Change detection in SAR images using deep belief network: a new training approach based on morphological images

In solving change detection problem, unsupervised methods are usually preferred to their supervised counterparts due to the difficulty of producing labelled data. Nevertheless, in this paper, a supervised deep learning-based method is presented for change detection in synthetic aperture radar (SAR)...

Full description

Saved in:
Bibliographic Details
Published in:IET image processing Vol. 13; no. 12; pp. 2255 - 2264
Main Authors: Samadi, Farnaam, Akbarizadeh, Gholamreza, Kaabi, Hooman
Format: Journal Article
Language:English
Published: The Institution of Engineering and Technology 17.10.2019
Subjects:
ISSN:1751-9659, 1751-9667
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract In solving change detection problem, unsupervised methods are usually preferred to their supervised counterparts due to the difficulty of producing labelled data. Nevertheless, in this paper, a supervised deep learning-based method is presented for change detection in synthetic aperture radar (SAR) images. A Deep Belief Network (DBN) was employed as the deep architecture in the proposed method, and the training process of this network included unsupervised feature learning followed by supervised network fine-tuning. From a general perspective, the trained DBN produces a change detection map as the output. Studies on DBNs demonstrate that they do not produce ideal output without a proper dataset for training. Therefore, the proposed method in this study provided a dataset with an appropriate data volume and diversity for training the DBN using the input images and those obtained from applying the morphological operators on them. The great computational volume and the time-consuming nature of simulation are the drawbacks of deep learning-based algorithms. To overcome such disadvantages, a method was introduced to greatly reduce computations without compromising the performance of the trained DBN. Experimental results indicated that the proposed method had an acceptable implementation time in addition to its desirable performance and high accuracy.
AbstractList In solving change detection problem, unsupervised methods are usually preferred to their supervised counterparts due to the difficulty of producing labelled data. Nevertheless, in this paper, a supervised deep learning-based method is presented for change detection in synthetic aperture radar (SAR) images. A Deep Belief Network (DBN) was employed as the deep architecture in the proposed method, and the training process of this network included unsupervised feature learning followed by supervised network fine-tuning. From a general perspective, the trained DBN produces a change detection map as the output. Studies on DBNs demonstrate that they do not produce ideal output without a proper dataset for training. Therefore, the proposed method in this study provided a dataset with an appropriate data volume and diversity for training the DBN using the input images and those obtained from applying the morphological operators on them. The great computational volume and the time-consuming nature of simulation are the drawbacks of deep learning-based algorithms. To overcome such disadvantages, a method was introduced to greatly reduce computations without compromising the performance of the trained DBN. Experimental results indicated that the proposed method had an acceptable implementation time in addition to its desirable performance and high accuracy.
Author Kaabi, Hooman
Akbarizadeh, Gholamreza
Samadi, Farnaam
Author_xml – sequence: 1
  givenname: Farnaam
  surname: Samadi
  fullname: Samadi, Farnaam
  organization: Department of Electrical Engineering, Faculty of Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran
– sequence: 2
  givenname: Gholamreza
  surname: Akbarizadeh
  fullname: Akbarizadeh, Gholamreza
  email: g.akbari@scu.ac.ir
