Automatic detection method of tunnel lining multi‐defects via an enhanced You Only Look Once network

Aiming to solve the challenges of low detection accuracy, poor anti‐interference ability, and slow detection speed in the traditional tunnel lining defect detection methods, a novel deep learning‐based model, named You Only Look Once network v4 enhanced by EfficientNet and depthwise separable convol...

Full description

Saved in:
Bibliographic Details
Published inComputer-aided civil and infrastructure engineering Vol. 37; no. 6; pp. 762 - 780
Main Authors Zhou, Zhong, Zhang, Junjie, Gong, Chenjie
Format Journal Article
LanguageEnglish
Published Hoboken Wiley Subscription Services, Inc 01.05.2022
Subjects
Online AccessGet full text
ISSN1093-9687
1467-8667
DOI10.1111/mice.12836

Cover

Abstract Aiming to solve the challenges of low detection accuracy, poor anti‐interference ability, and slow detection speed in the traditional tunnel lining defect detection methods, a novel deep learning‐based model, named You Only Look Once network v4 enhanced by EfficientNet and depthwise separable convolution (DSC; YOLOv4‐ED), is proposed. In the YOLOv4‐ED, EfficientNet is used as the backbone to improve the identification accuracy of indistinguishable defect targets in complex tunnel background and light conditions. Furthermore, DSC block is introduced to reduce the storage space of the model and thereby enhance the detection efficiency. The experimental results indicate that the mean average precision, F1 score, Model Size, and FPS of YOLOv4‐ED are 81.84%, 81.99%, 49.3 MB, and 43.5 f/s, respectively, which is superior to the comparison models in both detection accuracy and efficiency. Based on robust and cost‐effective YOLOv4‐ED, a tunnel lining defect detection platform (TLDDP) with the capacity of automated inspection of various lining defects (i.e., water leakage, crack, rebar‐exposed) is built. The established TLDDP can realize the high‐precision and automatic detection of multiple tunnel lining defects under different lighting and complex background conditions of the practical in‐service tunnel.
AbstractList Aiming to solve the challenges of low detection accuracy, poor anti‐interference ability, and slow detection speed in the traditional tunnel lining defect detection methods, a novel deep learning‐based model, named You Only Look Once network v4 enhanced by EfficientNet and depthwise separable convolution (DSC; YOLOv4‐ED), is proposed. In the YOLOv4‐ED, EfficientNet is used as the backbone to improve the identification accuracy of indistinguishable defect targets in complex tunnel background and light conditions. Furthermore, DSC block is introduced to reduce the storage space of the model and thereby enhance the detection efficiency. The experimental results indicate that the mean average precision, F 1 score, Model Size , and FPS of YOLOv4‐ED are 81.84%, 81.99%, 49.3 MB, and 43.5 f/s, respectively, which is superior to the comparison models in both detection accuracy and efficiency. Based on robust and cost‐effective YOLOv4‐ED, a tunnel lining defect detection platform (TLDDP) with the capacity of automated inspection of various lining defects (i.e., water leakage, crack, rebar‐exposed) is built. The established TLDDP can realize the high‐precision and automatic detection of multiple tunnel lining defects under different lighting and complex background conditions of the practical in‐service tunnel.
Aiming to solve the challenges of low detection accuracy, poor anti‐interference ability, and slow detection speed in the traditional tunnel lining defect detection methods, a novel deep learning‐based model, named You Only Look Once network v4 enhanced by EfficientNet and depthwise separable convolution (DSC; YOLOv4‐ED), is proposed. In the YOLOv4‐ED, EfficientNet is used as the backbone to improve the identification accuracy of indistinguishable defect targets in complex tunnel background and light conditions. Furthermore, DSC block is introduced to reduce the storage space of the model and thereby enhance the detection efficiency. The experimental results indicate that the mean average precision, F1 score, Model Size, and FPS of YOLOv4‐ED are 81.84%, 81.99%, 49.3 MB, and 43.5 f/s, respectively, which is superior to the comparison models in both detection accuracy and efficiency. Based on robust and cost‐effective YOLOv4‐ED, a tunnel lining defect detection platform (TLDDP) with the capacity of automated inspection of various lining defects (i.e., water leakage, crack, rebar‐exposed) is built. The established TLDDP can realize the high‐precision and automatic detection of multiple tunnel lining defects under different lighting and complex background conditions of the practical in‐service tunnel.
