AI4boundaries

Description

An open AI-ready dataset to map field boundaries with Sentinel-2 and aerial photography

European Commission, Joint Research Centre (JRC) (2022): AI4boundaries. European Commission, Joint Research Centre (JRC) [Dataset] PID: http://data.europa.eu/89h/0e79ce5d-e4c8-4721-8773-59a4acf2c9c9

FTP

Publication 2022

AI4boundaries

D`andrimont, R., Claverie, M., Kempeneers, P., Muraro, D., Martinez Sanchez, L. and Waldner, F., AI4boundaries, European Commission, 2022, JRC129491.

Abstract

Field boundaries are at the core of many agricultural applications and is a key enabler for operational monitoring of agricultural production to support food security. Recent scientific progress on deep learning methods has highlighted the capacity to extract field boundaries from satellite and aerial images with a clear improvement from object-based image analysis (e.g. multiresolution segmentation) or conventional filters (e.g. Sobel filters). However, these methods need labels to be trained. So far, no benchmark dataset exists to easily achieve this comparison. Absence of such benchmark data further impedes proper comparison with existing methods. Besides, there is no consensus on which evaluation metrics should be reported (both at the pixel and field levels). As a result, it is currently impossible to compare and benchmark new and existing methods.To fill these gaps, we propose the AI4Boundaries, an AI-ready dataset (i.e. labels and images) for field boundary detection to facilitate model development and comparison with three specific datasets: a single-date Sentinel-2 composite for large-scale, near real-time application such as crop mapping, a Sentinel-2 monthly composites for large-scale analyses in retrospect,

a 1-m orthophoto dataset for regional-scale analyses such as the automatic extraction of Geospatial Aid Application (GSAA)