期刊名称：International Journal of Early Childhood Special Education
电子版ISSN：1308-5581
出版年度：2022
卷号：14
期号：2
页码：6035-6038
DOI：10.9756/INT-JECSE/V14I2.684
语种：English
出版社：International Journal of Early Childhood Special Education
摘要：Concerns about safety have been a part of the building business for many years now Machine learning has focused on the identification of helmets, but the issue of identifying the wearer has been overlooked in prior studies, which has a negative impact on following safety education for workers. The study of re-identification has been the focus of many researchers, who have overlooked the need for safety detection in the process. For construction workers, this study provides a method based on deep learning that is different from the previous study of helmet detection and human identity recognition and can perform helmet detection and identification. Worker identity and helmet recognition can be accomplished using a computer vision-based system. We used a neural network based on the You Only Look Once (YOLO) v3 model to extract the features of the construction worker's face and helmet from the 3000 real-name channel photos that we collected. Research shows that the system has high recognition accuracy, rapid detection speed, accurate recognition of workers' and helmet detection and solves the problem of poor supervision of real-name channels.
关键词：Concerns about safety have been a part of the building business for many years now Machine learning has focused on the identification of helmets
