Building Extraction from Satellite Images Using Mask R-CNN and Swin Transformer

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F24%3APU151204" target="_blank" >RIV/00216305:26220/24:PU151204 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/10524085/" target="_blank" >https://ieeexplore.ieee.org/document/10524085/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/RADIOELEKTRONIKA61599.2024.10524085" target="_blank" >10.1109/RADIOELEKTRONIKA61599.2024.10524085</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Building Extraction from Satellite Images Using Mask R-CNN and Swin Transformer

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Building Extraction from Satellite Images Using Mask R-CNN and Swin Transformer

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20200 - Electrical engineering, Electronic engineering, Information engineering

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2024 34th International Conference Radioelektronika (RADIOELEKTRONIKA)

ISBN

979-8-3503-6216-9

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

„“-„“

Název nakladatele

Institute of Electrical and Electronics Engineers Inc.

Místo vydání

neuveden

Místo konání akce

Žilina, Slovakia

Datum konání akce

17. 4. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001229165000030