Building Instance Segmentation for Dense Urban Settlements
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (45) · 38460-38468
DOI: 10.1609/aaai.v40i45.41187 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Adnan Firoze und 2 weiteren Autor:innen.
Abstract (Originalsprache)
About 25% of the world’s population live in informal urban settlements containing densely packed buildings (approximately 8,000 houses per square-km) which do not lend themselves favorably to state-of-the-art satellite-based building segmentation methods due to, for example, occlusion, vegetation, shadows and low resolution. To address these challenges, we introduce a novel instance segmentation and counting approach for dense buildings. Our system first extracts a conservative set of tentative building center points using a deep network for jumpstarting a Segment Anything Model 2 (SAM2) module to produce an initial over-segmentation. Second, we use a graph neural network to refine the over-segmented regions into polygons representing accurate building masks. Experiments show that our approach achieves higher accuracy in instance segmentation and counting especially in challenging densely packed building areas in Brazil, Mexico, India, Pakistan, and Kenya, for instance.
Zitieren
APA
Firoze, A., Yeh, R. A., & Aliaga, D. (2026). Building Instance Segmentation for Dense Urban Settlements. Proceedings of the AAAI Conference on Artificial Intelligence, 40(45), 38460-38468. https://doi.org/10.1609/aaai.v40i45.41187
Vancouver
Firoze A, Yeh RA, Aliaga D. Building Instance Segmentation for Dense Urban Settlements. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(45):38460-38468. doi:10.1609/aaai.v40i45.41187
BibTeX
@article{Firoze2026,
author = {Firoze, Adnan and Yeh, Raymond A. and Aliaga, Daniel},
title = {Building Instance Segmentation for Dense Urban Settlements},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {45},
pages = {38460--38468},
doi = {10.1609/aaai.v40i45.41187}
}
EUVIMED