Super-resolution of synthetic aperture radar complex data by deep-learning

Pia Addabbo, Mario Luca Bernardi, Filippo Biondi, Marta Cimitile, Carmine Clemente, Nicomino Fiscante, Gaetano Giunta, Danilo Orlando

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

19 Downloads (Pure)


One of the greatest limitations of Synthetic Aperture Radar imagery is the capability to obtain an arbitrarily high spatial resolution. Indeed, despite optical sensors, this capability is not just limited by the sensor technology. Instead, improving the SAR spatial resolution requires large transmitted bandwidth and relatively long synthetic apertures that for regulatory and practical reasons are impossible to be met. This issue gets particularly relevant when dealing with Stripmap mode acquisitions and with relatively low carrier frequency sensors (where relatively large bandwidth signals are more difficult to be transmitted). To overcome this limitation, in this paper a deep learning based framework is proposed to enhance the SAR image spatial resolution while retaining the complex image accuracy. Results on simuated and real SAR data demonstrate the effectiveness of the proposed framework.
Original languageEnglish
Title of host publication2022 IEEE 9th International Workshop on Metrology for AeroSpace (MetroAeroSpace)
Place of PublicationPiscataway, NJ
Number of pages5
ISBN (Electronic)9781665410762
ISBN (Print)9781665410779
Publication statusPublished - 18 Aug 2022
Event2022 IEEE 9th International Workshop on Metrology for AeroSpace (MetroAeroSpace) - Pisa, Italy
Duration: 27 Jun 202229 Jun 2022

Publication series

NameIEEE International Workshop on Metrology for Aerospace (MetroAeroSpace)
ISSN (Print)2575-7482
ISSN (Electronic)2575-7490


Conference2022 IEEE 9th International Workshop on Metrology for AeroSpace (MetroAeroSpace)
Abbreviated titleMetroAeroSpace 2022


  • expectation maximization
  • polarimetric radar
  • radar
  • synthetic aperture radar


Dive into the research topics of 'Super-resolution of synthetic aperture radar complex data by deep-learning'. Together they form a unique fingerprint.

Cite this