The 2022 Wuhan Urban Informal Settlement Dataset (wuhanUIS_2022) provides high-resolution remote sensing imagery and annotations for Wuhan, China. It includes 2-meter spatial resolution Google Earth imagery and corresponding annotation masks in TIFF format, along with COCO-format JSON files for training, validation, and test sets. The dataset was authored by Yulin Ding and released on figshare in 2026.
Use Cases
- Benchmarking urban informal settlement detection algorithms based on the provided annotation masks.
- Training machine learning models for segmentation tasks using the COCO-format training set.
- Reproducing studies on long-term consistent UIS mapping based on the publicly available subset.
- Analyzing the spatial distribution and characteristics of informal settlements in Wuhan based on the 2022 imagery.
Strengths
- Includes high-resolution imagery with a specified 2-meter spatial resolution.
- Provides corresponding annotation masks and structured COCO-format files for machine learning workflows.
- Released under a CC-BY-4.0 license, facilitating open use and sharing.
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- The dataset is a subset; additional temporal data mentioned in the description are not publicly released.
- Row count is unknown, which may limit suitability assessment for certain tasks.
Provenance
- Source
- figshare
- Collection Method
- Likely derived from Google Earth imagery and manually or semi-automatically annotated.
- Time Range
- 2022
- Freshness
- Last updated 2026-05-08 08:57:26; freshness should be verified.
- Geography
- Wuhan, China