AgriDataValue - Weed Detection Image Dataset

AgriDataValue aims to establish itself as the “Game Changer” in Smart Farming digital transformation and agri-environmental monitoring, and strengthen the smart-farming capacities, competitiveness and fair income by introducing an innovative, open source, intelligent and multi-technology, fully distributed Agri-Environment Data Space (ADS). To achieve technological maturity, fast and massive acceptance, AgriDataValue adopts and adapts a multidimensional approach that combines state of the art big data and data-spaces’ technologies (BDVA/ IDSA/ GAIA-X) with agricultural knowledge, monetization, new business models and agri-environment policies, leverages on existing platforms, edge computing and network/ services, and introduces novel concepts, methods, tools, pilot facilities and engagement campaigns to go beyond today’s state of the art, perform breakthrough research and create sustainable innovation in upscaling (real-time) agricultural sensor data, already evident within the project lifetime.

--------------------------------------------------------------------------------------------------------------------------------------------

This dataset contains images along with their bounding box annotations for the purpose of weed detection. The bounding box annotations are in Yolo format and include two classes 'Crop' and 'Weed'.

The images were captured by a UAV over a field seeded with celeriac. The resolution of the images is 5280(width) x 3956(height).

Due to images' high resolution, image tiling and patching is encouraged (e.g. to 640x480) to also increase the number of images. Train/test/validation splitting was done in a random manner.

AgriDataValue旨在成为智慧农业数字化转型与农业环境监测领域的“变革者”，通过推出创新、开源、智能且多技术融合的全分布式农业环境数据空间（Agri-Environment Data Space, ADS），提升智慧农业发展能力、产业竞争力与从业者公平收益。为实现技术成熟度提升与快速大规模普及，AgriDataValue采用并适配了多维度融合路径：将当前前沿的大数据与数据空间技术（BDVA/ IDSA/ GAIA-X）与农业知识体系、商业化变现模式、新型商业模式及农业环境政策相结合，依托现有平台、边缘计算及网络服务体系，并引入全新概念、方法、工具、试点设施与推广活动，以突破当前技术前沿，在项目周期内已初见成效的规模化（实时）农业传感器数据领域开展突破性研究并打造可持续创新成果。

本数据集包含用于杂草检测任务的图像及其边界框标注，标注采用Yolo格式，涵盖“作物（Crop）”与“杂草（Weed）”两个类别。
图像由无人机（Unmanned Aerial Vehicle, UAV）在播种了块根芹的农田中采集，图像分辨率为5280（宽）×3956（高）。
由于图像分辨率较高，为扩充样本量，建议对图像进行分块处理（例如切分为640×480规格）。数据集的训练集/测试集/验证集划分采用随机方式完成。