MUUFL Gulfport is a campus-scale dataset containing co-registered hyperspectral and LiDAR data. The data is labeled for 11 urban land cover classes. The dataset was sourced from Kaggle, but the author, organization, and specific collection details are not provided.
Use Cases
- Classifying urban materials and surfaces based on hyperspectral reflectance signatures.
- Developing fusion models that integrate hyperspectral and LiDAR data for improved land cover mapping.
- Benchmarking machine learning algorithms for pixel-level classification of complex urban scenes.
- Studying the complementary information provided by spectral and elevation data for object delineation.
Strengths
- Dataset includes two complementary remote sensing modalities: hyperspectral and LiDAR.
- Provides labels for 11 distinct urban land cover classes.
- Data is collected at a campus scale, suggesting a controlled, well-documented environment.
Limitations
- Description metadata is limited; actual data quality requires manual inspection after download.
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count is unknown, which may limit suitability assessment.
Provenance
- Source
- Kaggle
- Geography
- Gulfport (likely Mississippi, USA), based on the dataset name.