CIB-SE-YOLOv8: Optimized YOLOv8 for Real-Time Safety Equipment Detection on Construction Sites

Autor:	Liu, Xiaoyi, Du, Ruina, Tan, Lianghao, Xu, Junran, Chen, Chen, Jiang, Huangqi, Aldwais, Saleh
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	Ensuring safety on construction sites is critical, with helmets playing a key role in reducing injuries. Traditional safety checks are labor-intensive and often insufficient. This study presents a computer vision-based solution using YOLO for real-time helmet detection, leveraging the SHEL5K dataset. Our proposed CIB-SE-YOLOv8 model incorporates SE attention mechanisms and modified C2f blocks, enhancing detection accuracy and efficiency. This model offers a more effective solution for promoting safety compliance on construction sites. Comment: 5 pages, 5 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2410.20699 Zobrazit plný text záznamu View this record from Arxiv