Using Deep Learning and Very-High-Resolution Imagery to Map Smallholder Field Boundaries

• Published in: Remote sensing (Basel, Switzerland) Vol. 14; no. 13; p. 3046
• Main Authors: Mei, Weiye, Wang, Haoyu, Fouhey, David, Zhou, Weiqi, Hinks, Isabella, Gray, Josh M., Van Berkel, Derek, Jain, Meha
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.07.2022
• Subjects: Accuracy; Agricultural production; Agriculture; Artificial neural networks; Boundaries; Datasets; Deep learning; Digitization; Farmers; Farming systems; Farms; field boundary delineation; Food production; High resolution; Image resolution; India; Mask R-CNN; Neural networks; Remote sensing; Satellite imagery; Seasons; smallholder farms; Wind; WorldView-3; India

The mapping of field boundaries can provide important information for increasing food production and security in agricultural systems across the globe. Remote sensing can provide a viable way to map field boundaries across large geographic extents, yet few studies have used satellite imagery to map...