UAV-derived building heights and floor counts for the University of Texas at Dallas (July 2025 dataset)
Year: 2025
Type: data-paper
Abstract: This Data Article presents a campus-scale dataset of building heights and estimated floor counts for the University of Texas at Dallas (UTD). Heights were derived from an unmanned aerial vehicle (UAV) photogrammetry workflow using a DJI Mavic 3 Multispectral (M3M) and ArcGIS Drone2Map (2024.2.0) to generate a Digital Surface Model (DSM), Digital Terrain Model (DTM), and true orthomosaic at 0.024 m ground sampling distance (GSD). Building footprints from OpenStreetMap (OSM) were refined and used with zonal statistics in ArcGIS Pro to summarize per-building height metrics (mean, median, min, max, std, pixel count). Estimated floor counts were computed using a representative floor height of 4.10 m. Validation against 38 buildings with ground-truth building height achieved height RMSE of 0.72 m (R² = 0.97) and floor-count RMSE of 0.52 floors with mean bias +0.04 floors (R² = 0.72). The dataset includes 373 continuous drone images, raster images (DSM/DTM/), building vectors with attributes, CSV tables for zonal statistics and validation, ArcGIS Pro models and scripts/metadata for reproducibility.
Source: Data in Brief
Authors: Shuang Tian, Fang Qiu
Institution: The University of Texas at Dallas
Language: English
Subfield: Geology
Field: Earth and Planetary Sciences
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,220
OpenAlex ID: W4416754180