Satellite imagery is crucial for tasks like environmental monitoring and urban planning. Typically, it relies on semantic segmentation or Land Use Land Cover (LULC) classification to categorize each pixel. Despite the advancements brought about by Deep Neural Networks (DNNs), their performance in segmentation tasks is hindered by challenges such as limited availability of labeled data, class imbalance and the inherent variability and complexity of satellite images. In order to mitigate those issues, our study explores the effectiveness of a Cut-and-Paste augmentation technique for semantic segmentation in satellite images. We adapt this augmentation, which usually requires labeled instances, to the case of semantic segmentation. By leveraging the connected components in the semantic segmentation labels, we extract instances that are then randomly pasted during training. Using the DynamicEarthNet dataset and a U-Net model for evaluation, we found that this augmentation significantly enhances the mIoU score on the test set from 37.9 to 44.1. This finding highlights the potential of the Cut-and-Paste augmentation to improve the generalization capabilities of semantic segmentation models in satellite imagery.

Evaluating the Efficacy of Cut-and-Paste Data Augmentation in Semantic Segmentation for Satellite Imagery / Motoi, Ionut M.; Saraceni, Leonardo; Nardi, Daniele; Ciarfuglia, Thomas A.. - (2024), pp. 9802-9806. (Intervento presentato al convegno IEEE International Symposium on Geoscience and Remote Sensing (IGARSS) tenutosi a Athens; Greece) [10.1109/igarss53475.2024.10640734].

Evaluating the Efficacy of Cut-and-Paste Data Augmentation in Semantic Segmentation for Satellite Imagery

Motoi, Ionut M.
Primo
;
Saraceni, Leonardo
;
Nardi, Daniele
;
Ciarfuglia, Thomas A.
2024

Abstract

Satellite imagery is crucial for tasks like environmental monitoring and urban planning. Typically, it relies on semantic segmentation or Land Use Land Cover (LULC) classification to categorize each pixel. Despite the advancements brought about by Deep Neural Networks (DNNs), their performance in segmentation tasks is hindered by challenges such as limited availability of labeled data, class imbalance and the inherent variability and complexity of satellite images. In order to mitigate those issues, our study explores the effectiveness of a Cut-and-Paste augmentation technique for semantic segmentation in satellite images. We adapt this augmentation, which usually requires labeled instances, to the case of semantic segmentation. By leveraging the connected components in the semantic segmentation labels, we extract instances that are then randomly pasted during training. Using the DynamicEarthNet dataset and a U-Net model for evaluation, we found that this augmentation significantly enhances the mIoU score on the test set from 37.9 to 44.1. This finding highlights the potential of the Cut-and-Paste augmentation to improve the generalization capabilities of semantic segmentation models in satellite imagery.
2024
IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)
remote sensing; data augmentation; deep learning
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Evaluating the Efficacy of Cut-and-Paste Data Augmentation in Semantic Segmentation for Satellite Imagery / Motoi, Ionut M.; Saraceni, Leonardo; Nardi, Daniele; Ciarfuglia, Thomas A.. - (2024), pp. 9802-9806. (Intervento presentato al convegno IEEE International Symposium on Geoscience and Remote Sensing (IGARSS) tenutosi a Athens; Greece) [10.1109/igarss53475.2024.10640734].
File allegati a questo prodotto
File Dimensione Formato  
Motoi_preprint_Evaluating_2024.pdf

accesso aperto

Note: DOI: 10.1109/IGARSS53475.2024.10640734
Tipologia: Documento in Pre-print (manoscritto inviato all'editore, precedente alla peer review)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 7.06 MB
Formato Adobe PDF
7.06 MB Adobe PDF
Motoi_Evaluating_2024.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 8.01 MB
Formato Adobe PDF
8.01 MB Adobe PDF   Contatta l'autore

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/11573/1721956
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact