Voxel51/PlantSeg-Test

PlantSeg是一个大规模野外植物病害分割数据集，包含11,458张带有高质量分割掩码的图像，涵盖115种病害类别和34种植物类型。与现有在受控实验室环境中收集的植物病害数据集不同，PlantSeg主要包含具有复杂背景、不同视角和光照条件的真实世界田间图像。数据集还包括按植物类型分类的8,000张健康植物图像。数据集由昆士兰大学和CSIRO农业与食品部门策划，采用CC BY-NC-ND 4.0许可。

PlantSeg is a large-scale in-the-wild dataset for plant disease segmentation, containing 11,458 images with high-quality segmentation masks across 115 disease categories and 34 plant types. Unlike existing plant disease datasets that are collected in controlled laboratory settings, PlantSeg primarily comprises real-world field images with complex backgrounds, various viewpoints, and different lighting conditions. The dataset also includes an additional 8,000 healthy plant images categorized by plant type. The dataset is curated by The University of Queensland and CSIRO Agriculture and Food, with a CC BY-NC-ND 4.0 license.