Eggplant Field Detection Dataset

This dataset contains 1,700 original eggplant images with bounding box annotations in YOLO format for fruit detection in field environments. The images cover occlusion, dense fruit distributions, small targets, and varying illumination conditions. The dataset is divided into training, validation, and test sets containing 1,208, 260, and 232 images, respectively. The original dataset partition is preserved in the directory structure. This release includes the original images, annotations, dataset configuration, and documentation. Offline-augmented training images, controlled illumination perturbation images, model source code, and trained weights are not included. Contact: [e-mail]. Dataset documentation and updates: [Zzz-0110/SCPD-YOLO-Eggplant-Dataset: Eggplant field detection dataset with YOLO annotations. Data hosted on Zenodo.]