  organization: Department of Electrical Engineering, Faculty of Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran
– sequence: 3
  givenname: Hooman
  surname: Kaabi
  fullname: Kaabi, Hooman
  organization: Department of Electrical Engineering, Faculty of Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran
BookMark eNqFkMtOwzAQRS0EErTwAez8Aym2Eztxd1DxqIQE4rGOJs40NaR25ARV_XscFbFgUVYz0sy5Y58JOXbeISGXnM04y_SVxSGxXZgJxouZEllxRM54LnmilcqPf3upT8mk7z8Yk5oV8oz4xRpcg7TGAc1gvaPW0dfrF2o30GBPv3rrmjjFjlbYWlxRh8PWh885hdhu6RDAunEHui54MGtaQY81jUkbH7q1b31jDbQ_gefkZAVtjxc_dUre727fFg_J49P9cnH9mJg0zVSiABXwIpUA2gipKy1NwSUqFKwQuZKizvNK1AwAMsErxSpj0ho4QM2yWqdTwve5Jvi-D7gquxBfEHYlZ-VorIzGymisHI2Vo7HI5H8YYwcYpYyfbA-S8z25tS3u_j9VLp9fxM0d4zpXEU728Lj24b-Ci2IOHPsGKV6Xug
CitedBy_id crossref_primary_10_1049_ipr2_12057
crossref_primary_10_1007_s11227_020_03604_4
crossref_primary_10_1049_iet_ipr_2018_6040
crossref_primary_10_1007_s13369_020_04481_y
crossref_primary_10_1109_TGRS_2020_3003264
crossref_primary_10_1080_01431161_2023_2244641
crossref_primary_10_1007_s13369_019_04151_8
crossref_primary_10_1016_j_ecoinf_2021_101310
crossref_primary_10_1109_JSTARS_2023_3301158
crossref_primary_10_1109_LGRS_2021_3050891
crossref_primary_10_1080_01431161_2024_2365818
crossref_primary_10_1016_j_isprsjprs_2020_03_011
crossref_primary_10_1049_iet_ipr_2019_0873
crossref_primary_10_1109_TGRS_2021_3053257
crossref_primary_10_1109_TIP_2022_3154922
crossref_primary_10_1109_JSTARS_2022_3215773
crossref_primary_10_1080_01431161_2025_2505257
crossref_primary_10_1155_2020_8886932
crossref_primary_10_3390_app12147282
crossref_primary_10_3390_rs15194802
crossref_primary_10_1049_iet_com_2019_0980
crossref_primary_10_1109_JSTARS_2020_2992230
crossref_primary_10_1016_j_dsp_2023_104331
crossref_primary_10_1177_1687814020930469
crossref_primary_10_3390_rs14030438
crossref_primary_10_1109_TIM_2025_3551842
crossref_primary_10_3389_fnbot_2021_751037
crossref_primary_10_1007_s00521_022_07928_5
crossref_primary_10_1049_iet_ipr_2019_1398
crossref_primary_10_3233_JIFS_220689
crossref_primary_10_1007_s13369_019_04235_5
crossref_primary_10_1109_TGRS_2023_3263563
crossref_primary_10_1109_JSTARS_2024_3464735
crossref_primary_10_3390_s21248290
crossref_primary_10_1049_ipr2_12078
crossref_primary_10_1080_01431161_2023_2182652
crossref_primary_10_1016_j_dsp_2021_103250
crossref_primary_10_1049_joe_2020_0086
crossref_primary_10_1109_JSTARS_2023_3280741
crossref_primary_10_1109_JSTARS_2020_3024002
crossref_primary_10_1109_TGRS_2020_3034102
crossref_primary_10_1109_JSTARS_2020_3041783
crossref_primary_10_1109_LGRS_2021_3050746
crossref_primary_10_1080_01431161_2025_2511209
crossref_primary_10_1109_LGRS_2021_3073900
crossref_primary_10_7717_peerj_cs_894
crossref_primary_10_2478_ijssis_2025_0026
crossref_primary_10_1109_TAES_2020_2981267
crossref_primary_10_1155_2022_3404858
crossref_primary_10_1080_01431161_2025_2529005
crossref_primary_10_1109_TGRS_2022_3168331
crossref_primary_10_1155_2021_5522894
crossref_primary_10_1109_JSTARS_2025_3557434
crossref_primary_10_1109_LGRS_2020_3022804
crossref_primary_10_1109_LSP_2024_3396657
crossref_primary_10_1109_TAES_2024_3421908
crossref_primary_10_1007_s11760_025_04147_y
crossref_primary_10_1080_01431161_2025_2518507
crossref_primary_10_1049_iet_ipr_2020_1078
crossref_primary_10_1049_iet_rsn_2020_0160
crossref_primary_10_1080_01431161_2025_2516691
crossref_primary_10_1016_j_isprsjprs_2020_10_007
crossref_primary_10_1080_14498596_2024_2384636
crossref_primary_10_1108_DTA_08_2019_0149
crossref_primary_10_3390_ijgi13040125
crossref_primary_10_1007_s00138_020_01110_4
crossref_primary_10_1109_TGRS_2020_3039738
crossref_primary_10_1109_JSTARS_2024_3471925
crossref_primary_10_1109_JSTARS_2025_3555627
crossref_primary_10_1080_2150704X_2022_2079389
crossref_primary_10_1080_01431161_2025_2557588
crossref_primary_10_1049_joe_2019_0996
crossref_primary_10_1049_iet_ipr_2018_6526
