Medical Waste is a high-resolution image dataset designed for intelligent identification and target detection of medical waste. It aims to help computer vision models achieve automatic detection and classification of medical waste in complex medical environments and is widely used in research areas such as smart healthcare, public health, automated waste sorting, and robot vision. This dataset contains thousands of high-resolution medical waste images and corresponding object detection annotations, covering 13 categories. It adopts a standard object detection annotation format, providing two bounding box annotation files: COCO (.json) and Pascal VOC (.xml). It can be directly adapted to mainstream computer vision frameworks such as PyTorch, TensorFlow, and YOLO. The dataset was manually collected and organized through research on different clinical and laboratory medical waste scenarios, and constructed using manual bounding box annotation. It focuses on covering complex detection scenarios such as transparent materials (glass and plastic), overlapping targets, and targets with large differences in size, in order to simulate the visual challenges in the real medical waste treatment environment.

Data categories

• Gauze (medical gauze)
• Medical Glasses
• Surgical Caps
• Test Tubes
• Urine Bags
• Shoe Covers (in single or paired)
• Latex Gloves (available in single and paired versions)
• Nitrile Gloves (available in single and paired versions)
• Surgical gloves (available in single and paired versions)