Cauli-Det: enhancing cauliflower disease detection with modified YOLOv8

Designed and trained a modified YOLOv8 architecture for multi-class cauliflower disease detection and localization from smartphone-captured field images. Precision 93.2%, recall 82.6%, mAP 91.1% across three disease classes (Bacterial Soft Rot, Downy Mildew, Black Rot) on a 656-image dataset.

Code: github.com/manchitro/cauli-det

DOI: https://doi.org/10.3389/fpls.2024.1373590