Finding Ground-based Radars in SAR images: Localizing Radio Frequency Interference using Unsupervised Deep Learning

Synthetic Aperture Radar (SAR) satellite images are used increasingly more for Earth observation. While SAR images are useable in most conditions, they occasionally experience image degradation due to interfering signals from external radars, called Radio Frequency Interference (RFI). RFI affected i...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on geoscience and remote sensing Ročník 61; s. 1
Hlavní autoři:	Sorensen, Kristian Aa, Kusk, Anders, Heiselberg, Peder, Heiselberg, Henning
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.01.2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Anomalies anomaly classification and localization Classification convolutional autoencoder Deep learning Image degradation Image reconstruction Radar Radar imaging Radio Radio frequency Radio frequency interference radio frequency interference (RFI) SAR (radar) Satellite imagery Ships Synthetic aperture radar synthetic aperture radar (SAR)
ISSN:	0196-2892, 1558-0644
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Synthetic Aperture Radar (SAR) satellite images are used increasingly more for Earth observation. While SAR images are useable in most conditions, they occasionally experience image degradation due to interfering signals from external radars, called Radio Frequency Interference (RFI). RFI affected images are often discarded in further analysis or pre-processed to remove the RFI. However, few on-ground radars can cause RFI in SAR images and such information can thus increase domain awareness greatly over both land and sea, where, e.g ., localizing and characterizing RFI signals in the ocean could help classify otherwise overlooked ships. The aim of the current study is to detect and localize RFI signals automatically in Sentinel-1 level-1 images and further characterize the on-ground radar. The spatial structure of RFI signals vary greatly. A convolutional autoencoder was therefore developed to reconstruct RFI-free Sentinel-1 images. Conversely, RFI-affected images could not be well reconstructed. Anomalous heatmaps were then developed to automatically detect and localize RFI anomalies in the images under varying environmental and geographical conditions whereafter the external radar characteristics were extracted manually from Sentinel-1 level-0 data. We could consequently classify and localize RFI signals believed to originate from both stationary radars and ship-borne radars. We further argue that the calculated ship-borne radar characteristics correspond to those of air-surveillance radars. Empirically, the method showed better detection results than those of previous studies. Our study shows that more information can be extracted from certain detected objects, such as ships, from SAR images.
AbstractList	Synthetic Aperture Radar (SAR) satellite images are used increasingly more for Earth observation. While SAR images are useable in most conditions, they occasionally experience image degradation due to interfering signals from external radars, called Radio Frequency Interference (RFI). RFI affected images are often discarded in further analysis or pre-processed to remove the RFI. However, few on-ground radars can cause RFI in SAR images and such information can thus increase domain awareness greatly over both land and sea, where, e.g ., localizing and characterizing RFI signals in the ocean could help classify otherwise overlooked ships. The aim of the current study is to detect and localize RFI signals automatically in Sentinel-1 level-1 images and further characterize the on-ground radar. The spatial structure of RFI signals vary greatly. A convolutional autoencoder was therefore developed to reconstruct RFI-free Sentinel-1 images. Conversely, RFI-affected images could not be well reconstructed. Anomalous heatmaps were then developed to automatically detect and localize RFI anomalies in the images under varying environmental and geographical conditions whereafter the external radar characteristics were extracted manually from Sentinel-1 level-0 data. We could consequently classify and localize RFI signals believed to originate from both stationary radars and ship-borne radars. We further argue that the calculated ship-borne radar characteristics correspond to those of air-surveillance radars. Empirically, the method showed better detection results than those of previous studies. Our study shows that more information can be extracted from certain detected objects, such as ships, from SAR images. Synthetic aperture radar (SAR) satellite images are used increasingly more for Earth observation. While SAR images are useable in most conditions, they occasionally experience image degradation due to interfering signals from external radars, called radio frequency interference (RFI). RFI-affected images are often discarded in further analysis or preprocessed to remove the RFI. However, few on-ground radars can cause RFI in SAR images and such information can thus increase domain awareness greatly over both land and sea, where, e.g., localizing and characterizing RFI signals in the ocean could help classify otherwise overlooked ships. The aim of the current study is to detect and localize RFI signals automatically in Sentinel-1 level-1 images and further characterize the on-ground radar. The spatial structure of RFI signals vary greatly. A convolutional autoencoder (CAE) was therefore developed to reconstruct RFI-free Sentinel-1 images. Conversely, RFI-affected images could not be well reconstructed. Anomalous heatmaps were then developed to automatically detect and localize RFI anomalies in the images under varying environmental and geographical conditions, whereafter the external radar characteristics were extracted manually from Sentinel-1 level-0 data. We could consequently classify and localize RFI signals believed to originate from both stationary radars and ship-borne radars. We further argue that the calculated ship-borne radar characteristics correspond to those of air-surveillance radars. Empirically, the method showed better detection results than those of previous studies. Our study shows that more information can be extracted from certain detected objects, such as ships, from SAR images.
