用SAM模型精准分割卫星影像农田边界，提供新数据集与开源方案
Segment Anything for Satellite Imagery: A Strong Baseline and a Regional Dataset for Automatic Field Delineation
- 基于SAM模型设计微调策略，适配高分辨率卫星影像农田分割
- 在多个区域实现90%以上分割准确率，泛化能力优于现有方法
- 发布全新区域性数据集ERAS，适合农业遥感与计算机视觉研究者
精准绘制农业田块边界对高效农业运营至关重要。借助计算机视觉技术从高分辨率卫星影像中自动提取边界，可避免昂贵的实地调查。本文提出一种基于段落任何模型（SAM）的田块分割流程，引入微调策略以适应该任务。除使用现有公开数据集外，还描述了一种获取补充性区域性数据集的方法，覆盖当前数据源未涵盖的区域。大量实验评估了分割精度并检验了模型泛化能力。所提方法为自动化田块划分提供了可靠基线。新发布的区域性数据集名为ERAS，现已公开可用。
原文摘要 · Abstract (English)
Accurate mapping of agricultural field boundaries is essential for the efficient operation of agriculture. Automatic extraction from high-resolution satellite imagery, supported by computer vision techniques, can avoid costly ground surveys. In this paper, we present a pipeline for field delineation based on the Segment Anything Model (SAM), introducing a fine-tuning strategy to adapt SAM to this task. In addition to using published datasets, we describe a method for acquiring a complementary regional dataset that covers areas beyond current sources. Extensive experiments assess segmentation accuracy and evaluate the generalization capabilities. Our approach provides a robust baseline for automated field delineation. The new regional dataset, known as ERAS, is now publicly available.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。