FUSU dataset covers 5 whole urban areas, 847 km^2 located in the north and south of China, with 17 land use and land cover (LULC) classes and over 170K images and 30 billion pixels of annotations, supporting segmentation, change detection and domain adaptation tasks.

FUSU features the most detailed land use classification system to date, with 17 classes and 30 billion pixels of annotations. It includes bi-temporal high-resolution satellite images with 0.2-0.5 m ground sample distance and monthly optical and radar satellite time series, covering 847 km^2 across five urban areas in the southern and northern ...

FUSU dataset covers 5 whole urban areas, 847 km^2 located in the north and south of China, with 17 land use and land cover (LULC) classes and over 170K images and 30 billion pixels of annotations, supporting segmentation, change detection and domain adaptation tasks.

2024年12月1日 · FUSU是首个针对细粒度城市 语义理解 的多时态、多源地类变化分割数据集，其提供高分辨率双时态图像和每月时序观测，支持对城市动态变化的高频率监测。 FUSU-Net是统一的时序架构，可同时进行变化检测和分割任务。 结合光学和SAR数据，通过特征融合提升了城市地类分割的精度。 尽管已有多个土地覆盖变化 分割数据 集用于城市变化监测，但这些数据集大多只关注粗粒度的土地覆盖分类系统。 现有数据集在分辨率、覆盖区域、时间间隔和标注精细度 …

2024年12月30日 · FUSU数据集的特点在于其多源性和多时相性，涵盖了高分辨率卫星图像和Sentinel系列卫星的月度数据，支持分割、变化检测和领域适应任务。 数据集包含17种土地利用类别，依据中国土地利用分类标准（GB/T21010-2017）进行标注，提供了丰富的语义信息。

In this paper, we introduce FUSU, the first multi-temporal, multi-source land use change segmentation dataset with the finest pixel-wise change segmentation annotations to date, covering 17 land use classes and over 30 billion pixels.

FUSU dataset covers 5 whole urban areas, 847 km^2 located in the north and south of China, with 17 land use and land cover (LULC) classes and over 170K images and 30 billion pixels of annotations, supporting segmentation, change detection and domain adaptation tasks. This data comprises 2 parts: 1.

fusu具有迄今为止最详细的土地利用分类系统，包括17个类别和300亿个像素的注释。 它包括双时相的高分辨率卫星图像，地面采样距离为20-50厘米，并包括覆盖中国五个城市区域的月度光学和雷达卫星时间序列，总面积为847平方公里。

We present FUSU, a comprehensive multi-source, multi-temporal change segmentation dataset for fine-grained urban semantic understanding. FUSU includes a detailed 17-class land use classification system, 30 billion annotated pixels, 847 km² coverage, and temporal information from bi-temporal high-resolution images and monthly Sentinel data.

2025年1月4日 · FUSU-Fine_grained_Urban_Semantic_Understanding 是 发布的数据集,于 2025-01-03 首发在 HuggingFace 应用于 城市遥感、土地利用分类 领域