CPPE-5 (Medical Personal Protective Equipment)
收藏资源简介:
CPPE-5数据集是由多伦多大学计算机科学系创建的,专注于医疗个人防护装备的次级分类。该数据集包含1029张图像,主要来源于Flickr和Google Images,每张图像都标注了边界框和正标签,涵盖了5个对象类别:防护服、面罩、手套、口罩和护目镜。数据集的创建旨在帮助机器自动识别个人防护装备的具体位置,特别是在复杂场景中的应用。此外,数据集强调收集非典型图像,确保所有图像都是真实生活中的场景,不同于其他现有数据集。CPPE-5数据集的应用领域包括在多个公共场所自动识别是否佩戴了PPE套装以及套装的哪些部分被佩戴,尤其在医疗场景中具有重要意义。
CPPE-5 Dataset was developed by the Department of Computer Science, University of Toronto, and focuses on the secondary classification of medical personal protective equipment (PPE). This dataset consists of 1029 images primarily sourced from Flickr and Google Images. Each image is annotated with bounding boxes and positive labels, covering five object categories: protective clothing, face shields, gloves, masks, and goggles. The dataset is constructed to enable machines to automatically identify the specific locations of personal protective equipment, especially for applications in complex scenarios. Additionally, the dataset prioritizes collecting atypical images to ensure all included images are real-life scenes, differentiating it from other existing datasets. The application fields of the CPPE-5 Dataset include automatically recognizing whether PPE kits are worn and which parts of the kits are worn across various public places, which is particularly significant in medical scenarios.

- 1CPPE-5: Medical Personal Protective Equipment Dataset多伦多大学计算机科学系 · 2023年



