Maritime target classification from SLC SAR data Spectral Profiles

Laura Parra Garcia; Carmine Clemente; Christos Ilioudis; Ernesto Imbembo; Gianluca Furano; Filippo Biondi; Danilo Orlando; Pia Addabbo

Maritime target classification from SLC SAR data Spectral Profiles

Laura Parra Garcia
, Carmine Clemente
, Christos Ilioudis
, Ernesto Imbembo
, Gianluca Furano
, Filippo Biondi
, Danilo Orlando
, Pia Addabbo

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

Abstract

In this study, an approach for automatic target recognition in Synthetic aperture radar (SAR) imaging, based on the spectral information of the SAR data is introduced. This work focuses on developing a binary classifier exploiting the
spectral information from different ships in the single look complex format (SLC), and the performance of the proposed approach is evaluated on SLC (before and after radiometric calibration) SAR data from Sentinel-1. A Recurrent Neural Network is developed for the classification task and the classes “cargo” and “tanker” are selected for the assessment. As a result, an accuracy of over 69% is obtained in the recognition.

Original language	English
Title of host publication	15th European Conference on Synthetic Aperture Radar, 2024
Publisher	IEEE
ISBN (Print)	978-3-8007-6286-6
Publication status	Published - 30 Aug 2024
Event	15th European Conference on Synthetic Aperture Radar - Munich, Germany Duration: 23 Apr 2024 → 26 Apr 2024

Conference

Conference	15th European Conference on Synthetic Aperture Radar
Abbreviated title	EUSAR 2024
Country/Territory	Germany
City	Munich
Period	23/04/24 → 26/04/24

Keywords

synthetic aperture radar (SAR)
Neural Network

Access to Document

https://ieeexplore.ieee.org/abstract/document/10659611

Cite this

@inproceedings{353c20fc40634a089066c97e41138dfb,

title = "Maritime target classification from SLC SAR data Spectral Profiles",

abstract = "In this study, an approach for automatic target recognition in Synthetic aperture radar (SAR) imaging, based on the spectral information of the SAR data is introduced. This work focuses on developing a binary classifier exploiting the spectral information from different ships in the single look complex format (SLC), and the performance of the proposed approach is evaluated on SLC (before and after radiometric calibration) SAR data from Sentinel-1. A Recurrent Neural Network is developed for the classification task and the classes “cargo” and “tanker” are selected for the assessment. As a result, an accuracy of over 69\% is obtained in the recognition.",

keywords = "synthetic aperture radar (SAR), Neural Network",

author = "\{Parra Garcia\}, Laura and Carmine Clemente and Christos Ilioudis and Ernesto Imbembo and Gianluca Furano and Filippo Biondi and Danilo Orlando and Pia Addabbo",

year = "2024",

month = aug,

day = "30",

language = "English",

isbn = "978-3-8007-6286-6",

booktitle = "15th European Conference on Synthetic Aperture Radar, 2024",

publisher = "IEEE",

note = "15th European Conference on Synthetic Aperture Radar, EUSAR 2024 ; Conference date: 23-04-2024 Through 26-04-2024",

}

Parra Garcia, L , Clemente, C, Ilioudis, C, Imbembo, E, Furano, G, Biondi, F, Orlando, D & Addabbo, P 2024, Maritime target classification from SLC SAR data Spectral Profiles. in 15th European Conference on Synthetic Aperture Radar, 2024. IEEE, 15th European Conference on Synthetic Aperture Radar, Munich, Germany, 23/04/24. <https://ieeexplore.ieee.org/abstract/document/10659611>

TY - GEN

T1 - Maritime target classification from SLC SAR data Spectral Profiles

AU - Parra Garcia, Laura

AU - Clemente, Carmine

AU - Ilioudis, Christos

AU - Imbembo, Ernesto

AU - Furano, Gianluca

AU - Biondi, Filippo

AU - Orlando, Danilo

AU - Addabbo, Pia

PY - 2024/8/30

Y1 - 2024/8/30

N2 - In this study, an approach for automatic target recognition in Synthetic aperture radar (SAR) imaging, based on the spectral information of the SAR data is introduced. This work focuses on developing a binary classifier exploiting the spectral information from different ships in the single look complex format (SLC), and the performance of the proposed approach is evaluated on SLC (before and after radiometric calibration) SAR data from Sentinel-1. A Recurrent Neural Network is developed for the classification task and the classes “cargo” and “tanker” are selected for the assessment. As a result, an accuracy of over 69% is obtained in the recognition.

AB - In this study, an approach for automatic target recognition in Synthetic aperture radar (SAR) imaging, based on the spectral information of the SAR data is introduced. This work focuses on developing a binary classifier exploiting the spectral information from different ships in the single look complex format (SLC), and the performance of the proposed approach is evaluated on SLC (before and after radiometric calibration) SAR data from Sentinel-1. A Recurrent Neural Network is developed for the classification task and the classes “cargo” and “tanker” are selected for the assessment. As a result, an accuracy of over 69% is obtained in the recognition.

KW - synthetic aperture radar (SAR)

KW - Neural Network

M3 - Conference contribution book

SN - 978-3-8007-6286-6

BT - 15th European Conference on Synthetic Aperture Radar, 2024

PB - IEEE

T2 - 15th European Conference on Synthetic Aperture Radar

Y2 - 23 April 2024 through 26 April 2024

ER -

Maritime target classification from SLC SAR data Spectral Profiles

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this