In this study, we proposed a deep learning-based approach for detecting multiple scatterers in SAR tomography. Unlike the forested areas, urban environments typically contain only a few dominant scatterers in each resolution cell. To estimate scatterer locations, various techniques have been developed to address the underlying version problem. Here, we investigate the potential of deep learning to tackle this challenge. Simulation experiments demonstrated that the proposed method achieves superior performance compared to traditional approaches.
DL-based Method for Scatterers Detection and Elevation Estimation of Building Areas with SAR Tomography
Yang, Wenyu;Franceschini, Stefano;Vitale, Sergio;Ferraioli, Giampaolo;Pascazio, Vito;Schirinzi, Gilda
2025-01-01
Abstract
In this study, we proposed a deep learning-based approach for detecting multiple scatterers in SAR tomography. Unlike the forested areas, urban environments typically contain only a few dominant scatterers in each resolution cell. To estimate scatterer locations, various techniques have been developed to address the underlying version problem. Here, we investigate the potential of deep learning to tackle this challenge. Simulation experiments demonstrated that the proposed method achieves superior performance compared to traditional approaches.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
