Improved mask detection based on YOLOv5s

Cuihua Tian; Zhihui Li

doi:10.1117/12.2674400

28 April 2023 Improved mask detection based on YOLOv5s

Cuihua Tian, Zhihui Li

Proceedings Volume 12626, International Conference on Signal Processing, Computer Networks, and Communications (SPCNC 2022); 1262619 (2023) https://doi.org/10.1117/12.2674400
Event: International Conference on Signal Processing, Computer Networks, and Communications (SPCNC 2022), 2022, Zhuhai, China

Abstract

COVID-19 epidemic is not over. The correct wearing of masks can effectively prevent the spread of the virus. Aiming at a series of problems of existing mask-wearing detection algorithms, such as only detecting whether to wear or not, being unable to detect whether to wear correctly, difficulty in detecting small targets in dense scenes, and low detection accuracy, It is suggested to use a better algorithm based on YOLOv5s. It improves the generalization and transmission performance of the model by changing the ACON activation function. Then Bifpn is used to replace PAN to effectively integrate the target features of different sizes extracted by the network. Finally, To enable the network to pay attention to a wide area, CA is introduced to the backbone. This embeds the location information into the channel attention.

Citation Download Citation

Cuihua Tian and Zhihui Li "Improved mask detection based on YOLOv5s", Proc. SPIE 12626, International Conference on Signal Processing, Computer Networks, and Communications (SPCNC 2022), 1262619 (28 April 2023); https://doi.org/10.1117/12.2674400

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available