Author	Heiselberg, Peder Kusk, Anders Heiselberg, Henning Sorensen, Kristian Aa
Author_xml	– sequence: 1 givenname: Kristian Aa orcidid: 0000-0001-6443-1297 surname: Sorensen fullname: Sorensen, Kristian Aa organization: Center for Security located at the National Space Institute of Denmark, Technical University of Denmark, Ørsteds Plads, building 348, Kgs. Lyngby, Denmark – sequence: 2 givenname: Anders orcidid: 0000-0001-7822-4758 surname: Kusk fullname: Kusk, Anders organization: Department of Microwaves and Remote Sensing, The National Space Institute of Denmark, Technical University of Denmark, Ørsteds Plads, building 348, Kgs. Lyngby, Denmark – sequence: 3 givenname: Peder orcidid: 0000-0002-8847-634X surname: Heiselberg fullname: Heiselberg, Peder organization: Department of Geodesy and Earth Observation, The National Space Institute of Denmark, Technical University of Denmark, Elektrovej, building 327 and 328, Kgs. Lyngby, Denmark – sequence: 4 givenname: Henning surname: Heiselberg fullname: Heiselberg, Henning organization: Center for Security located at the National Space Institute of Denmark, Technical University of Denmark, Ørsteds Plads, building 348, Kgs. Lyngby, Denmark
BookMark	eNp9kE1LAzEQhoMoWD9-gOAh4HnrJNntJt5EbRUKQj_OyzQ7W1Jqtia7Qv317tIexIOnYZjnfWfmvWCnvvbE2I2AoRBg7heT2XwoQaqhkiYDkCdsILJMJzBK01M2AGFGidRGnrOLGDcAIs1EPmBx7Hzp_JpPQt36MllhpJLPsMQQufN8_jjj7gPXFB_4tLa4dd893QGu5uNAny15u-dvvqFQUega4m3skaWP7Y7Cl-sNn4l2fEoYfDe6YmcVbiNdH-slW45fFk-vyfR98vb0OE2sUnmTkB2hWmkEVeq8StGshEFVinRV5UZloNFUGiVpAakFLAkk2gyQRJWDtVJdsruD7y7U3Z2xKTZ1G3y3spA6NQKkznRHiQNlQx1joKrYhe7jsC8EFH22RZ9t0WdbHLPtNPkfjXUNNq72TUC3_Vd5e1A6Ivq1SWillVI_wuuKPQ
CODEN	IGRSD2
CitedBy_id	crossref_primary_10_1109_ACCESS_2024_3507862 crossref_primary_10_1109_JSTARS_2024_3394445 crossref_primary_10_1109_TMTT_2023_3318669 crossref_primary_10_1016_j_apor_2024_104241 crossref_primary_10_1016_j_rse_2025_114955 crossref_primary_10_1109_JSTARS_2025_3559171
Cites_doi	10.1109/ACSSC.2003.1292216 10.1109/ICCV.2019.00179 10.1109/IGARSS.2018.8519373 10.1109/TGRS.2022.3190288 10.1109/COMITE.2013.6545070 10.1109/TGRS.2022.3213318 10.1109/TGRS.2022.3170363 10.1109/MGRS.2018.2832057 10.1109/TGRS.2013.2252469 10.3390/rs9111183 10.3390/rs13010007 10.3390/rs11202438 10.1109/IGARSS.2017.8127666 10.3390/rs14092236 10.1109/IGARSS39084.2020.9323726 10.1109/ACCESS.2021.3056504 10.1007/s11263-020-01419-7 10.1109/TGRS.2021.3049472 10.3390/rs11141654 10.3390/s20102919 10.1109/TIP.2003.819861 10.4236/jcc.2019.73002 10.23919/URSIAP-RASC.2019.8738633 10.3390/s18114034
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID	97E ESBDL RIA RIE AAYXX CITATION 7UA 8FD C1K F1W FR3 H8D H96 KR7 L.G L7M
DOI	10.1109/TGRS.2023.3295002
