劃定萬物：衛星影像上解析度無關的田界劃定

Delineate Anything: Resolution-Agnostic Field Boundary Delineation on Satellite Imagery

April 3, 2025

作者: Mykola Lavreniuk, Nataliia Kussul, Andrii Shelestov, Bohdan Yailymov, Yevhenii Salii, Volodymyr Kuzin, Zoltan Szantoi

cs.AI

摘要

從衛星影像中精確劃定農田邊界對於土地管理和作物監測至關重要。然而，現有方法因數據集規模有限、分辨率差異以及多樣化的環境條件而面臨挑戰。我們通過將任務重新定義為實例分割，並引入Field Boundary Instance Segmentation - 22M數據集（FBIS-22M）來解決這一問題。FBIS-22M是一個大規模、多分辨率的數據集，包含672,909個高分辨率衛星影像片段（分辨率範圍從0.25米到10米）和22,926,427個單個農田的實例掩碼，顯著縮小了農業數據集與其他計算機視覺領域數據集之間的差距。我們進一步提出了Delineate Anything模型，這是一個在我們新開發的FBIS-22M數據集上訓練的實例分割模型。我們提出的模型在[email protected]和[email protected]:0.95指標上分別實現了88.5%和103%的顯著提升，超越了現有方法，同時展示了顯著更快的推理速度以及在多樣化影像分辨率和未見地理區域上的強大零樣本泛化能力。代碼、預訓練模型和FBIS-22M數據集可在https://lavreniuk.github.io/Delineate-Anything獲取。

English

The accurate delineation of agricultural field boundaries from satellite imagery is vital for land management and crop monitoring. However, current methods face challenges due to limited dataset sizes, resolution discrepancies, and diverse environmental conditions. We address this by reformulating the task as instance segmentation and introducing the Field Boundary Instance Segmentation - 22M dataset (FBIS-22M), a large-scale, multi-resolution dataset comprising 672,909 high-resolution satellite image patches (ranging from 0.25 m to 10 m) and 22,926,427 instance masks of individual fields, significantly narrowing the gap between agricultural datasets and those in other computer vision domains. We further propose Delineate Anything, an instance segmentation model trained on our new FBIS-22M dataset. Our proposed model sets a new state-of-the-art, achieving a substantial improvement of 88.5% in [email protected] and 103% in [email protected]:0.95 over existing methods, while also demonstrating significantly faster inference and strong zero-shot generalization across diverse image resolutions and unseen geographic regions. Code, pre-trained models, and the FBIS-22M dataset are available at https://lavreniuk.github.io/Delineate-Anything.