从季节性卫星图像中进行奶牛场地点的弱监督时空候选发现

中文摘要 AI 辅助

从卫星图像中发现农场地点是一个时空候选排名问题，因为农场证据分布在牧场、田界、道路、建筑物和季节性植被模式中。直接的农场标签往往不完整，这使得完全监督检测变得困难。本文提出了一种弱监督管道，用于从季节性哨兵图像和开放地图先验中对奶牛场候选集群进行排名。该方法使用来自爱尔兰科克郡的春季、夏季和秋季对齐图像块，以及光谱带、植被指数、建筑面积指数和一个牧场通道。一个巴洛双胞胎编码器在没有农场标签的情况下学习多季节图像块嵌入。同时，将弱的开放街道地图农场先验分为一个先验集和一个留出集。先验特征支持一个基于规则的图像块分数，该分数结合了农场接近度、季节性牧场证据和夏季绿度，而留出特征仅用于代理评估。规则分数通过地理接近度和嵌入相似度在空间表示图上进行平滑，高分图像块被分组为排名候选集群。从26722个有效图像块中，主要运行选择了535个高置信度图像块并形成了71个候选集群。前5个集群在距离留出的开放街道地图农场特征500米内实现了0.60的精度，在1000米内实现了0.80的精度。前10个集群在500米内实现了0.40的精度，在1000米内实现了0.80的精度。结果表明，季节性表示学习和弱地理先验可以将大型卫星图像集减少为紧凑的候选集以供人工审查。

英文摘要

Farm site discovery from satellite imagery is a spatiotemporal candidate ranking problem because farm evidence is distributed across pasture, field boundaries, roads, buildings, and seasonal vegetation patterns. Direct farm labels are often incomplete, which makes fully supervised detection difficult. This paper proposes a weakly supervised pipeline for ranking dairy farm candidate clusters from seasonal Sentinel imagery and open map priors. The method uses aligned spring, summer, and autumn image tiles from County Cork, Ireland, with spectral bands, vegetation indices, built area indices, and a pasture channel. A Barlow Twins encoder learns multi-season tile embeddings without farm labels. In parallel, weak OpenStreetMap farm priors are split into a prior and a held-out set. Prior features support a rule-based tile score that combines farm proximity, seasonal pasture evidence, and summer greenness, while held-out features are reserved only for proxy evaluation. The rule score is smoothed over a spatial representation graph using geographic proximity and embedding similarity, and high-scoring tiles are grouped into ranked candidate clusters. From 26,722 valid tiles, the main run selects 535 high-confidence tiles and forms 71 candidate clusters. The top 5 clusters achieve 0.60 precision within 500 m and 0.80 precision within 1000 m of held-out OpenStreetMap farm features. The top 10 clusters achieve 0.40 precision within 500 m and 0.80 precision within 1000 m. The results show that seasonal representation learning and weak geographic priors can reduce large satellite image collections into compact candidate sets for human review.

发表机构

• School of Computer Science, University of Galway（戈尔韦大学计算机科学学院）
• Faculty of Computer Science and Engineering, GIK Institute of Engineering Sciences and Technology（工程科学与技术GIK学院计算机科学与工程系）

机构由 AI 辅助整理，请以论文原文为准。