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore CrossRef Water Resources Abstracts Technology Research Database Environmental Sciences and Pollution Management ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Aerospace Database Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Aerospace Database Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Technology Research Database ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Water Resources Abstracts Environmental Sciences and Pollution Management
DatabaseTitleList	Aerospace Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE/IET Electronic Library url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Physics
EISSN	1558-0644
EndPage	1
ExternalDocumentID	10_1109_TGRS_2023_3295002 10183833
Genre	orig-research
GroupedDBID	-~X 0R~ 29I 4.4 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AFRAH AGQYO AHBIQ AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS ESBDL F5P HZ~ IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS RXW TAE TN5 Y6R 5VS AAYXX AETIX AGSQL AI. AIBXA CITATION EJD H~9 IBMZZ ICLAB IFJZH VH1 7UA 8FD C1K F1W FR3 H8D H96 KR7 L.G L7M
ID	FETCH-LOGICAL-c337t-ec6a3b8a03d87f4a9b19a3d14bf793508a9f8a2e8104c0ade02ac50ae1f70cc23
IEDL.DBID	RIE
ISICitedReferencesCount	9
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001047542000002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0196-2892
IngestDate	Mon Jun 30 08:33:26 EDT 2025 Sat Nov 29 03:32:24 EST 2025 Tue Nov 18 21:43:02 EST 2025 Wed Aug 27 02:21:26 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c337t-ec6a3b8a03d87f4a9b19a3d14bf793508a9f8a2e8104c0ade02ac50ae1f70cc23
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-6443-1297 0000-0002-8847-634X 0000-0001-7822-4758 0000-0003-2229-2000
OpenAccessLink	https://ieeexplore.ieee.org/document/10183833
PQID	2849102858
PQPubID	85465
PageCount	1
ParticipantIDs	crossref_primary_10_1109_TGRS_2023_3295002 proquest_journals_2849102858 crossref_citationtrail_10_1109_TGRS_2023_3295002 ieee_primary_10183833
PublicationCentury	2000
PublicationDate	2023-01-01
PublicationDateYYYYMMDD	2023-01-01
PublicationDate_xml	– month: 01 year: 2023 text: 2023-01-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on geoscience and remote sensing
PublicationTitleAbbrev	TGRS
PublicationYear	2023
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref35 ref12 ref15 ref14 ref36 ref31 ref30 hajduch (ref16) 0 ref10 ref2 ref1 ref17 vaswani (ref34) 2017 ref19 ref18 o’malley (ref26) 2019 recchia (ref11) 2018 he (ref32) 2021 ref20 piantanida (ref22) 2022 ref21 friedt (ref37) 2021 dosovitskiy (ref33) 2021 ref28 ref27 li (ref25) 2018; 18 ref29 ref8 meadows (ref6) 2018 ref9 hajduch (ref7) 2017 ref4 ref3 ioffe (ref24) 2015 ref5 (ref23) 2020
