage partial network[J]. arXiv : 2011.08036, 2020.

R GIRSHICK , J DONAHUE , T DARRELL , 等 . Region-based convolutional networks for accurate object detection and segmentation . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2016 . 38 ( 1 ): 142 - 158 . DOI: 10.1109/TPAMI.2015.2437384 http://doi.org/10.1109/TPAMI.2015.2437384 .

GIRSHICK R. Fast R-CNN[C]// Proceedings of the IEEE International Conference on Computer Vision . Santiago: IEEE, 2015: 1440-1448.

S Q REN , K M HE , R GIRSHICK , 等 . Faster R-CNN: towards real-time object detection with region proposal networks . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017 . 39 ( 6 ): 1137 - 1149 . DOI: 10.1109/TPAMI.2016.2577031 http://doi.org/10.1109/TPAMI.2016.2577031 .

A CABANI , K HAMMOUDI , H BENHABILES , 等 . MaskedFace-Net-a dataset of correctly/incorrectly masked face images in the context of COVID-19 . Smart Health , 2021 . 19 100144 DOI: 10.1016/j.smhl.2020.100144 http://doi.org/10.1016/j.smhl.2020.100144 .

WANG Z Y, WANG G C, HUANG B J, et al . Masked face recognition dataset and application[J]. arXiv : 2003.09093, 2020.

牛作东 , 覃涛 , 李捍东 , 等 . 改进RetinaFace的自然场景口罩佩戴检测算法 . 计算机工程与应用 , 2020 . 56 ( 12 ): 1 - 7 . https://www.cnki.com.cn/Article/CJFDTOTAL-JSGG202012002.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JSGG202012002.htm .

Z D NIU , T QIN , H D LI , 等 . Improved algorithm of RetinaFace for natural scene mask wear detection . Computer Engineering and Applications , 2020 . 56 ( 12 ): 1 - 7 . https://www.cnki.com.cn/Article/CJFDTOTAL-JSGG202012002.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JSGG202012002.htm .

王艺皓 , 丁洪伟 , 李波 , 等 . 复杂场景下基于改进YOLOv3的口罩佩戴检测算法 . 计算机工程 , 2020 . 46 ( 11 ): 12 - 22 . https://www.cnki.com.cn/Article/CJFDTOTAL-JSJC202011002.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JSJC202011002.htm .

Y H WANG , H W DING , B LI , 等 . Mask wearing detection algorithm based on improved YOLOv3 in complex scenes . Computer Engineering , 2020 . 46 ( 11 ): 12 - 22 . https://www.cnki.com.cn/Article/CJFDTOTAL-JSJC202011002.htm https://www.cnki.com.cn/Article/CJFDTOTAL-JSJC202011002.htm .

LIN T Y, MAIRE M, BELONGIE S, et al . Microsoft COCO: common objects in context[C]//13 th European Conference on Computer Vision . Zurich: Springer, 2014: 740-755.

K M HE , X Y ZHANG , S Q REN , 等 . Spatial pyramid pooling in deep convolutional networks for visual recognition . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2015 . 37 ( 9 ): 1904 - 1916 . DOI: 10.1109/TPAMI.2015.2389824 http://doi.org/10.1109/TPAMI.2015.2389824 .

LIU S, QI L, QIN H F, et al . Path aggregation network for instance segmentation[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Salt Lake City: IEEE, 2018: 8759-8768.

LIN T Y, DOLLÁR P, GIRSHICK R, et al . Feature pyramid networks for object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . Honolulu: IEEE, 2017: 936-944.

MVLLER R, KORNBLITH S, HINTON G. When does label smoothing help?[J]. arXiv : 1906.02629, 2019.

WANG C Y, LIAO H Y M, WU Y H, et al . CSPNet: a new backbone that can enhance learning capability of CNN[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops . Seattle: IEEE, 2020: 1571-1580.

Z H ZHENG , P WANG , W LIU , 等 . Distance-IoU loss: faster and better learning for bounding box regression . Proceedings of the AAAI Conference on Artificial Intelligence , 2020 . 34 ( 7 ): 12993 - 13000 . DOI: 10.1609/aaai.v34i07.6999 http://doi.org/10.1609/aaai.v34i07.6999 .

LIU W, ANGUELOV D, ERHAN D, et al . SSD: single shot multibox detector[C]//14 th European Conference on Computer Vision . Amsterdam: Springer, 2016: 21-37.

SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. arXiv : 1409.1556, 2014.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于改进YOLO11的无人机航拍图像小目标检测算法

基于双分支在线优化和特征融合的视频目标跟踪算法

基于边缘增强和特征融合的伪装目标分割

基于Double-Head的雾天图像目标检测