Aiming to solve the challenges of low detection accuracy, poor anti‐interference ability, and slow detection speed in the traditional tunnel lining defect detection methods, a novel deep learning‐based model, named You Only Look Once network v4 enhanced by EfficientNet and depthwise separable convolution (DSC; YOLOv4‐ED), is proposed. In the YOLOv4‐ED, EfficientNet is used as the backbone to improve the identification accuracy of indistinguishable defect targets in complex tunnel background and light conditions. Furthermore, DSC block is introduced to reduce the storage space of the model and thereby enhance the detection efficiency. The experimental results indicate that the mean average precision, F1 score, Model Size, and FPS of YOLOv4‐ED are 81.84%, 81.99%, 49.3 MB, and 43.5 f/s, respectively, which is superior to the comparison models in both detection accuracy and efficiency. Based on robust and cost‐effective YOLOv4‐ED, a tunnel lining defect detection platform (TLDDP) with the capacity of automated inspection of various lining defects (i.e., water leakage, crack, rebar‐exposed) is built. The established TLDDP can realize the high‐precision and automatic detection of multiple tunnel lining defects under different lighting and complex background conditions of the practical in‐service tunnel.
Author Gong, Chenjie
Zhou, Zhong
Zhang, Junjie
Author_xml – sequence: 1
  givenname: Zhong
  surname: Zhou
  fullname: Zhou, Zhong
  organization: Hunan Tieyuan Civil Engineering Testing Co., Ltd
– sequence: 2
  givenname: Junjie
  surname: Zhang
  fullname: Zhang, Junjie
  organization: Central South University
– sequence: 3
  givenname: Chenjie
  surname: Gong
  fullname: Gong, Chenjie
  email: gongcj@csu.edu.cn
  organization: Hunan Tieyuan Civil Engineering Testing Co., Ltd
BookMark eNp9kLFOwzAURS1UJNrCwhdYYkNKcWzHbsaqKlCpqAsMTJFrv1C3iV0Sh6obn8A38iWkhAkh7vLucO57eneAes47QOgyJqO41U1pNYxiOmbiBPVjLmQ0FkL2Wk9SFqViLM_QoK43pBXnrI_ySRN8qYLV2EAAHax3uISw9gb7HIfGOShwYZ11L7hsimA_3z8M5C1Z4zersHIY3Fo5DQY_-wYvXXHAC--3rdOAHYS9r7bn6DRXRQ0XP3OInm5nj9P7aLG8m08ni0gzIUWUGmok1UCFSZOEc6p1DAaUZFIakqhUCq3FSlCV8NQQxjRJIB-LlPOV4SpnQ3TV7d1V_rWBOmQb31SuPZlRSQVhMqWspUhH6crXdQV5pm1Qx9dDpWyRxSQ7tpkd28y-22wj178iu8qWqjr8DccdvLcFHP4hs4f5dNZlvgDL34k5
CitedBy_id crossref_primary_10_3390_buildings12101555
crossref_primary_10_1016_j_undsp_2024_08_007
crossref_primary_10_1111_mice_12991
crossref_primary_10_3390_su16104285
crossref_primary_10_1111_mice_13042
crossref_primary_10_1177_14759217231222557
crossref_primary_10_1016_j_ijmst_2024_03_003
crossref_primary_10_3390_app12178506
crossref_primary_10_1111_mice_12998
crossref_primary_10_1016_j_tust_2023_105572
crossref_primary_10_1061_JCEMD4_COENG_14089
crossref_primary_10_1016_j_jrmge_2022_03_015
crossref_primary_10_1061_JPCFEV_CFENG_4928
crossref_primary_10_1016_j_asej_2024_102983
crossref_primary_10_26599_JIC_2023_9180004
crossref_primary_10_3390_app12094556
crossref_primary_10_1016_j_autcon_2023_105098
crossref_primary_10_3390_electronics12153222
crossref_primary_10_1016_j_autcon_2023_105014
crossref_primary_10_1016_j_autcon_2023_104840
crossref_primary_10_1002_nag_3367
crossref_primary_10_1111_mice_12914
crossref_primary_10_3390_jmse10111709
crossref_primary_10_1109_ACCESS_2022_3224594
crossref_primary_10_1007_s13349_024_00900_y
crossref_primary_10_1016_j_measurement_2023_114009
crossref_primary_10_3390_s24186007
crossref_primary_10_1016_j_aei_2024_102578
crossref_primary_10_1016_j_aei_2023_102214