References_xml	– ident: ref27 doi: 10.1109/ACSSC.2003.1292216 – ident: ref35 doi: 10.1109/ICCV.2019.00179 – ident: ref19 doi: 10.1109/IGARSS.2018.8519373 – start-page: 16000 year: 2021 ident: ref32 article-title: Masked autoencoders are scalable vision learners publication-title: Proc IEEE Conf Comput Vis and Pattern Recog – ident: ref21 doi: 10.1109/TGRS.2022.3190288 – volume: 18 start-page: 6765 year: 2018 ident: ref25 article-title: Hyperband: A novel bandit-based approach to hyperparameter optimization publication-title: J Mach Learn Res – ident: ref36 doi: 10.1109/COMITE.2013.6545070 – ident: ref15 doi: 10.1109/TGRS.2022.3213318 – year: 2017 ident: ref7 article-title: Sentinel-1 RadarSat-2 mutual interference – ident: ref5 doi: 10.1109/TGRS.2022.3170363 – ident: ref2 doi: 10.1109/MGRS.2018.2832057 – ident: ref17 doi: 10.1109/TGRS.2013.2252469 – ident: ref9 doi: 10.3390/rs9111183 – ident: ref10 doi: 10.3390/rs13010007 – ident: ref3 doi: 10.3390/rs11202438 – start-page: 1 year: 2017 ident: ref34 article-title: Attention is all you need publication-title: Proc Adv Neural Inf Process Syst – year: 2021 ident: ref33 article-title: An image is worth 16×16 words: Transformers for image recognition at scale publication-title: arXiv 2010 11929 – year: 2019 ident: ref26 publication-title: KerasTuner – ident: ref4 doi: 10.1109/IGARSS.2017.8127666 – ident: ref1 doi: 10.3390/rs14092236 – ident: ref8 doi: 10.1109/IGARSS39084.2020.9323726 – ident: ref31 doi: 10.1109/ACCESS.2021.3056504 – year: 0 ident: ref16 article-title: SAR-MPC Sentinel-1: Using the RFI annotations – ident: ref29 doi: 10.1007/s11263-020-01419-7 – year: 2018 ident: ref6 article-title: Sentinel-1 long duration mutual interference – ident: ref20 doi: 10.1109/TGRS.2021.3049472 – year: 2022 ident: ref22 article-title: Sentinel-1 Level 1 detailed algorithm definition – ident: ref12 doi: 10.3390/rs11141654 – start-page: 448 year: 2015 ident: ref24 article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift publication-title: Proc Int Conf Mach Learn – year: 2020 ident: ref23 publication-title: Sentinel-1 Level-0 Data Decoding Package – ident: ref18 doi: 10.3390/s20102919 – ident: ref28 doi: 10.1109/TIP.2003.819861 – ident: ref30 doi: 10.4236/jcc.2019.73002 – ident: ref13 doi: 10.23919/URSIAP-RASC.2019.8738633 – start-page: 1 year: 2018 ident: ref11 article-title: On the effective usage of Sentinel-1 noise pulses for denoising and RFI identification publication-title: Proc 12th Eur Conf Synth Aperture Radar – year: 2021 ident: ref37 publication-title: Sentinel-1 Level-0 Data Decoding Package – ident: ref14 doi: 10.3390/s18114034
SSID	ssj0014517
Score	2.4688847
Snippet	Synthetic Aperture Radar (SAR) satellite images are used increasingly more for Earth observation. While SAR images are useable in most conditions, they... Synthetic aperture radar (SAR) satellite images are used increasingly more for Earth observation. While SAR images are useable in most conditions, they...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	1
