3-D SAR Imaging via Perceptual Learning Framework With Adaptive Sparse Prior

Mathematically, 3-D synthetic aperture radar (SAR) imaging is a typical inverse problem, which, by nature, can be solved by applying the theory of sparse signal recovery. However, many reconstruction algorithms are constructed by exploring the inherent sparsity of imaging space, which may cause unsa...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on geoscience and remote sensing Ročník 61; s. 1 - 16
Hlavní autoři:	Wang, Mou, Wei, Shunjun, Shi, Jun, Zhang, Xiaoling, Guo, Yongxin
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Témata:	Algorithms Artificial neural networks Computer applications Echoes Feature extraction Image reconstruction Imaging techniques Inverse problems Iterative methods Learning Mathematical analysis Neural networks Operators (mathematics) Radar imaging Regularization SAR (radar) Signal reconstruction Synthetic aperture radar Visual perception
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	Mathematically, 3-D synthetic aperture radar (SAR) imaging is a typical inverse problem, which, by nature, can be solved by applying the theory of sparse signal recovery. However, many reconstruction algorithms are constructed by exploring the inherent sparsity of imaging space, which may cause unsatisfactory estimations in weakly sparse cases. To address this issue, we propose a new perceptual learning framework, dubbed as PeFIST-Net, for 3-D SAR imaging, by unfolding the fast iterative shrinkage-thresholding algorithm (FISTA) and exploring the sparse prior offered by the convolutional neural network (CNN). We first introduce a pair of approximated sensing operators in lieu of the conventional sensing matrices, by which the computational efficiency is highly improved. Then, to improve the reconstruction accuracy in inherently nonsparse cases, a mirror-symmetric CNN structure is designed to explore an optimal sparse representation of roughly estimated SAR images. The network weights control the hyperparameters of FISTA by elaborated regularization functions, ensuring a well-behaved updating tendency. Unlike directly using pixelwise loss function in existing unfolded networks, we introduce the perceptual loss by defining loss term based on high-level features extracted from the pretrained VGG-16 model, which brings higher reconstruction quality in terms of visual perception. Finally, the methodology is validated on simulations and measured SAR experiments. The experimental results indicate that the proposed method can obtain well-focused SAR images from highly incomplete echoes while maintaining fast computational speed.
AbstractList	Mathematically, 3-D synthetic aperture radar (SAR) imaging is a typical inverse problem, which, by nature, can be solved by applying the theory of sparse signal recovery. However, many reconstruction algorithms are constructed by exploring the inherent sparsity of imaging space, which may cause unsatisfactory estimations in weakly sparse cases. To address this issue, we propose a new perceptual learning framework, dubbed as PeFIST-Net, for 3-D SAR imaging, by unfolding the fast iterative shrinkage-thresholding algorithm (FISTA) and exploring the sparse prior offered by the convolutional neural network (CNN). We first introduce a pair of approximated sensing operators in lieu of the conventional sensing matrices, by which the computational efficiency is highly improved. Then, to improve the reconstruction accuracy in inherently nonsparse cases, a mirror-symmetric CNN structure is designed to explore an optimal sparse representation of roughly estimated SAR images. The network weights control the hyperparameters of FISTA by elaborated regularization functions, ensuring a well-behaved updating tendency. Unlike directly using pixelwise loss function in existing unfolded networks, we introduce the perceptual loss by defining loss term based on high-level features extracted from the pretrained VGG-16 model, which brings higher reconstruction quality in terms of visual perception. Finally, the methodology is validated on simulations and measured SAR experiments. The experimental results indicate that the proposed method can obtain well-focused SAR images from highly incomplete echoes while maintaining fast computational speed.