crossref_primary_10_1016_j_autcon_2022_104668
crossref_primary_10_3390_app12105142
crossref_primary_10_1007_s10064_023_03286_1
crossref_primary_10_1016_j_engappai_2024_109422
crossref_primary_10_1016_j_tust_2022_104737
crossref_primary_10_1007_s40515_025_00558_z
crossref_primary_10_1007_s11709_023_0948_z
crossref_primary_10_1016_j_autcon_2024_105280
crossref_primary_10_1007_s13349_025_00909_x
crossref_primary_10_3390_electronics13020253
crossref_primary_10_1109_ACCESS_2023_3330843
crossref_primary_10_1016_j_ijrmms_2024_105933
crossref_primary_10_1016_j_tust_2023_105107
crossref_primary_10_3390_technologies10050107
crossref_primary_10_1016_j_engfailanal_2022_106387
crossref_primary_10_3390_app131910583
crossref_primary_10_3390_app12104845
crossref_primary_10_1111_mice_12984
crossref_primary_10_32604_sdhm_2024_042388
crossref_primary_10_1016_j_jweia_2024_105698
crossref_primary_10_1051_e3sconf_202454804001
crossref_primary_10_1016_j_autcon_2024_105727
crossref_primary_10_1016_j_cscm_2023_e02555
crossref_primary_10_1016_j_compgeo_2022_104999
crossref_primary_10_1016_j_tust_2025_106508
crossref_primary_10_1587_transinf_2023EDP7073
crossref_primary_10_1007_s11694_023_02351_3
crossref_primary_10_1016_j_autcon_2023_105186
crossref_primary_10_1016_j_engappai_2022_105478
crossref_primary_10_1111_mice_13241
crossref_primary_10_1177_14759217241254748
crossref_primary_10_3390_app12104919
crossref_primary_10_1016_j_engfailanal_2023_107327
crossref_primary_10_1016_j_tust_2022_104567
crossref_primary_10_1016_j_conbuildmat_2023_131621
crossref_primary_10_3233_ICA_230709
crossref_primary_10_1049_itr2_12497
crossref_primary_10_1111_mice_13003
crossref_primary_10_1111_mice_13124
crossref_primary_10_1111_mice_13366
crossref_primary_10_1111_mice_12949
crossref_primary_10_1061_JCEMD4_COENG_13512
crossref_primary_10_3390_app14104148
crossref_primary_10_1016_j_aei_2023_102032
crossref_primary_10_1109_ACCESS_2024_3437154
crossref_primary_10_1007_s11709_023_0965_y
crossref_primary_10_1016_j_engappai_2022_105225
crossref_primary_10_1109_TNNLS_2023_3266243
crossref_primary_10_1016_j_isprsjprs_2023_04_011
crossref_primary_10_1155_2022_8357463
crossref_primary_10_3390_su15021292
crossref_primary_10_1177_14759217241267794
crossref_primary_10_1109_TCSVT_2024_3433555
crossref_primary_10_1111_mice_13097
crossref_primary_10_1016_j_advengsoft_2024_103691
crossref_primary_10_1038_s41598_024_75723_4
crossref_primary_10_1016_j_engfailanal_2025_109332
crossref_primary_10_1111_mice_13019
crossref_primary_10_21595_jme_2024_23977
crossref_primary_10_3390_app14051892
crossref_primary_10_1109_ACCESS_2024_3519321
crossref_primary_10_1016_j_engappai_2025_110035
crossref_primary_10_3390_su14148383
crossref_primary_10_1016_j_autcon_2023_104915
crossref_primary_10_32604_cmc_2023_043566
crossref_primary_10_1016_j_tust_2023_105432
crossref_primary_10_1111_mice_13067
crossref_primary_10_1016_j_jii_2025_100790
crossref_primary_10_1016_j_tust_2024_105713
crossref_primary_10_1111_mice_12932
crossref_primary_10_1016_j_autcon_2022_104595
crossref_primary_10_1177_14759217231171696
crossref_primary_10_1016_j_autcon_2022_104633
crossref_primary_10_1016_j_tust_2024_106124
crossref_primary_10_1109_JSEN_2023_3344124
crossref_primary_10_3390_s23167106
crossref_primary_10_1016_j_tust_2022_104811
crossref_primary_10_1111_mice_13181
crossref_primary_10_1016_j_tust_2023_105428
crossref_primary_10_1080_17499518_2023_2172187
crossref_primary_10_1016_j_engfailanal_2024_109082
