Lab-data 和 Field-data

本数据集由温尼伯大学创建，包含两个大规模的植物图像数据集：Lab-data和Field-data，适用于农业领域的机器学习和计算机视觉模型训练。Lab-data包含超过1.2百万张室内种植的作物和杂草图像，而Field-data则包含超过54万张农田中的植物图像。所有图像均按物种标记，并提供详细的元数据。Lab-data中的图像涵盖了多种拍摄角度，而Field-data的图像则主要从顶部拍摄。这些数据集旨在解决农业中的精准识别问题，如作物类型和植物年龄的自动识别，支持智能农业的发展。

This dataset was developed by the University of Winnipeg, and it includes two large-scale plant image datasets: Lab-data and Field-data, which are designed for training machine learning and computer vision models in the agricultural field. Lab-data contains over 1.2 million images of indoor-grown crops and weeds, while Field-data includes more than 540,000 plant images captured in farmlands. All images are labeled by species and come with detailed metadata. Images in Lab-data cover a variety of shooting angles, whereas those in Field-data are mostly captured from a top-down perspective. These datasets aim to solve precise recognition problems in agriculture, such as automatic identification of crop types and plant ages, and support the development of smart agriculture.