Land cover (LC) segmentation plays a critical role in various applications, including environmental analysis and natural disaster management. However, generating accurate LC maps is a complex and time-consuming task that requires the expertise of multiple annotators and regular updates to account for environmental changes. In this work, we introduce SPADA, a framework for fuel map delineation that addresses the challenges associated with LC segmentation using sparse annotations and domain adaptation techniques for semantic segmentation. Performance evaluations using reliable ground truths, such as LUCAS and Urban Atlas, demonstrate the technique's effectiveness. SPADA outperforms state-of-the-art semantic segmentation approaches as well as third-party products, achieving a mean Intersection over Union (IoU) score of 42.86 and an F1 score of 67.93 on Urban Atlas and LUCAS, respectively.

Land Cover Segmentation with Sparse Annotations from Sentinel-2 Imagery / Galatola, Marco; Arnaudo, Edoardo; Barco, Luca; Rossi, Claudio; Dominici, Fabrizio. - ELETTRONICO. - (2023), pp. 6952-6955. (Intervento presentato al convegno 2023 IEEE International Symposium on Geoscience and Remote Sensing (IGARSS 2023) tenutosi a Pasadena (USA) nel 16 - 21 July, 2023) [10.1109/IGARSS52108.2023.10281933].

Land Cover Segmentation with Sparse Annotations from Sentinel-2 Imagery

Arnaudo, Edoardo;Barco, Luca;Dominici, Fabrizio
2023

Abstract

Land cover (LC) segmentation plays a critical role in various applications, including environmental analysis and natural disaster management. However, generating accurate LC maps is a complex and time-consuming task that requires the expertise of multiple annotators and regular updates to account for environmental changes. In this work, we introduce SPADA, a framework for fuel map delineation that addresses the challenges associated with LC segmentation using sparse annotations and domain adaptation techniques for semantic segmentation. Performance evaluations using reliable ground truths, such as LUCAS and Urban Atlas, demonstrate the technique's effectiveness. SPADA outperforms state-of-the-art semantic segmentation approaches as well as third-party products, achieving a mean Intersection over Union (IoU) score of 42.86 and an F1 score of 67.93 on Urban Atlas and LUCAS, respectively.
2023
979-8-3503-2010-7
File in questo prodotto:
File Dimensione Formato  
IGARSS_2023_land_cover_compressed.pdf

accesso aperto

Descrizione: Camera ready
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Pubblico - Tutti i diritti riservati
Dimensione 521.11 kB
Formato Adobe PDF
521.11 kB Adobe PDF Visualizza/Apri
Land_Cover_Segmentation_with_Sparse_Annotations_from_Sentinel-2_Imagery.pdf

accesso riservato

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 304.21 kB
Formato Adobe PDF
304.21 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2981337