Lightweight DB-YOLO mask-wearing intelligent detection and android application based on bidirectional weighted feature fusion

Qin, B., Zeng, Y., Wang, X., Peng, J., Li, T., Wang, T. and Qin, Y. (2023) Lightweight DB-YOLO mask-wearing intelligent detection and android application based on bidirectional weighted feature fusion. Electronics, 12(24), 4936. (doi: 10.3390/electronics12244936)

Abstract

Conventional facemask detection algorithms face challenges of insufficient accuracy, large model size, and slow computation speed, limiting their deployment in real-world scenarios, especially on edge devices. Aiming at addressing these issues, we proposed a DB-YOLO facemask intelligent detection algorithm, which is a lightweight solution that leverages bidirectional weighted feature fusion. Our method is built on the YOLOv5 algorithm model, replacing the original YOLOv5 backbone network with the lightweight ShuffleNetv2 to reduce parameters and computational requirements. Additionally, we integrated BiFPN as the feature fusion layer, enhancing the model’s detection capability for objects of various scales. Furthermore, we employed a CARAFE lightweight upsampling factor to improve the model’s perception of details and small-sized objects and the EIOU loss function to expedite model convergence. We validated the effectiveness of our proposed method through experiments conducted on the Pascal VOC2007+2012 and Face_Mask datasets. Our experimental results demonstrate that the DB-YOLO model boasts a compact size of approximately 1.92 M. It achieves average precision values of 70.1% and 93.5% on the Pascal VOC2007+2012 and Face_Mask datasets, respectively, showcasing a 2.3% improvement in average precision compared to the original YOLOv5s. Furthermore, the model’s size is reduced by 85.8%. We also successfully deployed the model on Android devices using the NCNN framework, achieving a detection speed of up to 33 frames per second. Compared to lightweight algorithm models like YOLOv5n, YOLOv4-Tiny, and YOLOv3-Tiny, DB-YOLO not only reduces the model’s size but also effectively improves detection accuracy, exhibiting excellent practicality and promotional value on edge devices.

• Item Type: Articles
• Additional Information: Financial support was provided in part by the National Natural Science Foundation of 464 China (grant number. 62373142, 62033014, 61903136), Natural Science Foundation of Hunan Prov- 465 ince (grant number. 2021JJ50006, 2022JJ50074). Hunan Engineering Research Center of Electric Drive 466 and Regenerative Energy Storage and Utilization.
• Keywords: Object detection, YOLOv5, lightweight, BiFPN, edge deployment.
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Qin, Yuxin

Creator Roles

Qin, Y.: Visualization, Writing – review and editing

• Authors: Qin, B., Zeng, Y., Wang, X., Peng, J., Li, T., Wang, T., and Qin, Y.
• College/School: College of Science and Engineering > School of Computing Science
• Journal Name: Electronics
• Publisher: MDPI
• ISSN: 2079-9292
• ISSN (Online): 2079-9292
• Copyright Holders: Copyright © 2023 by the Authors
• First Published: First published in Electronics 12(24):4936
• Publisher Policy: Reproduced under a creative commons licence