Asset Details
Do you wish to reserve the book?
An improved personal protective equipment detection method based on YOLOv4
Hey, we have placed the reservation for you!
By the way, why not check out events that you can attend while you pick your title.
Oops! Something went wrong.
Looks like we were not able to place the reservation. Kindly try again later.
Are you sure you want to remove the book from the shelf?
An improved personal protective equipment detection method based on YOLOv4
Do you wish to request the book?
An improved personal protective equipment detection method based on YOLOv4
Please be aware that the book you have requested cannot be checked out. If you would like to checkout this book, you can reserve another copy
We have requested the book for you!
Your request is successful and it will be processed during the Library working hours. Please check the status of your request in My Requests.
Oops! Something went wrong.
Looks like we were not able to place your request. Kindly try again later.
Journal Article
An improved personal protective equipment detection method based on YOLOv4
2024
Overview
Personal protective equipment (PPE) detection plays a crucial role in ensuring safety in various settings such as factories, hospitals, and disease prevention measures. However, manually checking individuals for proper PPE usage in public can be a challenging task. This paper focuses on the detection of face mask usage and aims to develop a robust system that can identify individuals who are not wearing masks or are not wearing them correctly. Here, we present an enhanced face mask detection method based on YOLOv4. Currently, there is a shortage of a comprehensive and diverse dataset that can be used to accurately evaluate the correct use of masks, mainly due to limited samples of incorrect mask wearing. To address this issue, we propose a pipeline to generate a simulated face mask dataset derived from the original dataset. This approach allows us to enhance the performance of the face mask detection model without requiring additional data samples. Additionally, we introduce a modified face mask detection model called MaskYOLO, which includes improvements in the original YOLOv4 network structure. In the feature extraction network, a global context block is incorporated between the backbone and neck of YOLOv4 to obtain a more comprehensive understanding of the scene. Furthermore, the prediction network incorporates an improved structure to achieve a more efficient network. The effectiveness and accuracy of the proposed method are demonstrated through statistical analyses of the experimental results. Our method outperforms the YOLOv4 baseline by 3.1% in mean Average Precision (mAP).
Publisher
Springer US,Springer Nature B.V
