Title: Reflective clothing detection based on YOLOv5s fused with SE attention mechanism

Authors: Yuanyuan Wang; Dingyun Gu; Yemeng Zhu; Zhihan Zhang; Jiahui Cao; Haiyan Zhang

Addresses: School of Computer and Software Engineering, Huaiyin Institute of Technology, Huai'an, 223001, China; Engineering Laboratory of Mobile Interconnection Technology for Internet of Things, Jiangsu Province, Huai'an City, Huai'an, 223001, China ' School of Computer and Software Engineering, Huaiyin Institute of Technology, Huai'an, 223001, China ' School of Computer and Software Engineering, Huaiyin Institute of Technology, Huai'an, 223001, China ' School of Computer and Software Engineering, Huaiyin Institute of Technology, Huai'an, 223001, China ' School of Computer and Software Engineering, Huaiyin Institute of Technology, Huai'an, 223001, China ' School of Computer and Software Engineering, Huaiyin Institute of Technology, Huai'an, 223001, China

Abstract: This paper proposes a YOLOv5s deep learning algorithm incorporating the SE attention mechanism to address the issue of workers failing to wear reflective clothing on duty, which has resulted in casualties from time to time. The YOLOv5s model is used to train the reflective clothing dataset obtained by collecting images of construction sites, and the SE attention mechanism module is added to the network structure of YOLOv5 for improved performance. The reflective clothing detection algorithm is then deployed to the web for real-time detection. The experimental results show that the algorithm achieves mAP value of 96.70% with the SE attention module, resulting in an accuracy improvement of 1.09% compared to the model without the SE module. This enables practical applications to reduce the incidence of construction accidents at construction sites.

Keywords: reflective clothing detection; YOLOv5; attention mechanism; vue; flask.

DOI: 10.1504/IJRIS.2025.145054

International Journal of Reasoning-based Intelligent Systems, 2025 Vol.17 No.1, pp.9 - 16

Received: 20 Feb 2023
Accepted: 27 Apr 2023
Published online: 18 Mar 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article