Author	Shi, Jun Wang, Mou Wei, Shunjun Zhang, Xiaoling Guo, Yongxin
Author_xml	– sequence: 1 givenname: Mou orcidid: 0000-0003-3462-3989 surname: Wang fullname: Wang, Mou organization: School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China – sequence: 2 givenname: Shunjun orcidid: 0000-0001-8091-9540 surname: Wei fullname: Wei, Shunjun organization: School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China – sequence: 3 givenname: Jun orcidid: 0000-0001-7676-8380 surname: Shi fullname: Shi, Jun organization: School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China – sequence: 4 givenname: Xiaoling orcidid: 0000-0003-2343-3055 surname: Zhang fullname: Zhang, Xiaoling organization: School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China – sequence: 5 givenname: Yongxin orcidid: 0000-0001-8842-5609 surname: Guo fullname: Guo, Yongxin organization: Department of Electrical and Computer Engineering, National University of Singapore, Queenstown, Singapore
BookMark	eNp9kE1PAjEQhhuDiYD-AG9NPC_2u7tHgoIkm0gA47FpSheLsF3bgvHfuxs4efAwmcmbeWaSZwB6ta8tAPcYjTBGxeN6tlyNCCJ0RAmVQqAr0Mec5xkSjPVAH-FCZCQvyA0YxLhDCDOOZR-UNHuCq_ESzg966-otPDkNFzYY26Sj3sPS6lB3-TTog_324RO-u_QBxxvdJHeycNXoEC1cBOfDLbiu9D7au0sfgrfp83rykpWvs_lkXGaGYpEyzIhBRUU3rGiLGMmN5kZurGHYdDMzUrahYYZjThAWluZMVppwU-VS0iF4ON9tgv862pjUzh9D3b5URErRspSLdguft0zwMQZbqSa4gw4_CiPVSVOdNNVJUxdpLSP_MMYlnZyvU9Bu_w_5CzcIcUc
CitedBy_id	crossref_primary_10_1109_MGRS_2024_3494754 crossref_primary_10_1109_TAES_2025_3560943 crossref_primary_10_1109_TGRS_2024_3447900 crossref_primary_10_1109_TGRS_2025_3545675 crossref_primary_10_1109_TGRS_2024_3492070 crossref_primary_10_1109_TITS_2025_3541846 crossref_primary_10_1109_TVT_2024_3398218 crossref_primary_10_1109_JSEN_2025_3569231 crossref_primary_10_1109_JSTARS_2024_3472845
Cites_doi	10.1109/TGRS.2022.3205628 10.1109/MSP.2014.2311271 10.1109/TIM.2019.2918371 10.1109/CVPR.2018.00196 10.1109/TGRS.2010.2053038 10.1109/TMI.2020.2968472 10.1016/j.isprsjprs.2015.10.003 10.5555/3104322.3104374 10.1109/TGRS.2022.3150067 10.1109/TCI.2020.2993170 10.1109/JSTARS.2020.3000760 10.1109/TAES.2017.2675138 10.1109/JSEN.2020.3025053 10.1109/TMI.2018.2827462 10.1109/TGRS.2021.3093307 10.1109/MSP.2016.2573847 10.1109/JSTARS.2020.3014696 10.1109/TGRS.2010.2050487 10.1109/TAP.2018.2869660 10.1109/22.942570 10.1109/TGRS.2022.3164193 10.1109/SiPS47522.2019.9020494 10.1109/TSP.2007.914345 10.1109/TIP.2021.3104168 10.2528/PIER11033105 10.1109/TMM.2021.3087020 10.1109/MGRS.2013.2248301 10.1109/TGRS.2021.3073123 10.1109/jstsp.2022.3207902 10.1109/TGRS.2022.3165541 10.1109/JSTSP.2015.2469646 10.1109/MSP.2020.3016905 10.1137/080716542 10.1109/TIP.2019.2895768 10.1109/MAES.2013.6575407 10.1109/TNNLS.2022.3208252 10.1109/TGRS.2021.3068405 10.1109/TMI.2021.3054167 10.1109/36.868873 10.1109/TGRS.2021.3139914 10.1109/TGRS.2015.2448686 10.1109/TAP.2020.3027898 10.48550/arXiv.1603.08155 10.1073/pnas.0909892106 10.1109/tnnls.2022.3189997 10.1109/TSP.2017.2708040 10.1109/CVPR42600.2020.00328 10.1109/TGRS.2022.3169455 10.1109/TIT.2007.909108 10.1109/TAP.2020.3030974 10.1109/MSP.2012.2211477 10.1561/2200000016
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	AAYXX CITATION 7UA 8FD C1K F1W FR3 H8D H96 KR7 L.G L7M
DOI	10.1109/TGRS.2023.3237660
DatabaseName	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
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Physics
EISSN	1558-0644
EndPage	16
ExternalDocumentID	10_1109_TGRS_2023_3237660
