Multi-class Fruit Detection Dataset for Real-Time Embedded Vision Systems
Abstract
This dataset contains 76.981 annotated images of 31 fruit and vegetable categories.All images are annotated in YOLO format. The dataset includes training, validation,and test splits, as well as the data augmentation scripts used in the experiments. It was created for training lightweight object detection models deployed onembedded platforms such as NVIDIA Jetson devices.
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 12 February 2026
- Document type
- Dataset