crossref_primary_10_1016_j_engappai_2023_107085
crossref_primary_10_1016_j_conbuildmat_2024_138240
crossref_primary_10_1186_s40537_025_01065_1
crossref_primary_10_1080_17499518_2024_2337380
crossref_primary_10_1111_mice_13110
crossref_primary_10_3390_s22197400
crossref_primary_10_1093_iti_liad019
crossref_primary_10_1007_s11760_024_03786_x
crossref_primary_10_1111_mice_13117
crossref_primary_10_1016_j_aei_2025_103127
crossref_primary_10_1016_j_ghm_2024_01_001
crossref_primary_10_1016_j_undsp_2022_07_003
crossref_primary_10_1016_j_compgeo_2022_105002
crossref_primary_10_3390_s24175452
crossref_primary_10_1016_j_undsp_2024_06_005
crossref_primary_10_1016_j_patcog_2024_111251
Cites_doi 10.1007/s00521-019-04359-7
10.1061/(ASCE)CP.1943-5487.0000516
10.1109/TNNLS.2017.2682102
10.1109/ICPR.2006.98
10.1109/CVPR.2014.81
10.1109/TIP.2020.2994445
10.1016/j.tust.2018.04.002
10.1109/TSMC.1979.4310076
10.1002/widm.1308
10.1111/mice.12367
10.3233/ICA-2010-0345
10.1111/mice.12686
10.1007/s11554-021-01130-x
10.1109/CVPR.2017.690
10.1016/j.autcon.2021.103934
10.1111/mice.12263
10.1111/mice.12613
10.1061/AJRUA6.0000989
10.1177/1475921720938486
10.1016/j.tust.2017.05.010
10.1111/mice.12731
10.1155/2021/8846442
10.1016/j.patcog.2019.01.006
10.1016/j.imavis.2011.10.003
10.1016/j.tust.2020.103724
10.1007/978-3-319-46448-0_2
10.1016/j.autcon.2019.102920
10.1109/TITS.2019.2910595
10.1016/j.soildyn.2017.05.013
10.1061/(ASCE)CO.1943-7862.0001047
10.1016/j.autcon.2020.103357
10.1016/j.tust.2020.103594
10.1016/j.tust.2016.12.008
10.28991/cej-2019-03091316
10.1111/mice.12564
10.1111/j.1467-8667.2005.00376.x
10.1109/TNNLS.2018.2876865
10.3141/2225-10
10.1016/j.tust.2021.104082
10.1111/mice.12580
10.1111/exsy.12647
10.1016/j.ijleo.2015.09.147
10.1109/CVPR.2018.00913
10.1109/ICPR.2006.479
10.1061/(ASCE)GM.1943-5622.0001371
10.1007/978-981-15-5093-5_9
10.1109/CISP.2008.13
10.1111/mice.12497
10.1016/j.tust.2020.103658
10.1061/(ASCE)CO.1943-7862.0001570
10.1111/mice.12519
10.1002/stc.2187
10.4028/www.scientific.net/AMM.580-583.1218
10.1109/TPAMI.2015.2389824
10.1007/s00521-019-04146-4
ContentType Journal Article
Copyright 2022
2022 Computer‐Aided Civil and Infrastructure Engineering
Copyright_xml – notice: 2022
– notice: 2022 Computer‐Aided Civil and Infrastructure Engineering
DBID AAYXX
CITATION
7SC
8FD
FR3
JQ2
KR7
L7M
L~C
L~D
DOI 10.1111/mice.12836
DatabaseName CrossRef
Computer and Information Systems Abstracts
Technology Research Database
Engineering Research Database
ProQuest Computer Science Collection
Civil Engineering Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Civil Engineering Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Engineering Research Database
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList CrossRef
Civil Engineering Abstracts

DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Engineering
Computer Science
EISSN 1467-8667
EndPage 780
ExternalDocumentID 10_1111_mice_12836
MICE12836
Genre article
GroupedDBID ..I
.3N
.4S
.DC
.GA
05W
0R~
10A
1OB
1OC
29F
31~
33P
3SF
4.4
50Y
50Z
51W
51X
52M
52N
52O
52P
52S
52T
52U
52W
52X
5GY
5HH
5LA
5VS
66C
6P2
702
7PT
8-0
8-1
8-3
8-4
8-5
8UM
930
A03
AAESR
AAEVG
AAHHS
AAHQN
AAMNL
AANHP
AANLZ
AAONW
AASGY
AAXRX
AAYCA
AAZKR
ABCQN
ABCUV
ABDBF
ABEML
ABFSI
ABJNI
ACAHQ
ACBWZ
ACCFJ
ACCZN
ACGFS
ACPOU
ACRPL
ACSCC
ACUHS
ACXBN
ACXQS
ACYXJ
ADBBV
ADEOM
ADIZJ
ADKYN
ADMGS
ADNMO
ADOZA
ADXAS
ADZMN
ADZOD
AEEZP
AEIGN
AEIMD
AENEX
AEQDE
AEUQT
AEUYR
AFBPY
AFEBI
AFFPM
AFGKR
AFPWT
AHBTC
AHEFC
AI.
