Logo do repositório
 
Publicação

Fast and accurate system for onboard target recognition on raw SAR echo data

2025-10-26Artigo científico Acesso aberto
Ver registo simples
authorProfile.emailbiblioteca@isel.pt
datacite.subject.fosEngenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática
dc.contributor.authorJacinto, Gustavo
dc.contributor.authorVéstias, Mário
dc.contributor.authorFlores, Paulo
dc.contributor.authorDuarte, Rui
dc.date.accessioned2026-01-08T13:27:58Z
dc.date.available2026-01-08T13:27:58Z
dc.date.issued2025-10-26
dc.descriptionThis work is funded by national funds through Fundação para a Ciência e a Tecnologia, I.P. (FCT) under projects UID/6486/2025 and UID/PRR/6486/2025 and under projects UID/50021/2025 and UID/PRR/50021/2025, project 2023.15325.PEX, and project LISBOA2030-FEDER-00692100-15811.
dc.description.abstractSynthetic Aperture Radar (SAR) onboard satellites provides high-resolution Earth imaging independent of weather conditions. SAR data are acquired by an aircraft or satellite and sent to a ground station to be processed. However, for novel applications requiring real-time analysis and decisions, onboard processing is necessary to escape the limited downlink bandwidth and latency. One such application is real-time target recognition, which has emerged as a decisive operation in areas such as defense and surveillance. In recent years, deep learning models have improved the accuracy of target recognition algorithms. However, these are based on optical image processing and are computation and memory expensive, which requires not only processing the SAR pulse data but also optimized models and architectures for efficient deployment in onboard computers. This paper presents a fast and accurate target recognition system directly on raw SAR data using a neural network model. This network receives and processes SAR echo data for fast processing, alleviating the computationally expensive DSP image generation algorithms such as Backprojection and RangeDoppler. Thus, this allows the use of simpler and faster models, while maintaining accuracy. The system was designed, optimized, and tested on low-cost embedded devices with low size, weight, and energy requirements (Khadas VIM3 and Raspberry Pi 5). Results demonstrate that the proposed solution achieves a target classification accuracy for the MSTAR dataset close to 100% in less than 1.5 ms and 5.5 W of power.eng
dc.identifier.citationJacinto, G., Véstias, M., Flores, P., & Duarte, R. P. (2025). Fast and accurate system for onboard target recognition on raw SAR echo data. Remote Sensing, 17(21), 3547. https://doi.org/10.3390/rs17213547
dc.identifier.doi10.3390/rs17213547
dc.identifier.eissn2072-4292
dc.identifier.urihttp://hdl.handle.net/10400.21/22458
dc.language.isoeng
dc.peerreviewedyes
dc.publisherMDPI AG
dc.relationInstituto de Engenharia de Sistemas e Computadores, Investigação e Desenvolvimento em Lisboa
dc.relationUID/PRR/6486/2025
dc.relationUID/50021/2025
dc.relationUID/PRR/50021/2025
dc.relation2023.15325.PEX
dc.relationLISBOA2030-FEDER-00692100-15811
dc.relation.hasversionhttps://www.mdpi.com/2072-4292/17/21/3547
dc.relation.ispartofRemote Sensing
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectSAR echo data
dc.subjectTarget recognition
dc.subjectNeural network
dc.subjectEmbedded
dc.subjectUID/6486/2025
dc.subjectUID/PRR/6486/2025
dc.subjectUID/50021/2025
dc.subjectUID/PRR/50021/2025
dc.subject2023.15325.PEX
dc.subjectLISBOA2030-FEDER-00692100-15811
dc.titleFast and accurate system for onboard target recognition on raw SAR echo dataeng
dc.typejournal article
dspace.entity.typePublication
oaire.awardTitleInstituto de Engenharia de Sistemas e Computadores, Investigação e Desenvolvimento em Lisboa
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UID%2FCEC%2F50021%2F2013/PT
oaire.citation.endPage13
oaire.citation.issue21
oaire.citation.startPage1
oaire.citation.titleRemote Sensing
oaire.citation.volume17
oaire.fundingStream6817 - DCRRNI ID
oaire.versionhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43
person.familyNameVéstias
person.familyNameFlores
person.familyNameDuarte
person.givenNameMário
person.givenNamePaulo
person.givenNameRui
person.identifier.ciencia-id4717-C2C7-3F2C
person.identifier.ciencia-id2E1D-56F2-9C01
person.identifier.ciencia-idB91E-770F-19A3
person.identifier.orcid0000-0001-8556-4507
person.identifier.orcid0000-0002-7013-4202
person.identifier.orcid0000-0002-7060-4745
person.identifier.ridH-9953-2012
person.identifier.ridA-4415-2008
person.identifier.ridI-4402-2015
person.identifier.scopus-author-id14525867300
person.identifier.scopus-author-id9841599800
person.identifier.scopus-author-id24823991600
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
relation.isAuthorOfPublicationa7d22b29-c961-45ac-bc09-cd5e1002f1e8
relation.isAuthorOfPublication3fbdaee0-5d4e-4e16-a39c-31fcc6f71bec
relation.isAuthorOfPublicationf2b4b9e6-6c89-48c7-bc83-62d2e98a787b
relation.isAuthorOfPublication.latestForDiscovery3fbdaee0-5d4e-4e16-a39c-31fcc6f71bec
relation.isProjectOfPublication94be91c6-45fa-4c16-acc4-7d73b4aa32bf
relation.isProjectOfPublication.latestForDiscovery94be91c6-45fa-4c16-acc4-7d73b4aa32bf

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
Fast_MVestias.pdf
Tamanho:
301.15 KB
Formato:
Adobe Portable Document Format
Ver/Abrir
Licença
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
license.txt
Tamanho:
4.03 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Ver/Abrir

Coleções

ISEL - Eng. Elect. Tel. Comp. - Artigos