[1]余阿祥,李承润,于书仪,等.多注意力机制的口罩检测网络[J].南京师范大学学报(工程技术版),2021,(01):023-29.[doi:10.3969/j.issn.1672-1292.2021.01.004]
 Yu Axiang,Li Chengrun,Yu Shuyi,et al.Multi-Attention Mechanism of Mask Wearing Detection Network[J].Journal of Nanjing Normal University(Engineering and Technology),2021,(01):023-29.[doi:10.3969/j.issn.1672-1292.2021.01.004]
点击复制

多注意力机制的口罩检测网络
分享到:

南京师范大学学报(工程技术版)[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2021年01期
页码:
023-29
栏目:
计算机科学与技术
出版日期:
2021-03-15

文章信息/Info

Title:
Multi-Attention Mechanism of Mask Wearing Detection Network
文章编号:
1672-1292(2021)01-0023-07
作者:
余阿祥1李承润1于书仪1李洪均12
(1.南通大学信息科学技术学院,江苏 南通 226019)(2.南京大学计算机软件新技术国家重点实验室,江苏 南京 210023)
Author(s):
Yu Axiang1Li Chengrun1Yu Shuyi1Li Hongjun12
(1.School of Information Science and Technology,Nantong University,Nantong 226019,China)(2.State Key Laboratory for Novel Software Technology,Nanjing University,Nanjing 210023,China)
关键词:
口罩佩戴检测多注意力机制特征挖掘柔性非极大抑制
Keywords:
mask wearing testmulti-attention mechanismfeature of the miningsoft-NMS
分类号:
TP391
DOI:
10.3969/j.issn.1672-1292.2021.01.004
文献标志码:
A
摘要:
提出一种口罩佩戴检测模型,引入多注意力机制,提升了网络特征挖掘能力; 利用柔性非极大抑制方法,消除多余目标检测框. 在公共数据库上的仿真实验表明,该模型检测人脸口罩佩戴的平均精度达到93.81%,帧率达到11.8 fps,能有效地进行人脸口罩佩戴检测.
Abstract:
A mask in public places can effectively control the transmission of the coronavirus. To this end,a mask wearing detection model is proposed. The model introduces a multi-attention mechanism to improve the network feature mining ability and uses soft-NMS methods to eliminate redundant target detection boxes. A simulation experiment is conducted on a public database. The average accuracy of the proposed face mask wearing detection reaches 93.81%,and the frame rate reaches 11.8 fps. The experimental results show that the model can effectively detect the face mask wearing.

参考文献/References:

[1] 赵文明,宋述慧,陈梅丽,等. 2019 新型冠状病毒信息库[J]. 遗传,2020,42(2):212-221.
[2]白浪,王铭,唐小琼,等. 对新型冠状病毒肺炎诊疗中的热点问题的思考[J]. 华西医学,2020,35(2):125-131.
[3]GIRSHICK R,DONAHUE J,DARRELL T,et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Columbus,USA:IEEE Computer Society,2014:580-587.
[4]GIRSHICK R. Fast R-CNN[C]//IEEE International Conference on Computer Vision(CVPR). Santiago,Chile:IEEE Computer Society,2015:1440-1448.
[5]REN S Q,HE K M,GIRSHICK R,et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[6]REDMON J,DIVVALA S,GIRSHICK R,et al. You only look once:unified,real-time object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Las Vegas,USA:IEEE Computer Society,2016:779-788.
[7]LIU W,ANGUELOV D,ERHAN D,et al. SSD:single shot MultiBox detector[C]//European Conference on Computer Vision(ECCV). Amsterdam,Netherlands:ECCV,2016:21-37.
[8]REDMON J,FARHADI A. YOLO9000:better,faster,stronger[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Honolulu,USA:IEEE Computer Society,2017:6517-6525.
[9]REDMON J,FARHAD A. YOLOv3:An incremental improvement[EB/OL]. [2020-08-08]. https://arxiv.org/abs/1804.02767.
[10]LIN T,GOYAL P,GIRSHICK R,et al. Focal loss for dense object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Honolulu,USA:IEEE Computer Society,2017:2999-3007.
[11]TAN M,LE Q V. EfficientNet:rethinking model scaling for convolutional neural networks[C]//International Conference on Machine Learning(ICML). California,USA:IMLS,2019:6105-6114.
[12]TAN M,PANG R,LE Q V,et al. EfficientDet:scalableand efficient object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Seattle,USA:IEEE Computer Society,2020:10781-10790.
[13]HE K M,ZHANG X Y,REN S Q,et al. Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Las Vegas,USA:IEEE Computer Society,2016:770-778.
[14]SIMONYAN K,ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[C]//International Conference of Learning Representation. San Diego,USA,2015.
[15]SANDLER M,HOWARD A,ZHU M,et al. MobileNetV2:inverted residuals and linear bottlenecks[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Salt Lake City,USA:IEEE Computer Society,2018:4510-4520.
[16]LIU S,QI L,QI H,et al. Path aggregation network for instance segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Salt Lake City,USA:IEEE Computer Society,2018:8759-8768.
[17]GHIASI G,LIN T,LE Q V,et al. NAS-FPN:learning scalable feature pyramid architecture for object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Long Beach,USA:IEEE Computer Society,2019:7036-7045.
[18]石磊,王毅,成颖,等. 自然语言处理中的注意力机制研究综述[J]. 数据分析与知识发现,2020,4(5):1-14.
[19]王文冠,沈建冰,贾云得. 视觉注意力检测综述[J]. 软件学报,2019,30(2):416-439.
[20]HU J,SHEN L,SUN G. Squeeze-and-excitation networks[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Salt Lake City,USA:IEEE Computer Society,2018:7132-7141.
[21]BODLA N,SINGH B,CHELLAPPA R,et al. Soft-NMS—Improving object detection with one line of code[C]//IEEE International Conference on Computer Vision(ICCV). Venice,Italy:IEEE Computer Society,2017:5562-5570.
[22]GE S,LI J,YE Q,et al. Detecting masked faces in the wild with LLE-CNNs[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Honolulu,USA:IEEE Computer Society,2017:426-434.
[23]YANG S,LUO P,LOY C C,et al. WIDER FACE:a face detection benchmark[C]//IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Las Vegas,USA:IEEE Computer Society,2016:5525-5533.
[24]KINGMA D P,BA J. Adam:a method for stochastic optimization[C]//The 3rd International Conference for Learning Representations. San Diego,USA,2015.
[25]GLOYOT X,BENGIO Y. Understanding the difficulty of training deep feed forward neural networks[J]. Journal of Machine Learning Research,2010,9:249-250.

备注/Memo

备注/Memo:
收稿日期:2020-08-08.
基金项目:国家自然科学基金项目(61871241、61976120)、南京大学计算机软件新技术国家重点实验室基金项目(KFKT2019B015)、江苏省研究生科研与实践创新计划项目(KYCX19_2056)、南通大学大学生创新训练计划项目(2020109).
通讯作者:李洪均,博士,副教授,研究方向:人工智能. E-mail:lihongjun@ntu.edu.cn
更新日期/Last Update: 2021-03-15