AITYG
AIURR
AIWBW
AJBDE
AJXKR
ALAGY
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ALVPJ
AMBMR
AMYDB
ARCSS
ASPBG
ATUGU
AUFTA
AVWKF
AZBYB
AZFZN
AZVAB
BAFTC
BDRZF
BFHJK
BHBCM
BMNLL
BMXJE
BNHUX
BROTX
BRXPI
BY8
CAG
COF
CS3
CWDTD
D-E
D-F
DCZOG
DPXWK
DR2
DRFUL
DRSTM
DU5
E.L
EAD
EAP
EBS
EDO
EJD
EMK
EST
ESX
F00
F01
F04
FEDTE
G-S
G.N
GODZA
H.T
H.X
HF~
HGLYW
HVGLF
HZI
HZ~
I-F
IHE
IX1
J0M
K48
LATKE
LC2
LC3
LEEKS
LH4
LITHE
LOXES
LP6
LP7
LUTES
LW6
LYRES
MEWTI
MK4
MK~
MRFUL
MRSTM
MSFUL
MSSTM
MXFUL
MXSTM
N04
N05
NF~
O66
O9-
OIG
P2P
P2W
P2X
P4D
PALCI
Q.N
Q11
QB0
R.K
RJQFR
RX1
SAMSI
SUPJJ
TN5
TUS
UB1
VH1
W8V
W99
WBKPD
WIH
WIK
WLBEL
WOHZO
WQJ
WRC
WXSBR
WYISQ
XG1
ZZTAW
~IA
~WT
AAMMB
AAYXX
ADMLS
AEFGJ
AEYWJ
AGHNM
AGQPQ
AGXDD
AGYGG
AIDQK
AIDYY
AIQQE
CITATION
7SC
8FD
FR3
JQ2
KR7
L7M
L~C
L~D
ID FETCH-LOGICAL-c3676-9d2d72ce26d955442cc1edea7377d05a976cc6b62a549d033c05ef86944bd4af3
IEDL.DBID DR2
ISSN 1093-9687
IngestDate Sun Jul 13 04:13:45 EDT 2025
Wed Oct 01 04:16:00 EDT 2025
Thu Apr 24 23:04:17 EDT 2025
Wed Jan 22 16:26:46 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 6
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c3676-9d2d72ce26d955442cc1edea7377d05a976cc6b62a549d033c05ef86944bd4af3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
PQID 2726037923
PQPubID 2045171
PageCount 19
ParticipantIDs proquest_journals_2726037923
crossref_citationtrail_10_1111_mice_12836
crossref_primary_10_1111_mice_12836
wiley_primary_10_1111_mice_12836_MICE12836
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate May 2022
PublicationDateYYYYMMDD 2022-05-01
PublicationDate_xml – month: 05
  year: 2022
  text: May 2022
PublicationDecade 2020
PublicationPlace Hoboken
PublicationPlace_xml – name: Hoboken
PublicationTitle Computer-aided civil and infrastructure engineering
PublicationYear 2022
Publisher Wiley Subscription Services, Inc
Publisher_xml – name: Wiley Subscription Services, Inc
References 2015; 37
2019; 90
2021; 20
2017b; 100
2010; 17
2016; 30
2019; 19
2005; 20
2016; 142
2021; 36
2018; 4
2021; 115
2019; 21
2017; 32
2022; 37
2018; 77
2018; 33
2011; 29
2017a; 28
1979; 9
2021; 2021
2018; 144
2017; 63
2019; 9
2011; 2225
2019; 5
2019; 30
2017; 68
2021; 108
2021; 107
2008
2020; 37
2020; 106
2006
2020; 35
2016; 127
2020; 32
2019; 107
2018; 25
2015; 28
2021
2020
2021; 18
2019
2018
2017
2016
2015
2014; 580
2014
2021; 132
2020; 119
2020; 29
e_1_2_10_23_1
e_1_2_10_46_1
e_1_2_10_21_1
e_1_2_10_42_1
e_1_2_10_40_1
e_1_2_10_2_1
e_1_2_10_4_1
e_1_2_10_18_1
e_1_2_10_6_1
e_1_2_10_16_1
e_1_2_10_39_1
e_1_2_10_8_1
e_1_2_10_14_1
e_1_2_10_37_1
e_1_2_10_57_1
e_1_2_10_58_1
e_1_2_10_13_1
e_1_2_10_34_1
e_1_2_10_11_1
e_1_2_10_32_1
e_1_2_10_30_1
e_1_2_10_51_1
Ren S. (e_1_2_10_45_1) 2015; 28
e_1_2_10_61_1
e_1_2_10_29_1
e_1_2_10_63_1
e_1_2_10_27_1
Wan Z. (e_1_2_10_53_1) 2020
e_1_2_10_65_1
e_1_2_10_25_1
e_1_2_10_48_1
e_1_2_10_24_1
e_1_2_10_22_1
e_1_2_10_43_1
e_1_2_10_20_1
e_1_2_10_41_1
Girshick R. (e_1_2_10_15_1) 2015
Tan M. (e_1_2_10_49_1) 2019
e_1_2_10_52_1
e_1_2_10_3_1
e_1_2_10_19_1
e_1_2_10_54_1
e_1_2_10_17_1
e_1_2_10_38_1
e_1_2_10_56_1
e_1_2_10_7_1
e_1_2_10_36_1
