用U-Net模型从卫星图自动识别农田界线，提升土地管理效率。
Detecting Cadastral Boundary from Satellite Images Using U-Net model
- 基于ResNet34的U-Net模型，三类语义分割识别界线、农田和背景。
- 在伊朗农田卫星图上，精度88%、召回率75%、F-score达81%。
- 适合土地测绘、智慧农业等需要自动化边界提取的场景。
确定农田的不动产边界是土地管理中的关键问题。因此，利用深度学习方法加速并简化从卫星图像和无人机（UAV）图像中提取不动产边界至关重要。本文采用迁移学习，使用以ResNet34为骨干网络的U-Net模型，通过三类语义分割（“界线”、“农田”、“背景”）检测不动产边界。我们在伊朗的两组农田卫星图像上进行评估，采用“精度”、“召回率”和“F-score”作为指标，分别达到88%、75%和81%，结果表现良好。
原文摘要 · Abstract (English)
Finding the cadastral boundaries of farmlands is a crucial concern for land administration. Therefore, using deep learning methods to expedite and simplify the extraction of cadastral boundaries from satellite and unmanned aerial vehicle (UAV) images is critical. In this paper, we employ transfer learning to train a U-Net model with a ResNet34 backbone to detect cadastral boundaries through three-class semantic segmentation: "boundary", "field", and "background". We evaluate the performance on two satellite images from farmlands in Iran using "precision", "recall", and "F-score", achieving high values of 88%, 75%, and 81%, respectively, which indicate promising results.
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。