crossref_primary_10_1016_j_dsp_2021_103036
crossref_primary_10_1007_s00357_023_09448_w
crossref_primary_10_1016_j_measurement_2020_108657
crossref_primary_10_1109_JSTARS_2024_3408339
crossref_primary_10_1007_s13369_020_04788_w
crossref_primary_10_1016_j_measurement_2020_108417
crossref_primary_10_1049_ipr2_12523
crossref_primary_10_1155_2020_4609423
crossref_primary_10_3390_rs12132098
crossref_primary_10_4018_IJSI_293269
crossref_primary_10_1109_TETCI_2020_3041019
crossref_primary_10_3390_rs14092046
crossref_primary_10_3390_rs16203852
crossref_primary_10_1109_LGRS_2020_3040972
crossref_primary_10_1109_TPWRD_2020_3046161
crossref_primary_10_1007_s13369_019_04322_7
crossref_primary_10_3390_rs13204171
crossref_primary_10_1038_s41598_025_10972_5
crossref_primary_10_1109_TETCI_2020_3010017
crossref_primary_10_1016_j_cmpb_2019_105301
crossref_primary_10_1109_JSTARS_2023_3321769
crossref_primary_10_1109_TPWRD_2024_3421913
crossref_primary_10_3390_math10224387
crossref_primary_10_3390_rs14040957
crossref_primary_10_1016_j_jksuci_2020_10_008
crossref_primary_10_1109_JSTARS_2025_3542436
crossref_primary_10_1016_j_measurement_2020_107736
crossref_primary_10_1080_07900627_2024_2438203
crossref_primary_10_1109_JSTARS_2024_3424831
crossref_primary_10_1109_TGRS_2023_3245674
crossref_primary_10_3390_rs15153868
crossref_primary_10_1007_s10044_024_01370_0
crossref_primary_10_1109_JSTARS_2021_3088691
crossref_primary_10_1109_TIP_2025_3562054
crossref_primary_10_1049_ell2_12290
crossref_primary_10_1049_ipr2_12154
crossref_primary_10_1109_JSTARS_2024_3374054
crossref_primary_10_1007_s13369_019_04152_7
crossref_primary_10_3390_rs14040871
crossref_primary_10_1049_iet_ipr_2019_0652
crossref_primary_10_1080_22797254_2024_2372854
crossref_primary_10_1080_2150704X_2021_1897180
crossref_primary_10_3390_app142310770
crossref_primary_10_1109_TGRS_2022_3194903
crossref_primary_10_1109_ACCESS_2020_3006097
crossref_primary_10_1109_JSEN_2023_3314608
crossref_primary_10_1109_TGRS_2023_3344062
crossref_primary_10_1016_j_measurement_2019_107089
crossref_primary_10_1109_JSTARS_2025_3543591
crossref_primary_10_1049_iet_ipr_2019_0086
crossref_primary_10_1080_01431161_2023_2249595
crossref_primary_10_3390_rs12101688
crossref_primary_10_1080_01431161_2025_2467303
crossref_primary_10_1109_ACCESS_2024_3415054
crossref_primary_10_1109_JSTARS_2024_3393238
crossref_primary_10_1007_s00138_021_01171_z
crossref_primary_10_1109_JSTARS_2024_3402243
Cites_doi 10.1109/TIP.2011.2170702
10.1109/TNNLS.2015.2435783
10.1080/01431161.2017.1371861
10.1117/1.1631315
10.1109/JSTARS.2013.2265697
10.1007/978-0-387-45528-0
10.1561/2200000006
10.1080/01431161.2014.916054
10.1016/j.sigpro.2009.10.018
10.1016/S0167-8655(03)00060-6
10.1109/TGRS.2012.2223219
10.1109/LGRS.2012.2189867
10.1109/ICIP.2013.6738559
10.1109/36.843009
10.1109/TNNLS.2013.2296046
10.1162/neco.2006.18.7.1527
10.1109/LGRS.2011.2167211
10.1109/JSTARS.2016.2541678
10.1007/s00500-014-1460-0
10.1109/TGRS.2004.842441
10.1109/36.905239
10.1126/science.1127647
10.1109/TGRS.2004.842478
ContentType Journal Article
Copyright The Institution of Engineering and Technology
2021 The Authors. IET Image Processing published by John Wiley & Sons, Ltd. on behalf of The Institution of Engineering and Technology
Copyright_xml – notice: The Institution of Engineering and Technology
– notice: 2021 The Authors. IET Image Processing published by John Wiley & Sons, Ltd. on behalf of The Institution of Engineering and Technology
DBID AAYXX
CITATION
DOI 10.1049/iet-ipr.2018.6248
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList

CrossRef
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISSN 1751-9667
EndPage 2264
ExternalDocumentID 10_1049_iet_ipr_2018_6248
IPR2BF01976
Genre article
GrantInformation_xml – fundername: Shahid Chamran University of Ahvaz
  grantid: 96/3/02/16670
– fundername: Shahid Chamran University of Ahvaz
  funderid: 97/3/02/26247
GroupedDBID 0R
24P
29I
5GY
6IK
8VB
AAJGR
ABPTK
ACGFS