e_1_2_10_12_1
e_1_2_10_35_1
e_1_2_10_9_1
e_1_2_10_59_1
e_1_2_10_10_1
e_1_2_10_33_1
e_1_2_10_31_1
Redmon J. (e_1_2_10_44_1) 2016
e_1_2_10_50_1
Wang P. (e_1_2_10_55_1) 2021; 2021
e_1_2_10_60_1
e_1_2_10_62_1
Alekseychuk O. (e_1_2_10_5_1) 2006
e_1_2_10_64_1
e_1_2_10_28_1
e_1_2_10_66_1
e_1_2_10_26_1
e_1_2_10_47_1
References_xml – volume: 106
  year: 2020
  article-title: Evolutionary hybrid neural network approach to predict shield tunneling‐induced ground settlements
  publication-title: Tunnelling and Underground Space Technology
– start-page: 850
  year: 2006
  end-page: 855
– volume: 33
  start-page: 638
  issue: 8
  year: 2018
  end-page: 654
  article-title: A fast detection method via region‐based fully convolutional neural networks for shield tunnel lining defects
  publication-title: Computer‐Aided Civil and Infrastructure Engineering
– volume: 5
  start-page: 1119
  issue: 5
  year: 2019
  end-page: 1123
  article-title: Analysis and study on crack characteristics of highway tunnel lining
  publication-title: Civil Engineering Journal
– start-page: 1440
  year: 2015
  end-page: 1448
  article-title: Fast R‐CNN
– volume: 18
  start-page: 1
  year: 2021
  end-page: 11
  article-title: Efficient real‐time defect detection for spillway tunnel using deep learning
  publication-title: Journal of Real‐Time Image Processing
– volume: 36
  start-page: 227
  issue: 2
  year: 2021
  end-page: 241
  article-title: Learning‐based image scale estimation using surface textures for quantitative visual inspection of regions‐of‐interest
  publication-title: Computer‐Aided Civil and Infrastructure Engineering
– volume: 37
  start-page: 386
  issue: 3
  year: 2022
  end-page: 402
  article-title: An optimization strategy to improve the deep learning‐based recognition model of leakage in shield tunnels
  publication-title: Computer‐Aided Civil and Infrastructure Engineering
– volume: 2021
  year: 2021
  article-title: Automatic identification and location of tunnel lining cracks
  publication-title: Advances in Civil Engineering
– volume: 17
  start-page: 197
  issue: 3
  year: 2010
  end-page: 210
  article-title: Enhanced probabilistic neural network with local decision circles: A robust classifier
  publication-title: Integrated Computer‐Aided Engineering
– volume: 36
  start-page: 61
  issue: 1
  year: 2021
  end-page: 72
  article-title: Automatic detection method of cracks from concrete surface imagery using two‐step light gradient boosting machine
  publication-title: Computer‐Aided Civil and Infrastructure Engineering
– year: 2018
– volume: 25
  issue: 8
  year: 2018
  article-title: Sensing dynamic displacements in masonry rail bridges using 2D digital image correlation
  publication-title: Structural Control and Health Monitoring
– volume: 32
  start-page: 8675
  issue: 12
  year: 2020
  end-page: 8690
  article-title: A dynamic ensemble learning algorithm for neural networks
  publication-title: Neural Computing and Applications
– volume: 68
  start-page: 38
  year: 2017
  end-page: 57
