Vaihingen Dataset for Semantic Segmentation v1.0

The Vaihingen dataset is a high-resolution remote sensing benchmark for 2D semantic labeling, provided by ISPRS WG III/4. It contains 33 true orthophoto tiles (average size 2500×2000 pixels) with a spatial resolution of 9 cm/pixel. File Structure: top: Top-view true orthophotos (TIFF, 3 bands, 8-bit) gts: Ground truth labels (TIFF, single band, 6 classes) dsm: Digital Surface Model (DSM, TIFF, 32-bit float) Technical Specifications: Spatial Resolution: 9 cm/pixel Coordinate System: WGS84 / UTM 32N (EPSG:32632) Number of Tiles: 33 images Label Classes: 6 classes 0: Impervious surfaces 1: Building 2: Low vegetation 3: Tree 4: Car 5: Background Usage Notes: Image and label files share the same naming convention Recommended libraries: GDAL, rasterio (Python), OpenCV