ACIWK
AENEX
ALMA_UNASSIGNED_HOLDINGS
BFFAM
CS3
DU5
ESX
HZ
IFIPE
IPLJI
JAVBF
LAI
M43
MS
O9-
OCL
P2P
QWB
RIE
RNS
RUI
UNR
ZL0
.DC
0R~
1OC
4.4
8FE
8FG
AAHHS
AAHJG
ABJCF
ABQXS
ACCFJ
ACCMX
ACESK
ACXQS
ADZOD
AEEZP
AEQDE
AFKRA
AIWBW
AJBDE
ALUQN
ARAPS
AVUZU
BENPR
BGLVJ
CCPQU
EBS
EJD
GROUPED_DOAJ
HCIFZ
HZ~
IAO
ITC
K1G
L6V
M7S
MCNEO
MS~
OK1
P62
PTHSS
ROL
S0W
AAMMB
AAYXX
AEFGJ
AFFHD
AGXDD
AIDQK
AIDYY
CITATION
IDLOA
PHGZM
PHGZT
PQGLB
WIN
ID FETCH-LOGICAL-c3346-6ae6a1835aa9c259b95c815e6e20827652d77b2d0aaa421b60bcc3da1aad04d93
IEDL.DBID 24P
ISICitedReferencesCount 143
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000497707700024&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1751-9659
IngestDate Tue Nov 18 20:42:54 EST 2025
Wed Oct 29 21:12:29 EDT 2025
Wed Jan 22 16:30:25 EST 2025
Tue Jan 05 21:44:15 EST 2021
IsPeerReviewed true
IsScholarly true
Issue 12
Keywords supervised counterparts
image classification
morphological images
unsupervised methods
detection performance
deep learning-based supervised method
introduced method
diversity
supervised network fine-tuning
deep belief network
training approach
radar imaging
synthetic aperture radar image changes
belief networks
learning (artificial intelligence)
change detection problems
trained DBN
input SAR images
training process
deep architecture
unsupervised learning
change detection map
synthetic aperture radar
labelled data
appropriate data volume
deep learning-based algorithms
input images
dataset
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c3346-6ae6a1835aa9c259b95c815e6e20827652d77b2d0aaa421b60bcc3da1aad04d93
PageCount 10
ParticipantIDs wiley_primary_10_1049_iet_ipr_2018_6248_IPR2BF01976
iet_journals_10_1049_iet_ipr_2018_6248
crossref_primary_10_1049_iet_ipr_2018_6248
crossref_citationtrail_10_1049_iet_ipr_2018_6248
ProviderPackageCode RUI
PublicationCentury 2000
PublicationDate 2019-10-17
PublicationDateYYYYMMDD 2019-10-17
PublicationDate_xml – month: 10
  year: 2019
  text: 2019-10-17
  day: 17
PublicationDecade 2010
PublicationTitle IET image processing
PublicationYear 2019
Publisher The Institution of Engineering and Technology
Publisher_xml – name: The Institution of Engineering and Technology
References Gong, M.; Zhao, J.; Liu, J. (C14) 2016; 27
Gong, M.; Jia, M.; Su, L. (C26) 2014; 35
Bazi, Y.; Bruzzone, L.; Melgani, F. (C2) 2005; 43
Zhang, X.; Chen, J.; Meng, H. (C15) 2013; 10
Tan, K.; Jin, X.; Plaza, A. (C7) 2016; 9
Sezgin, M.; Sankur, B. (C3) 2004; 13
Szymanski, L.; McCane, B. (C10) 2014; 25
Bengio, Y. (C11) 2009; 2
Gong, M.; Zhou, Z.; Ma, J. (C25) 2012; 21
Tan, K.; Li, E.; Du, Q. (C19) 2014; 7
Bruzzone, L.; Prieto, D.F. (C1) 2000; 38
Celik, T. (C5) 2010; 90
Liu, J.; Gong, M.; Zhao, J. (C12) 2016; 20
Rosin, P.L.; Ioannidis, E. (C24) 2003; 24
Cao, G.; Wang, B.; Xavier, H.C. (C13) 2017; 38
Hinton, G.E.; Salakhutdinov, R.R. (C22) 2006; 313
Gong, M.; Cao, Y.; Wu, Q. (C6) 2012; 9
Pesaresi, M.; Benediktsson, J.A. (C18) 2001; 39
Hinton, G.E.; Osindero, S.; Teh, Y.W. (C23) 2006; 18
Bovolo, F.; Marin, C.; Bruzzone, L. (C4) 2013; 51
Vincent, P.; Larochelle, H.; Lajoie, I. (C9) 2010; 11
Benediktsson, J.A.; Palmason, J.A.; Sveinsson, J.R. (C17) 2005; 43
2010; 11
2008
2014; 25
2006; 18
2005; 43
2006
2005
2006; 313
2000; 38
2013; 10
2017; 38
2013; 51
2004; 13
2003; 24
2016; 20
2014; 35
2001; 39
2013
2009; 2
2010; 90
2016; 27
2014; 7
2012; 21
2016; 9
2012; 9
e_1_2_8_24_1
e_1_2_8_25_1
e_1_2_8_26_1
e_1_2_8_27_1
Vincent P. (e_1_2_8_10_1) 2010; 11
e_1_2_8_3_1
e_1_2_8_2_1
e_1_2_8_5_1
e_1_2_8_4_1
e_1_2_8_7_1
e_1_2_8_6_1
e_1_2_8_9_1
e_1_2_8_8_1
e_1_2_8_20_1
e_1_2_8_21_1
e_1_2_8_22_1
e_1_2_8_23_1
e_1_2_8_18_1
e_1_2_8_19_1
e_1_2_8_13_1
e_1_2_8_14_1
e_1_2_8_15_1
Gonzalez R.C. (e_1_2_8_17_1) 2008
e_1_2_8_16_1
e_1_2_8_11_1
e_1_2_8_12_1
References_xml – volume: 2
  start-page: 1
  issue: 1
  year: 2009
  end-page: 127
  ident: C11
  article-title: Learning deep architectures for AI
  publication-title: Found. Trends® Mach. Learn.
