Nov, 2025
Journal
ORBITaL-Net: A labeled training library for large-scale building feature extraction
Over the course of several years, nearly 1.5 million building outlines have been created from approximately 128,000 training tiles covering roughly 7,000 km2 of very high-resolution multispectral overhead imagery, primarily dated between 2010 and 2020. This dataset, dubbed the Oak Ridge Building Image and TrAining Label Net (ORBITaL-Net), is designed for machine learning a…