Proper personal protective equipment (PPE) use is critical to prevent disease transmission to healthcare providers, especially those treating patients with a high infection risk. to address the challenge of monitoring PPE usage in healthcare, computer vision has been evaluated for tracking adherence. Existing datasets for this purpose, however, lack a diversity of PPE and nonadherence classes, represent single not multiple providers, and do not depict dynamic provider movement during patient care. We introduce the Resuscitation Room Personal Protective Equipment (R2PPE) dataset that bridges this gap by providing a realistic portrayal of diverse PPE use by multiple interacting individuals in a healthcare setting. This dataset contains 26 videos, 10,034 images and 123,751 bounding box annotations for 17 classes of PPE adherence and nonadherence for eyewear, masks, gowns, and gloves, and one additional head class. Evaluations using newly proposed metrics confirm R2PPE exhibits higher annotation density than three established general-purpose and medical PPE datasets. The R2PPE dataset provides a resource for developing computer vision algorithms for monitoring PPE use in healthcare.
01/17/2025 - The paper was published on Scientific Data.
09/27/2024 - The R2PPE dataset was published on Zenodo.
26 videos
10,034 images
123,751 bounding boxes
18 object classes
12.4 bounding boxes per imageĀ
Yang, W., Kim, M.S., Sippel, G.J. et al. An image dataset for surveillance of personal protective equipment adherence in healthcare. Sci Data 12, 96 (2025). https://doi.org/10.1038/s41597-024-04355-0
We are actively working on generating additional data, including but not limited to:
More PPE types.
More simulation videos.
Models pre-trained with real-case videos to enhance practical generalization.
Expanding data diversity with multi-label images, segmentation annotations, and both image and video data captured from multiple cameras covering the same scene.