ORBITaL-Net: A labeled training library for large-scale building feature extraction

Abstract 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 km 2 of very high-resolution multispectral overhead imagery, primarily dated between 2010 and 2020. This dataset, dubbed the Oak Ridge Bu...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Benjamin Swan, Joe Pyle, Darrell Roddy, H. Lexie Yang, Amy Rose, Melanie Laverdiere
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	Nature Portfolio 2025-10-01
Edice:	Scientific Data
On-line přístup:	https://doi.org/10.1038/s41597-025-05677-3
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!