computer-vision-agriculture
Computer-vision agriculture applies image-based machine learning algorithms to automatically detect, classify, and monitor crop conditions such as growth stage, disease, or fruiting body development. For plant science, this technology enables rapid, non-invasive, and highly consistent assessment of traits like morphology or maturity that would otherwise require labor-intensive manual observation. By turning visual data into quantifiable measurements, researchers can track subtle developmental or health changes over time, accelerating both cultivation research and yield optimization studies.
open_in_new WikipediaPubMed · 2026-06-29
Researchers built a large, freely available image dataset of shiitake mushrooms photographed in real growing conditions, covering three varieties and four categories including growth stages and deformed specimens. The dataset is designed to train AI systems that can automate mushroom grading, harvesting robots, and yield estimation.
The dataset includes 1,782 original high-resolution images expanded to 6,500 via augmentation, with 43,752 individually annotated mushroom instances.
Three commercially important varieties (9608, Chunsheng No. 1, Qihe No. 9) are represented across three growth stages plus a deformed-mushroom category.
Images capture realistic challenges including complex lighting, occlusion, dense clustering, and multiple viewing angles, making the dataset applicable to real-world AI deployment.
