Moving Target Shadow Detection using Transformer in Video Sar

Video synthetic aperture radar (SAR) has been found to be very valuable for detecting and tracking moving targets and observing areas of interest. Shadows produced by target motion in sequential radar images can be used to detect targets themselves. Since existing deep learning shadow detection meth...

Full description

Saved in:
Bibliographic Details
Published in:IEEE International Geoscience and Remote Sensing Symposium proceedings pp. 2614 - 2617
Main Authors: Wang, Wei, Zhou, Yuanyuan, Xie, Zhikun, Zhang, Tianwen, Shi, Jun, Zhang, Xiaoling
Format: Conference Proceeding
Language:English
Published: IEEE 17.07.2022
Subjects:
Deep learning
Feature extraction
Laboratories
moving target
Radar detection
Radar imaging
shadow detection
Target tracking
transformer
Transformers
Video SAR
ISSN:2153-7003
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Video synthetic aperture radar (SAR) has been found to be very valuable for detecting and tracking moving targets and observing areas of interest. Shadows produced by target motion in sequential radar images can be used to detect targets themselves. Since existing deep learning shadow detection methods often require many hand-designed components, in this paper, we propose a shadow detection method for video SAR moving target based on transformer, which is named Deformable Shadow-DETR. Deformable Shadow-DETR can better extract shadow features, and use the transformer encoder-decoder network to treat shadow detection as a direct set prediction problem, eliminating the need for cumbersome hand-designed components. Experiments on the real video SAR data published by the Sandia National Laboratories show that our proposed moving target shadow detection method can achieve excellent performance.
AbstractList Video synthetic aperture radar (SAR) has been found to be very valuable for detecting and tracking moving targets and observing areas of interest. Shadows produced by target motion in sequential radar images can be used to detect targets themselves. Since existing deep learning shadow detection methods often require many hand-designed components, in this paper, we propose a shadow detection method for video SAR moving target based on transformer, which is named Deformable Shadow-DETR. Deformable Shadow-DETR can better extract shadow features, and use the transformer encoder-decoder network to treat shadow detection as a direct set prediction problem, eliminating the need for cumbersome hand-designed components. Experiments on the real video SAR data published by the Sandia National Laboratories show that our proposed moving target shadow detection method can achieve excellent performance.
Author Zhou, Yuanyuan
Shi, Jun
Wang, Wei
Zhang, Xiaoling
Zhang, Tianwen
Xie, Zhikun
Author_xml – sequence: 1
  givenname: Wei
  surname: Wang
  fullname: Wang, Wei
  organization: University of Electronic Science and Technology of China,Chengdu,P.R.China,611731
– sequence: 2
  givenname: Yuanyuan
  surname: Zhou
  fullname: Zhou, Yuanyuan
  organization: Sichuan Aerospace Electronic Equipment Research Institute
– sequence: 3
  givenname: Zhikun
  surname: Xie
  fullname: Xie, Zhikun
  organization: University of Electronic Science and Technology of China,Chengdu,P.R.China,611731
– sequence: 4
  givenname: Tianwen
  surname: Zhang
  fullname: Zhang, Tianwen
  organization: University of Electronic Science and Technology of China,Chengdu,P.R.China,611731
– sequence: 5
  givenname: Jun
  surname: Shi
  fullname: Shi, Jun
  organization: University of Electronic Science and Technology of China,Chengdu,P.R.China,611731
– sequence: 6
  givenname: Xiaoling
  surname: Zhang
