Benchmark Dataset of Cropland Parcel Boundaries from Multi-Source Remote Sensing Imagery for AI application

We provide a standardized dataset of diversified parcel labels based on multi-source remote sensing imagery. The parcels included in this dataset are sourced from four countries: the Netherlands, Denmark, Spain, and China, encompassing over 140,000 cropland parcel. The average parcel size across different study areas ranges from 0.05 hectares to 10 hectares. The remote sensing imagery is derived from more than 10 data sources, including satellites, UAV (unmanned aerial vehicle), and public mapping platforms, with spatial resolutions varying from 0.05 meters to 10 meters.