界定任意流：从任意源快速生成国家级农田边界
Delineate Anything Flow: Fast, Country-Level Field Boundary Detection from Any Source
AI总结：
本文提出DelAnyFlow方法，通过实例分割和后处理生成高精度农田边界，实现大规模农田边界映射，提升边界完整性与效率。
摘要：
准确从卫星影像中界定农业农田边界对土地管理和作物监测至关重要，但现有方法常产生不完整边界、合并相邻农田且难以扩展。我们提出Delineate Anything Flow（DelAnyFlow）方法，一种分辨率无关的大型农田边界映射方法。DelAnyFlow结合基于YOLOv11主干的DelAny实例分割模型，训练于大规模Field Boundary Instance Segmentation-22M（FBIS 22M）数据集，通过结构化后处理、合并、向量化和简化生成边界向量。FBIS 22M是最大规模的数据集，包含672,909个多分辨率图像块（0.25-10米）和22.9亿个验证过的农田实例。DelAny模型在mAP上超过SAM2 100%且推理速度快400倍。DelAny在零样本泛化和国家级应用中表现优异：使用Sentinel 2数据为2024年，DelAnyFlow在单个工作站下六小时内为乌克兰（603,000平方公里）生成完整农田边界层。DelAnyFlow输出显著提高边界完整性，尤其在小农户和碎片化系统（0.25-1公顷）中。对于乌克兰，DelAnyFlow在5米和2.5米分辨率下分别识别了375万和515万块农田，相比Sinergise Solutions的266万和NASA Harvest的169万。本文提供了一种可扩展且经济的方法，用于缺乏数字地籍数据的地区农田界定。项目页面包含模型权重、代码、国家级向量输出和数据集链接：https://lavreniuk.github.io/Delineate-Anything/。
英文摘要：
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, vectorization, and simplification to generate 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/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