  fullname: Zhang, Xiaoling
  organization: University of Electronic Science and Technology of China,Chengdu,P.R.China,611731
BookMark eNotj81KAzEYRaMo2NY-gZu8wIz5n2TholRbCxXBqW5LkvlSIzaRzKj49hbt4nIPXDhwx-gs5QQIYUpqSom5Xi1nT20rlOaiZoSx2mgtJCUnaGoaTZWSgjWGkVM0YlTyqiGEX6Bx378dQDNCRujmIX_FtMMbW3Yw4PbVdvkb38IAfog54c_-by029SGXPRQcE36JHWTc2nKJzoN972F67Al6Xtxt5vfV-nG5ms_WVWSED5X2TDljG3mIBW4d5cSJYBxVzgfgwnkdGuW5M8FSqY2wtAPGlJAeOtbxCbr690YA2H6UuLflZ3t8y38Bc1dMRQ
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/IGARSS46834.2022.9884510
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Geology
EISBN 9781665427920
1665427922
EISSN 2153-7003
EndPage 2617
ExternalDocumentID 9884510
Genre orig-research
GroupedDBID 6IE
6IF
6IH
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IPLJI
OCL
RIE
RIL
RIO
RNS
ID FETCH-LOGICAL-i203t-8c26b9a759a7ae3ab130b4f9b16bcfe34bc8f76c3b9fa15894a1de22645ced2d3
IEDL.DBID RIE
ISICitedReferencesCount 3
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000920916602203&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:15:02 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-8c26b9a759a7ae3ab130b4f9b16bcfe34bc8f76c3b9fa15894a1de22645ced2d3
PageCount 4
ParticipantIDs ieee_primary_9884510
PublicationCentury 2000
PublicationDate 2022-July-17
PublicationDateYYYYMMDD 2022-07-17
PublicationDate_xml – month: 07
  year: 2022
  text: 2022-July-17
  day: 17
PublicationDecade 2020
PublicationTitle IEEE International Geoscience and Remote Sensing Symposium proceedings
PublicationTitleAbbrev IGARSS
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0038200
Score 1.8225561
Snippet Video synthetic aperture radar (SAR) has been found to be very valuable for detecting and tracking moving targets and observing areas of interest. Shadows...
SourceID ieee
SourceType Publisher
StartPage 2614
SubjectTerms Deep learning
Feature extraction
Laboratories
moving target
Radar detection
Radar imaging
shadow detection
Target tracking
transformer
Transformers
Video SAR
Title Moving Target Shadow Detection using Transformer in Video Sar
URI https://ieeexplore.ieee.org/document/9884510
WOSCitedRecordID wos000920916602203&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
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA61KHjy0YpvcvDotvvIbpKDB1FbBS3FraW3kscs7mVX1q3ivzdJtxXBi4dASEhCZiAzmXxfBqELAToMgTCPQhybC4oWHlcW4y6EZLEgwnfp3qaPdDRisxkft9DlmgsDAA58Bj1bdW_5ulQLGyrrc8ZIbPlUG5QmS67W6tSNjCXzV0gdn_cfhtfPaUoSFtnASRj2mrG_kqg4GzLY-d_qu6j7Q8bD47WZ2UMtKPbR1tBl5P3qoKsnFxPAEwfpxumr0OUnvoXaYawKbIHtpnfln0KF8wJPcw0lTkXVRS-Du8nNvdfkRPDy0I9qj6kwkVzQ2BQBkZDGBkmScRkkUmUQEalYRhMVSZ6JIGaciECDZcvGyqhFRweoXZQFHCJMuA6M9-crDpyEIMzUMgOmAqDKugZHqGOFMH9bfnsxb_Z__HfzCdq2cvbcn5OnqF1XCzhDm-qjzt-rc6erb47ElaI
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA6lKnry0Ypvc_DotvtIdpODB_HRFttS3Fp6K3nM4l52Zd0q_ns36UMELx4CISEJmYHMZPJ9GYSuBGjfB8KcCCitLihaOFwZjLsQklFBhGvTvU360XDIplM-qqHrNRcGACz4DFqmat_yda7mJlTW5owRavhUG5QQ312wtVbnblDZMneF1XF5u9e5fY5jErLAhE58v7Uc_SuNirUij7v_W38PNX_oeHi0NjT7qAbZAdrq2Jy8Xw10M7BRATy2oG4cvwqdf-J7KC3KKsMG2l71rjxUKHCa4UmqIcexKJro5fFhfNd1llkRnNR3g9Jhyg8lFxGtioBAyMoKSZJw6YVSJRAQqVgShSqQPBEeZZwIT4Phy1JVKUYHh6ie5RkcIUy49ir_z1UcOPFBVFPLBJjyIFLGOThGDSOE2dvi44vZcv8nfzdfou3ueNCf9XvDp1O0Y2Tu2B8oz1C9LOZwjjbVR5m-FxdWb9-Ihpjp
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%3Abook&rft.genre=proceeding&rft.title=IEEE+International+Geoscience+and+Remote+Sensing+Symposium+proceedings&rft.atitle=Moving+Target+Shadow+Detection+using+Transformer+in+Video+Sar&rft.au=Wang%2C+Wei&rft.au=Zhou%2C+Yuanyuan&rft.au=Xie%2C+Zhikun&rft.au=Zhang%2C+Tianwen&rft.date=2022-07-17&rft.pub=IEEE&rft.eissn=2153-7003&rft.spage=2614&rft.epage=2617&rft_id=info:doi/10.1109%2FIGARSS46834.2022.9884510&rft.externalDocID=9884510