– volume: 20
  start-page: 4645
  issue: 12
  year: 2016
  end-page: 4657
  ident: C12
  article-title: Difference representation learning using stacked restricted Boltzmann machines for change detection in SAR images
  publication-title: Soft Comput.
– volume: 9
  start-page: 307
  issue: 2
  year: 2012
  end-page: 311
  ident: C6
  article-title: A neighborhood-based ratio approach for change detection in SAR images
  publication-title: IEEE Geosci. Remote Sens. Lett.
– volume: 13
  start-page: 146
  issue: 1
  year: 2004
  end-page: 166
  ident: C3
  article-title: Survey over image thresholding techniques and quantitative performance evaluation
  publication-title: J. Electron. Imaging
– volume: 11
  start-page: 3371
  issue: Dec
  year: 2010
  end-page: 3408
  ident: C9
  article-title: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion
  publication-title: J. Mach. Learn. Res.
– volume: 21
  start-page: 2141
  issue: 4
  year: 2012
  end-page: 2151
  ident: C25
  article-title: Change detection in synthetic aperture radar images based on image fusion and fuzzy clustering
  publication-title: IEEE Trans. Image Process.
– volume: 43
  start-page: 480
  issue: 3
  year: 2005
  end-page: 491
  ident: C17
  article-title: Classification of hyperspectral data from urban areas based on extended morphological profiles
  publication-title: IEEE Trans. Geosci. Remote Sens.
– volume: 51
  start-page: 2042
  issue: 4
  year: 2013
  end-page: 2054
  ident: C4
  article-title: A hierarchical approach to change detection in very high resolution SAR images for surveillance applications
  publication-title: IEEE Trans. Geosci. Remote Sens.
– volume: 18
  start-page: 1527
  issue: 7
  year: 2006
  end-page: 1554
  ident: C23
  article-title: A fast learning algorithm for deep belief nets
  publication-title: Neural Comput.
– volume: 38
  start-page: 1171
  issue: 3
  year: 2000
  end-page: 1182
  ident: C1
  article-title: Automatic analysis of the difference image for unsupervised change detection
  publication-title: IEEE Trans. Geosci. Remote Sens.
– volume: 25
  start-page: 1816
  issue: 10
  year: 2014
  end-page: 1827
  ident: C10
  article-title: Deep networks are effective encoders of periodicity
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– volume: 10
  start-page: 14
  issue: 1
  year: 2013
  end-page: 18
  ident: C15
  article-title: A novel SAR image change detection based on graph-cut and generalized Gaussian model
  publication-title: IEEE Geosci. Remote Sens. Lett.
– volume: 24
  start-page: 2345
  issue: 14
  year: 2003
  end-page: 2356
  ident: C24
  article-title: Evaluation of global image thresholding for change detection
  publication-title: Pattern Recognit. Lett.
– volume: 27
  start-page: 125
  issue: 1
  year: 2016
  end-page: 138
  ident: C14
  article-title: Change detection in synthetic aperture radar images based on deep neural networks
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– volume: 313
  start-page: 504
  issue: 5786
  year: 2006
  end-page: 507
  ident: C22
  article-title: Reducing the dimensionality of data with neural networks
  publication-title: Science
– volume: 90
  start-page: 1471
  issue: 5
  year: 2010
  end-page: 1485
  ident: C5
  article-title: A Bayesian approach to unsupervised multiscale change detection in synthetic aperture radar images
  publication-title: Signal Process.
– volume: 38
  start-page: 7161
  issue: 23
  year: 2017
  end-page: 7175
  ident: C13
  article-title: A new difference image creation method based on deep neural networks for change detection in remote-sensing images
  publication-title: Int. J. Remote Sens.
– volume: 43
  start-page: 874
  issue: 4
  year: 2005
  end-page: 887
  ident: C2
  article-title: An unsupervised approach based on the generalized Gaussian model to automatic change detection in multitemporal SAR images
  publication-title: IEEE Trans. Geosci. Remote Sens.
– volume: 39
  start-page: 309
  issue: 2
  year: 2001
  end-page: 320
  ident: C18
  article-title: A new approach for the morphological segmentation of high-resolution satellite imagery
  publication-title: IEEE Trans. Geosci. Remote Sens.
– volume: 35
  start-page: 4009
  issue: 11–12
  year: 2014
  end-page: 4030
  ident: C26
  article-title: Detecting changes of the Yellow River estuary via SAR images based on a local fit-search model and kernel-induced graph cuts
  publication-title: Int. J. Remote Sens.
