Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
GIBRIL, M. AL-RUZOUQ, R. BOLCEK, J. SHANABLEH, A. JENA, R.
Originální název
Building Extraction from Satellite Images Using Mask R-CNN and Swin Transformer
Typ
článek ve sborníku ve WoS nebo Scopus
Jazyk
angličtina
Originální abstrakt
Extracting building footprints from satellite or aerial imagery is critical for many applications. Yet, the precise delineation of buildings from very high spatial resolution remotely sensed images remains challenging. This study investigated the potentiality of using Mask R-CNN based on the Swin Transformer and Feature Pyramid Network (FPN) in extracting building footprints from RGB images in heterogeneous urban landscapes. The Swin Transformer and FPN were used to extract multiscale features. The model's performance was compared with several instance segmentation models based on the ResNet-50 backbone, including Mask scoring R-CNN, YOLCAT, and SOLO. Results showed that the model successfully segmented building footprints with a mAP50 and F-measure of 0.85 and 0.89, respectively, outperformed the evaluated instance segmentation models.
Klíčová slova
instance segmentation; swin transformer; building extraction; mask-rcnn; solo
Autoři
GIBRIL, M.; AL-RUZOUQ, R.; BOLCEK, J.; SHANABLEH, A.; JENA, R.
Vydáno
14. 5. 2024
Nakladatel
Institute of Electrical and Electronics Engineers Inc.
ISBN
979-8-3503-6216-9
Kniha
2024 34th International Conference Radioelektronika (RADIOELEKTRONIKA)
Strany počet
5
URL
https://ieeexplore.ieee.org/document/10524085/
BibTex
@inproceedings{BUT188444, author="Mohamed Barakat A. {Gibril} and Rami {Al-Ruzouq} and Jan {Bolcek} and Abdallah {Shanableh} and Ratiranjan {Jena}", title="Building Extraction from Satellite Images Using Mask R-CNN and Swin Transformer", booktitle="2024 34th International Conference Radioelektronika (RADIOELEKTRONIKA)", year="2024", pages="5", publisher="Institute of Electrical and Electronics Engineers Inc.", doi="10.1109/RADIOELEKTRONIKA61599.2024.10524085", isbn="979-8-3503-6216-9", url="https://ieeexplore.ieee.org/document/10524085/" }