Multi-Scale Fusion Mask Wearing Detection Method Based on Improved YOLOV5s

被引：0

作者：

Yang, Guoliang ^{[1
]}

Yu, Shuaiying ^{[1
]}

Yang, Hao ^{[1
]}

机构：

[1] School of Electrical Engineering and Automation, Jiangxi University of Science and Technology, Jiangxi, Ganzhou

来源：

Computer Engineering and Applications | 2023年 / 59卷 / 14期

关键词：

attention mechanism; EIoU loss; feature grouping; mask wearing detection; small object detection; YOLOV5s;

D O I：

10.3778/j.issn.1002-8331.2301-0171

中图分类号：

学科分类号：

摘要：

Aiming at the problems of low detection accuracy and high missed detection rate of small targets in the mask wearing detection algorithm in complex scenes, a mask wearing detection model based on improved YOLOV5s is proposed. In order to alleviate the problem of information loss caused by continuous downsampling, an inverted adaptive attention module（IAAM）is proposed. In order to improve the sensing ability of high-resolution detection layer to global information, a channel feature grouping module（CFGM）is designed, and the small object detection accuracy is greatly improved by using this module. Combined with the data features in the actual scene, EIoU Loss is introduced, and the color space transformation in data enhancement is cancelled. Experimental results show that the improved model has improved recall rate, detection accuracy, inference speed and detection ability of small targets, and can complete real-time mask wearing detection task in complex scenes. © 2023 Journal of Computer Engineering and Applications Beijing Co., Ltd.; Science Press. All rights reserved.

引用

页码：184 / 191

页数：7

共 21 条

[1]

HU Z L, SONG C, Et al., Clinical characteristics of 24 asymptomatic infections with COVID-19 screened among close contacts in Nanjing，China[J], Science China （Life Sciences, 63, 5, pp. 706-719, (2020)

[2]

WU S, ZHAO D N., Survey of object detection based on deep convolutional network[J], Pattern Recognition and Artificial Intelligence, 31, 4, pp. 335-346, (2018)

[3]

ZAIDI S, ANSARI M S, ASLAM A, Et al., A survey of modern deep learning based object detection models[J], Digital Signal Processing, 126, (2022)

[4]

DESAI K, PARIKH S, PATEL K, Et al., Survey of object detection algorithms and techniques[C], Cybernetics，Cognition and Machine Learning Applications, pp. 247-257, (2020)

[5]

LI X B, LI Y G，, GUO N，, Et al., Mask detection algorithm based on YOLOv5 intergrating attention mechanism[J], Journal of Graphics, 44, 1, pp. 16-25, (2023)

[6]

CHEN Z J, ZENG L J., Multi category mask wearing detection based on dynamic weighted category balance loss[J], Journal of Graphics, 43, 4, pp. 590-598, (2022)

[7]

WANG B, LE H X, LI W J，, Et al., Mask detection algorithm based on improved YOLO lightweight network[J], Computer Engineering and Applications, 57, 8, pp. 62-69, (2021)

[8]

CHENG H R, WANG X T，, LI J R，, Et al., Improved YOLOv4-tiny epidemic collaborative mask wearing detection method[J], Computer Engineering and Applications

[9]

ZHU J, WANG J L, WANG B., Lightweight mask detection algorithm based on improved YOLOv4-tiny[J], Chinese Journal Liquid Crystal and Display, 36, 11, pp. 1525-1534, (2021)

[10]

LU Y C., Mask wearing detection model based on SSD algorithm[J], Technology and Innovation, 18, pp. 101-103, (2022)

← 1 2 3 →