– volume: 7
  start-page: 40
  issue: 1
  year: 2014
  end-page: 48
  ident: C19
  article-title: Hyperspectral image classification using band selection and morphological profiles
  publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.
– volume: 9
  start-page: 3439
  issue: 8
  year: 2016
  end-page: 3451
  ident: C7
  article-title: Automatic change detection in high-resolution remote sensing images by using a multiple classifier system and spectral–spatial features
  publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.
– volume: 38
  start-page: 1171
  issue: 3
  year: 2000
  end-page: 1182
  article-title: Automatic analysis of the difference image for unsupervised change detection
  publication-title: IEEE Trans. Geosci. Remote Sens.
– volume: 10
  start-page: 14
  issue: 1
  year: 2013
  end-page: 18
  article-title: A novel SAR image change detection based on graph‐cut and generalized Gaussian model
  publication-title: IEEE Geosci. Remote Sens. Lett.
– volume: 7
  start-page: 40
  issue: 1
  year: 2014
  end-page: 48
  article-title: Hyperspectral image classification using band selection and morphological profiles
  publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.
– start-page: 627
  year: 2008
  end-page: 628
– volume: 39
  start-page: 309
  issue: 2
  year: 2001
  end-page: 320
  article-title: A new approach for the morphological segmentation of high‐resolution satellite imagery
  publication-title: IEEE Trans. Geosci. Remote Sens.
– volume: 11
  start-page: 3371
  issue: Dec
  year: 2010
  end-page: 3408
  article-title: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion
  publication-title: J. Mach. Learn. Res.
– volume: 313
  start-page: 504
  issue: 5786
  year: 2006
  end-page: 507
  article-title: Reducing the dimensionality of data with neural networks
  publication-title: Science
– volume: 24
  start-page: 2345
  issue: 14
  year: 2003
  end-page: 2356
  article-title: Evaluation of global image thresholding for change detection
  publication-title: Pattern Recognit. Lett.
– start-page: 2713
  year: 2013
  end-page: 2717
– volume: 38
  start-page: 7161
  issue: 23
  year: 2017
  end-page: 7175
  article-title: A new difference image creation method based on deep neural networks for change detection in remote‐sensing images
  publication-title: Int. J. Remote Sens.
– volume: 35
  start-page: 4009
  issue: 11–12
  year: 2014
  end-page: 4030
  article-title: Detecting changes of the Yellow River estuary via SAR images based on a local fit‐search model and kernel‐induced graph cuts
  publication-title: Int. J. Remote Sens.
– volume: 90
  start-page: 1471
  issue: 5
  year: 2010
  end-page: 1485
  article-title: A Bayesian approach to unsupervised multiscale change detection in synthetic aperture radar images
  publication-title: Signal Process.
– volume: 20
  start-page: 4645
  issue: 12
  year: 2016
  end-page: 4657
  article-title: Difference representation learning using stacked restricted Boltzmann machines for change detection in SAR images
  publication-title: Soft Comput.
– volume: 18
  start-page: 1527
  issue: 7
  year: 2006
  end-page: 1554
  article-title: A fast learning algorithm for deep belief nets
  publication-title: Neural Comput.
– volume: 25
  start-page: 1816
  issue: 10
  year: 2014
  end-page: 1827
  article-title: Deep networks are effective encoders of periodicity
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– volume: 43
  start-page: 874
  issue: 4
  year: 2005
  end-page: 887
  article-title: An unsupervised approach based on the generalized Gaussian model to automatic change detection in multitemporal SAR images
  publication-title: IEEE Trans. Geosci. Remote Sens.
– volume: 2
  start-page: 1
  issue: 1
  year: 2009
  end-page: 127
  article-title: Learning deep architectures for AI
  publication-title: Found. Trends® Mach. Learn.
– volume: 43
  start-page: 480
  issue: 3
  year: 2005
  end-page: 491
  article-title: Classification of hyperspectral data from urban areas based on extended morphological profiles
  publication-title: IEEE Trans. Geosci. Remote Sens.
– volume: 51
  start-page: 2042
  issue: 4
  year: 2013
  end-page: 2054
  article-title: A hierarchical approach to change detection in very high resolution SAR images for surveillance applications
  publication-title: IEEE Trans. Geosci. Remote Sens.
– volume: 9
  start-page: 3439
  issue: 8
  year: 2016
  end-page: 3451
  article-title: Automatic change detection in high‐resolution remote sensing images by using a multiple classifier system and spectral–spatial features
  publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens.
– volume: 13
  start-page: 146
  issue: 1
  year: 2004
  end-page: 166
  article-title: Survey over image thresholding techniques and quantitative performance evaluation
  publication-title: J. Electron. Imaging
– year: 2006
– start-page: 33
  year: 2005
  end-page: 40
– volume: 21
  start-page: 2141
  issue: 4
  year: 2012
  end-page: 2151
  article-title: Change detection in synthetic aperture radar images based on image fusion and fuzzy clustering
  publication-title: IEEE Trans. Image Process.