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AASAJ AAWTH AAYXX ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AETIX AFRAH AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CITATION CS3 DU5 EBS EJD F5P HZ~ H~9 IBMZZ ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS RXW TAE TN5 VH1 Y6R 7UA 8FD AARMG ABAZT C1K F1W FR3 H8D H96 KR7 L.G L7M
ID	FETCH-LOGICAL-c316t-142c09f3d493d42c75ca5c7dec41c5ca54c7775cc4c5152016e3847fa25cf8773
ISICitedReferencesCount	12
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000935399000002&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 08:19:41 EDT 2025 Tue Nov 18 22:21:55 EST 2025 Sat Nov 29 02:50:29 EST 2025
IsDoiOpenAccess	false
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c316t-142c09f3d493d42c75ca5c7dec41c5ca54c7775cc4c5152016e3847fa25cf8773
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-8842-5609 0000-0003-3462-3989 0000-0001-8091-9540 0000-0003-2343-3055 0000-0001-7676-8380
OpenAccessLink	https://scholarbank.nus.edu.sg/handle/10635/238745
PQID	2776775356
PQPubID	85465
PageCount	16
ParticipantIDs	proquest_journals_2776775356 crossref_primary_10_1109_TGRS_2023_3237660 crossref_citationtrail_10_1109_TGRS_2023_3237660
PublicationCentury	2000
PublicationDate	2023-00-00 20230101
PublicationDateYYYYMMDD	2023-01-01
PublicationDate_xml	– year: 2023 text: 2023-00-00
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on geoscience and remote sensing
PublicationYear	2023
Publisher	The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref12 ref56 ref15 ref14 ref53 ref52 ref11 ref55 ref10 ref54 ref17 ref16 ref19 ref18 Curlander (ref1) 1991; 11 ref51 ref50 ref46 ref45 ref48 ref47 ref41 ref44 ref43 ref49 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 ref35 Hershey (ref28) 2014 ref34 ref37 ref36 ref31 ref30 ref33 ref32 ref2 ref39 ref38 Simonyan (ref42) 2014 Sun (ref26); 29 ref24 ref23 ref25 ref20 ref22 ref21 ref27 ref29
References_xml	– ident: ref54 doi: 10.1109/TGRS.2022.3205628 – ident: ref3 doi: 10.1109/MSP.2014.2311271 – ident: ref6 doi: 10.1109/TIM.2019.2918371 – volume: 29 start-page: 1 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref26 article-title: Deep ADMM-Net for compressive sensing MRI – ident: ref25 doi: 10.1109/CVPR.2018.00196 – ident: ref8 doi: 10.1109/TGRS.2010.2053038 – ident: ref44 doi: 10.1109/TMI.2020.2968472 – ident: ref10 doi: 10.1016/j.isprsjprs.2015.10.003 – ident: ref24 doi: 10.5555/3104322.3104374 – ident: ref37 doi: 10.1109/TGRS.2022.3150067 – ident: ref18 doi: 10.1109/TCI.2020.2993170 – ident: ref15 doi: 10.1109/JSTARS.2020.3000760 – ident: ref17 doi: 10.1109/TAES.2017.2675138 – ident: ref35 doi: 10.1109/JSEN.2020.3025053 – ident: ref43 doi: 10.1109/TMI.2018.2827462 – ident: ref39 doi: 10.1109/TGRS.2021.3093307 – ident: ref23 doi: 10.1109/MSP.2016.2573847 – ident: ref33 doi: 10.1109/JSTARS.2020.3014696 – year: 2014 ident: ref42 article-title: Very deep convolutional networks for large-scale image recognition publication-title: arXiv:1409.1556 – ident: ref12 doi: 10.1109/TGRS.2010.2050487 – ident: ref47 doi: 10.1109/TAP.2018.2869660 – ident: ref7 doi: 10.1109/22.942570 – ident: ref34 doi: 10.1109/TGRS.2022.3164193 – ident: ref30 doi: 10.1109/SiPS47522.2019.9020494 – ident: ref22 doi: 10.1109/TSP.2007.914345 – ident: ref49 doi: 10.1109/TIP.2021.3104168 – ident: ref14 doi: 10.2528/PIER11033105 – ident: ref45 doi: 10.1109/TMM.2021.3087020 – ident: ref2 doi: 10.1109/MGRS.2013.2248301 – ident: ref36 doi: 10.1109/TGRS.2021.3073123 – ident: ref55 doi: 10.1109/jstsp.2022.3207902 – ident: ref40 doi: 10.1109/TGRS.2022.3165541 – volume: 11 volume-title: Synthetic Aperture Radar year: 1991 ident: ref1 – ident: ref5 doi: 10.1109/JSTSP.2015.2469646 – ident: ref31 doi: 10.1109/MSP.2020.3016905 – ident: ref21 doi: 10.1137/080716542 – ident: ref46 doi: 10.1109/TIP.2019.2895768 – ident: ref4 doi: 10.1109/MAES.2013.6575407 – ident: ref53 doi: 10.1109/TNNLS.2022.3208252 – ident: ref38 doi: 10.1109/TGRS.2021.3068405 – ident: ref48 doi: 10.1109/TMI.2021.3054167 – ident: ref11 doi: 10.1109/36.868873 – ident: ref32 doi: 10.1109/TGRS.2021.3139914 – ident: ref13 doi: 10.1109/TGRS.2015.2448686 – ident: ref50 doi: 10.1109/TAP.2020.3027898 – ident: ref41 doi: 10.48550/arXiv.1603.08155 – ident: ref19 doi: 10.1073/pnas.0909892106 – ident: ref56 doi: 10.1109/tnnls.2022.3189997 – ident: ref27 doi: 10.1109/TSP.2017.2708040 – ident: ref29 doi: 10.1109/CVPR42600.2020.00328 – ident: ref9 doi: 10.1109/TGRS.2022.3169455 – year: 2014 ident: ref28 article-title: Deep unfolding: Model-based inspiration of novel deep architectures publication-title: arXiv:1409.2574 – ident: ref16 doi: 10.1109/TIT.2007.909108 – ident: ref51 doi: 10.1109/TAP.2020.3030974 – ident: ref52 doi: 10.1109/MSP.2012.2211477 – ident: ref20 doi: 10.1561/2200000016
SSID	ssj0014517
Score	2.4901435
Snippet	Mathematically, 3-D synthetic aperture radar (SAR) imaging is a typical inverse problem, which, by nature, can be solved by applying the theory of sparse...
SourceID	proquest crossref
SourceType	Aggregation Database Enrichment Source Index Database
StartPage	1
SubjectTerms	Algorithms Artificial neural networks Computer applications Echoes Feature extraction Image reconstruction Imaging techniques Inverse problems Iterative methods Learning Mathematical analysis Neural networks Operators (mathematics) Radar imaging Regularization SAR (radar) Signal reconstruction Synthetic aperture radar Visual perception
Title	3-D SAR Imaging via Perceptual Learning Framework With Adaptive Sparse Prior
URI	https://www.proquest.com/docview/2776775356
Volume	61
WOSCitedRecordID	wos000935399000002&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 Electronic Library (IEL) 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/eLvHCXMwtV1Lb9NAEF6FAlI5ICggWgraAycsFz_WXu-xAspDoarqIOVm2eN1G1ScKC_1T_CfmX05DhWIHjjEclbJOPF8np33EPJaIIpExSO_AnzcWFNKXwgI_AzqhjFeQlTplvlDfnqajcfibDD46Wph1le8bbPrazH7r6zGNWS2Kp29Bbs7oriA58h0PCLb8fhPjI_9915-fO59_mEGEK0npcpzV-krqlRk6HwhJy4tCyWDCt3U5UynEeUztHWldzafTOd91VWZhWqihBsvruMMF3LqCoN0orpEzktvobLi7ZaonfVGoHydrjaBIJ1FkF-u2u-rDp-5njDsfdmsdP7s8aRU44Uu-l4KU0LsXJYi9dGsMzJXWjGbZD4qQ6wvh01TditIw96ObIoxb8p63Sp19PE8P1JXPIpVgo8ZTrDdV_u3_a7LQtT2TyAKRaJQJApL4g65G3G0tEw5YBeUYkloq-_NH7JBciTx9sav2FZztnd5rbqMHpGH1uagxwYrj8lAtnvkQa8T5R65rzOBYfGEDBE_FPFDLX4o4odu8EMdfmiHH6rwQx1-qMEP1fh5Sr6dfBi9--TbkRs-xGG69EMWQSCauGYCXxHwBMoEeC2BhaDOGXCOi8AAFWFUHlMZo37TlFECTcZ5_IzstNNWPic0rWQIohaiDhrWBHGVBiKrJOdBJMtKRPskcHeoANuPXo1FuSr-yJd98qb7ysw0Y_nbhw_dbS_s47koItW8Ci30JD24Da0XZFe9Na63Q7KznK_kS3IP1svJYv5Ko-QXdwuHag
linkProvider	IEEE
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=3-D+SAR+Imaging+via+Perceptual+Learning+Framework+With+Adaptive+Sparse+Prior&rft.jtitle=IEEE+transactions+on+geoscience+and+remote+sensing&rft.au=Wang%2C+Mou&rft.au=Wei%2C+Shunjun&rft.au=Shi%2C+Jun&rft.au=Zhang%2C+Xiaoling&rft.date=2023&rft.issn=0196-2892&rft.eissn=1558-0644&rft.volume=61&rft.spage=1&rft.epage=16&rft_id=info:doi/10.1109%2FTGRS.2023.3237660&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TGRS_2023_3237660
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