SubjectTerms	Anomalies anomaly classification and localization Classification convolutional autoencoder Deep learning Image degradation Image reconstruction Radar Radar imaging Radio Radio frequency Radio frequency interference radio frequency interference (RFI) SAR (radar) Satellite imagery Ships Synthetic aperture radar synthetic aperture radar (SAR)
Title	Finding Ground-based Radars in SAR images: Localizing Radio Frequency Interference using Unsupervised Deep Learning
URI	https://ieeexplore.ieee.org/document/10183833 https://www.proquest.com/docview/2849102858
Volume	61
WOSCitedRecordID	wos001047542000002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE/IET Electronic Library customDbUrl: eissn: 1558-0644 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014517 issn: 0196-2892 databaseCode: RIE dateStart: 19800101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PaxQxFH7YYkEPWmvF1bbk4EnINpnMbCbeirrtoRTZttLbkEnelAGdXXZ2Bf3rzctkS0Es9DaHlzDMN3m_8r73AD7k1uW5kTXXE2F5rsuGG-GRB8tdoKxVJiLL9fu5vrgob27Mt0RWj1wYRIzFZzimx3iX7-duTamyY-ouFSIqtQVbWuuBrHV3ZZAXMnGjJzxEEVm6wpTCHF-dzi7HNCd8rDJTbFIoGyMUp6r8o4qjfZm-fOSb7cKL5EiykwH5V_AEuz14fq-94B7sxPJO17-GftpG9gqjVFPnOdkuz2bWh7CWtR27PJmx9mdQLf0ndk7Wrf1D0kGgnbPpcii3_s1i-jARBBlVzN-y665fL0jf0IZfEBcsdWy93Yfr6derz2c8jVvgTim94ugmVtWlFcqXusmtqaWxysu8bsIhDo6cNU1pMyxDBOeE9Sgy6wphUTZaOJepN7DdzTt8C0ygz6TNdDMJ4Zb2pbGFb4R2KFBKW7sRiM33r1zqRU4jMX5UMSYRpiLIKoKsSpCN4OPdksXQiOMh4X3C6J7gAM8IDjYoV-ms9lUw0IbcrKJ8959l7-EZ7T5kXg5ge7Vc4yE8db9Wbb88ir_hX5702kI
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3db9MwED_BAMEe-BhDdAzwA09I7uzYqWPeJkYZolSo69DeIse-TJEgrZoWCf56bMedJiEm8ZaHcxLlF9_5Pn53AG-ksVJqXlE1YoZKVdRUM4fUW-4ceSUyFlmu3yZqOi0uLvTXRFaPXBhEjMVnOAyXMZfvFnYTQmVHobuU96jEbbiTS5nxnq51lTSQOU_s6BH1fkSWkpic6aP5x9nZMEwKH4pM59sgytYMxbkqfynjaGHGj_7z3R7Dw3SUJMc99k_gFrZ7sHutweAe3IsFnrZ7Ct24ifwVEoJNraPBejkyM847tqRpydnxjDQ_vHLp3pFJsG_N7yDtBZoFGa_6gutfJAYQE0WQhJr5S3Ledptl0DjhhieIS5J6tl7uw_n4w_z9KU0DF6gVQq0p2pERVWGYcIWqpdEV10Y4Lqvab2N_lDO6LkyGhffhLDMOWWZszgzyWjFrM_EMdtpFi8-BMHQZN5mqR97hUq7QJnc1UxYZcm4qOwC2_f6lTd3Iw1CM72X0SpguA2RlgKxMkA3g7dWSZd-K4ybh_YDRNcEengEcblEu027tSm-idTho5cXBP5a9hvun8y-TcvJp-vkFPAhP6uMwh7CzXm3wJdy1P9dNt3oVf8k_H2PdiQ
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Finding+Ground-based+Radars+in+SAR+images%3A+Localizing+Radio+Frequency+Interference+using+Unsupervised+Deep+Learning&rft.jtitle=IEEE+transactions+on+geoscience+and+remote+sensing&rft.au=Sorensen%2C+Kristian+Aa&rft.au=Kusk%2C+Anders&rft.au=Heiselberg%2C+Peder&rft.au=Heiselberg%2C+Henning&rft.date=2023-01-01&rft.pub=IEEE&rft.issn=0196-2892&rft.spage=1&rft.epage=1&rft_id=info:doi/10.1109%2FTGRS.2023.3295002&rft.externalDocID=10183833
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0196-2892&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0196-2892&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0196-2892&client=summon