– volume: 27
  start-page: 125
  issue: 1
  year: 2016
  end-page: 138
  article-title: Change detection in synthetic aperture radar images based on deep neural networks
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– volume: 9
  start-page: 307
  issue: 2
  year: 2012
  end-page: 311
  article-title: A neighborhood‐based ratio approach for change detection in SAR images
  publication-title: IEEE Geosci. Remote Sens. Lett.
– ident: e_1_2_8_26_1
  doi: 10.1109/TIP.2011.2170702
– ident: e_1_2_8_15_1
  doi: 10.1109/TNNLS.2015.2435783
– ident: e_1_2_8_14_1
  doi: 10.1080/01431161.2017.1371861
– volume: 11
  start-page: 3371
  year: 2010
  ident: e_1_2_8_10_1
  article-title: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion
  publication-title: J. Mach. Learn. Res.
– ident: e_1_2_8_4_1
  doi: 10.1117/1.1631315
– ident: e_1_2_8_20_1
  doi: 10.1109/JSTARS.2013.2265697
– ident: e_1_2_8_22_1
– ident: e_1_2_8_21_1
  doi: 10.1007/978-0-387-45528-0
– start-page: 627
  volume-title: Digital image processing
  year: 2008
  ident: e_1_2_8_17_1
– ident: e_1_2_8_12_1
  doi: 10.1561/2200000006
– ident: e_1_2_8_27_1
  doi: 10.1080/01431161.2014.916054
– ident: e_1_2_8_6_1
  doi: 10.1016/j.sigpro.2009.10.018
– ident: e_1_2_8_25_1
  doi: 10.1016/S0167-8655(03)00060-6
– ident: e_1_2_8_5_1
  doi: 10.1109/TGRS.2012.2223219
– ident: e_1_2_8_16_1
  doi: 10.1109/LGRS.2012.2189867
– ident: e_1_2_8_9_1
  doi: 10.1109/ICIP.2013.6738559
– ident: e_1_2_8_2_1
  doi: 10.1109/36.843009
– ident: e_1_2_8_11_1
  doi: 10.1109/TNNLS.2013.2296046
– ident: e_1_2_8_24_1
  doi: 10.1162/neco.2006.18.7.1527
– ident: e_1_2_8_7_1
  doi: 10.1109/LGRS.2011.2167211
– ident: e_1_2_8_8_1
  doi: 10.1109/JSTARS.2016.2541678
– ident: e_1_2_8_13_1
  doi: 10.1007/s00500-014-1460-0
– ident: e_1_2_8_3_1
  doi: 10.1109/TGRS.2004.842441
– ident: e_1_2_8_19_1
  doi: 10.1109/36.905239
– ident: e_1_2_8_23_1
  doi: 10.1126/science.1127647
– ident: e_1_2_8_18_1
  doi: 10.1109/TGRS.2004.842478
SSID ssj0059085
Score 2.530279
Snippet In solving change detection problem, unsupervised methods are usually preferred to their supervised counterparts due to the difficulty of producing labelled...
SourceID crossref
wiley
iet
SourceType Enrichment Source
Index Database
Publisher
StartPage 2255
SubjectTerms appropriate data volume
belief networks
change detection map
change detection problems
dataset
deep architecture
deep belief network
deep learning‐based algorithms
deep learning‐based supervised method
detection performance
diversity
image classification
input images
input SAR images
introduced method
labelled data
learning (artificial intelligence)
morphological images
radar imaging
Research Article
supervised counterparts
supervised network fine‐tuning
synthetic aperture radar
synthetic aperture radar image changes
trained DBN
training approach
training process
unsupervised learning
unsupervised methods
Title Change detection in SAR images using deep belief network: a new training approach based on morphological images
URI http://digital-library.theiet.org/content/journals/10.1049/iet-ipr.2018.6248
https://onlinelibrary.wiley.com/doi/abs/10.1049%2Fiet-ipr.2018.6248
Volume 13
WOSCitedRecordID wos000497707700024&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: PRVWIB
