PRUE: A Practical Recipe for Field Boundary Segmentation at Scale

arXiv cs.CV / 3/31/2026

📰 NewsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper presents the first systematic evaluation of segmentation methods and geospatial foundation models for global field boundary delineation using the Fields of The World (FTW) benchmark.
Testing 18 models under unified experimental settings, it finds that a U-Net semantic segmentation model beats instance-based and GFM alternatives across performance and deployment-oriented metrics.
The authors propose a PRUE-style segmentation approach combining a U-Net backbone, composite loss functions, and targeted data augmentations to improve robustness to real-world variations like illumination and geographic changes.
The proposed method reaches 76% IoU and 47% object-F1 on FTW, improving the prior baseline by 6% and 9% respectively.
The paper releases all models and model-derived field boundary datasets for five countries, aiming to make field mapping workflows more reproducible and scalable.

Abstract

Large-scale maps of field boundaries are essential for agricultural monitoring tasks. Existing deep learning approaches for satellite-based field mapping are sensitive to illumination, spatial scale, and changes in geographic location. We conduct the first systematic evaluation of segmentation and geospatial foundation models (GFMs) for global field boundary delineation using the Fields of The World (FTW) benchmark. We evaluate 18 models under unified experimental settings, showing that a U-Net semantic segmentation model outperforms instance-based and GFM alternatives on a suite of performance and deployment metrics. We propose a new segmentation approach that combines a U-Net backbone, composite loss functions, and targeted data augmentations to enhance performance and robustness under real-world conditions. Our model achieves a 76\% IoU and 47\% object-F1 on FTW, an increase of 6\% and 9\% over the previous baseline. Our approach provides a practical framework for reliable, scalable, and reproducible field boundary delineation across model design, training, and inference. We release all models and model-derived field boundary datasets for five countries.