Delineate Anything Flow: Fast, Country-Level Field Boundary Detection from Any Source

2025-11-17

AI Summary

Existing field boundary extraction methods suffer from incomplete boundaries, erroneous merging of adjacent parcels, and poor generalization. This paper proposes DelAnyFlow—a resolution-agnostic framework integrating the DelAny model (trained on the FBIS 22M dataset comprising 22.9 million instances) to enable zero-shot generalization and topology-preserving vector boundary generation. The method combines YOLOv11-based instance segmentation, structured post-processing, and a multi-source imagery (e.g., Sentinel-2) vectorization pipeline. Applied to Ukraine-wide 5 m-resolution satellite imagery (603,000 km²), DelAnyFlow extracts 3.75 million fields within six hours on a single workstation. It achieves over 100× higher accuracy than SAM2 and substantially outperforms Sinergise and NASA Harvest products. To our knowledge, this is the first national-scale, high-accuracy, scalable, and fine-grained cropland mapping solution.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Accurate delineation of agricultural field boundaries from satellite imagery is essential for land management and crop monitoring, yet existing methods often produce incomplete boundaries, merge adjacent fields, and struggle to scale. We present the Delineate Anything Flow (DelAnyFlow) methodology, a resolution-agnostic approach for large-scale field boundary mapping. DelAnyFlow combines the DelAny instance segmentation model, based on a YOLOv11 backbone and trained on the large-scale Field Boundary Instance Segmentation-22M (FBIS 22M) dataset, with a structured post-processing, merging, and vectorization sequence to generate topologically consistent vector boundaries. FBIS 22M, the largest dataset of its kind, contains 672,909 multi-resolution image patches (0.25-10m) and 22.9million validated field instances. The DelAny model delivers state-of-the-art accuracy with over 100% higher mAP and 400x faster inference than SAM2. DelAny demonstrates strong zero-shot generalization and supports national-scale applications: using Sentinel 2 data for 2024, DelAnyFlow generated a complete field boundary layer for Ukraine (603,000km2) in under six hours on a single workstation. DelAnyFlow outputs significantly improve boundary completeness relative to operational products from Sinergise Solutions and NASA Harvest, particularly in smallholder and fragmented systems (0.25-1ha). For Ukraine, DelAnyFlow delineated 3.75M fields at 5m and 5.15M at 2.5m, compared to 2.66M detected by Sinergise Solutions and 1.69M by NASA Harvest. This work delivers a scalable, cost-effective methodology for field delineation in regions lacking digital cadastral data. A project landing page with links to model weights, code, national-scale vector outputs, and dataset is available at https://lavreniuk.github.io/Delineate-Anything/.

Problem

• Detecting agricultural field boundaries from satellite imagery accurately
• Addressing incomplete boundaries and merged adjacent fields in existing methods
• Providing scalable field mapping for regions lacking cadastral data

Innovation

• Uses YOLOv11 backbone for instance segmentation
• Leverages large-scale FBIS 22M dataset for training
• Implements structured post-processing for vector boundaries