  databaseName: Wiley Online Library Free Content
  customDbUrl:
  eissn: 1751-9667
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0059085
  issn: 1751-9659
  databaseCode: WIN
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
– providerCode: PRVWIB
  databaseName: Wiley Online Library Open Access
  customDbUrl:
  eissn: 1751-9667
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0059085
  issn: 1751-9659
  databaseCode: 24P
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://authorservices.wiley.com/open-science/open-access/browse-journals.html
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrR3ZSsNAcLHVB1-sJ9aLfRAfhGg2x27XtyoWBSnFA_sWZo9IQNNiqv6-szkKIiiILyHsMWxmdq7szgwhh6BiaWxqPW6U8KLA-h5EoD2Zhkr63AZcloHCN2I47I3HcrRALppYmCo_xPyHm-OMUl47BgdVVSFBoxaJmNmZl01dSk_WO-FB1GuRRcZC4bZ2EI0acexqesdlVKSrJ89jOT_alKffQHxRTi3s_mqyljpn0PmX1a6SldrkpP1qj6yRBZuvk05tftKauYsNMqkiDaixs_J-Vk6znN71b2n2gkKnoO6K_BP22ilVuBqb0ry6Q35GAV8_aFNugjaJyqnTkYYipJcJ0rORszXATfIwuLy_uPLqegyeDsOIexwsBxQBMYDU6DYpGeseiy1SFA0JwePACKEC4wNAFDDFfaV1aIABGD8yMtwi7XyS221CUyUNB8GYQvxYI6SQCmIN6ICiA-OLLvEbQiS6TlbuPuI5KQ_NI5kgQhNEaOIQmjiEdsnxfMq0ytTx0-Aj11bza_HTwLAk6-8gk-vRbXA-QJNZ8J0_zdoly9gunWZkYo-0Z69vdp8s6fdZVrwelLsan4_Xw0_lrfyF
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrR3LahsxcEicQnuJ07QhadpEh5JDYdt9aCWrNyeNcahrTJqCb8vosWEhXpvYbX4_o30YQsGFktuykgZpRvOSNDMAH1GnyrrcBcJqGfDYhQFyNIHKE61C4WKhqkDhkRyPe9OpmmzBtzYWps4PsT5w85xRyWvP4P5AunY4uU-SWbhVUCx8Ts-o91nEvLcNO5y0ja9jEPNJK499Ue-0Cov0BeVFqtZ3m-rLXyCeaKdtan5qs1ZKZ9B9nunuwW5jdLJ-vUtew5Yr96HbGKCsYe_lG5jXsQbMulX1QqtkRcl-9q9ZMSOxs2T-kfwttboF0zQdl7OyfkX-lSF9PrC24ARrU5UzryUtI0izOVG0lbQNwLfwa3B5czEMmooMgUkSLgKBTiAJgRRRGXKctEpNL0od0ZRMCSnS2EqpYxsiIo8jLUJtTGIxQrQhtyo5gE45L90hsFwrK1BGkSb8OCuVVBpTg-SCkgsTyiMIW0pkpklX7hdxl1XX5lxlhNCMEJp5hGYeoUfwaT1kUefq2NT5zP9rOHa5qWNS0fXfILOryXV8PiCjWYp3_zXqFF4Ob36MstHV-PsxvKI-yuvJSL6Hzur-t_sAL8yfVbG8P6m2-CPn7v9Y
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrR3ZShxBsPAi5MUrCd72g_gQGDNHH9u-eS2KsixqwLeh-pgwoLOLu0l-3-o5FiSgEHwbpquLnqqua7qrCuAAjdDOFz6SzqiIpz6OkKONdJEZHUufSl0nCt-owaD38KCHc3De5cI09SFmP9yCZNT6Ogi4H7uiCTh5KJJZ-mlUjkNNz6R3JFPem4dFLkjXhvrOfNjp49DUW9RpkaGhvBR6drapf_yD4pV1mqfh1z5rbXT6Kx-z3FVYbp1OdtLskjWY89U6rLQOKGvFe_IFRk2uAXN-Wt_QqlhZsbuTW1Y-kdqZsHBJ_heN-jEztBxfsKq5RX7MkB7_sq7hBOtKlbNgJR0jTE8j4minaVuEX-Fn_-L-7DJqOzJENsu4jCR6iaQEBKK2FDgZLWwvEZ54Sq6EkiJ1SpnUxYjI08TI2FibOUwQXcydzr7BQjWq_AawwmgnUSWJIfp4p7TSBoVFCkEphInVJsQdJ3LblisPH_GY18fmXOdE0JwImgeC5oGgm_B9NmXc1Op4C_gwvGsldvIWYFbz9X2U-dXwNj3tk9Os5NZ_zdqHT8Pzfn5zNbjehs8EooOZTNQOLEyff_tdWLJ_puXkea_e4S-N8v7c
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=Change+detection+in+SAR+images+using+deep+belief+network%3A+a+new+training+approach+based+on+morphological+images&rft.jtitle=IET+image+processing&rft.au=Samadi%2C+Farnaam&rft.au=Akbarizadeh%2C+Gholamreza&rft.au=Kaabi%2C+Hooman&rft.date=2019-10-17&rft.issn=1751-9659&rft.eissn=1751-9667&rft.volume=13&rft.issue=12&rft.spage=2255&rft.epage=2264&rft_id=info:doi/10.1049%2Fiet-ipr.2018.6248&rft.externalDBID=n%2Fa&rft.externalDocID=10_1049_iet_ipr_2018_6248
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1751-9659&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1751-9659&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1751-9659&client=summon