  article-title: Comparison of the structural behavior of reinforced concrete and steel fiber reinforced concrete tunnel segmental joints
  publication-title: Tunnelling and Underground Space Technology
– volume: 9
  start-page: 62
  issue: 1
  year: 1979
  end-page: 66
  article-title: A threshold selection method from gray‐level histograms
  publication-title: IEEE Transactions on Systems, Man, and Cybernetics
– volume: 35
  start-page: 373
  issue: 4
  year: 2020
  end-page: 388
  article-title: Concrete crack detection with handwriting script interferences using faster region‐based convolutional neural network
  publication-title: Computer‐Aided Civil and Infrastructure Engineering
– start-page: 580
  year: 2014
  end-page: 587
  article-title: Rich feature hierarchies for accurate object detection and semantic segmentation
– start-page: 21
  year: 2016
  end-page: 37
  article-title: SSD: Single shot multibox detector
– volume: 4
  issue: 4
  year: 2018
  article-title: Characterization of crack and leakage defects of concrete linings of road tunnels in China
  publication-title: ASCE‐ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering
– volume: 36
  start-page: 126
  issue: 2
  year: 2021
  end-page: 142
  article-title: Uncertainty‐assisted deep vision structural health monitoring
  publication-title: Computer‐Aided Civil and Infrastructure Engineering
– volume: 30
  issue: 3
  year: 2016
  article-title: Distortion‐free image mosaicing for tunnel inspection based on robust cylindrical surface estimation through structure from motion
  publication-title: ASCE Journal of Computing in Civil Engineering
– volume: 107
  year: 2019
  article-title: Instance‐level recognition and quantification for concrete surface bughole based on deep learning
  publication-title: Automation in Construction
– start-page: 7263
  year: 2017
  end-page: 7271
  article-title: YOLO9000: Better, faster, stronger
– year: 2020
  article-title: Slender object detection: Diagnoses and improvements
  publication-title: arXiv preprint
– volume: 90
  start-page: 119
  year: 2019
  end-page: 133
  article-title: Wider or deeper: Revisiting the ResNet model for visual recognition
  publication-title: Pattern Recognition
– start-page: 792
  year: 2008
  end-page: 796
– volume: 29
  start-page: 861
  issue: 12
  year: 2011
  end-page: 872
  article-title: FoSA: F* seed‐growing approach for crack‐line detection from pavement images
  publication-title: Image and Vision Computing
– year: 2015
– volume: 107
  year: 2021
  article-title: Analyses of the defects in highway tunnels in China
  publication-title: Tunnelling and Underground Space Technology
– volume: 142
  issue: 2
  year: 2016
  article-title: A novel machine learning model for estimation of sale prices of real estate units
  publication-title: Journal of Construction Engineering and Management
– volume: 32
  start-page: 6393
  issue: 10
  year: 2020
  end-page: 6404
  article-title: FEMa: A finite element machine for fast learning
  publication-title: Neural Computing and Applications
– volume: 20
  start-page: 484
  issue: 2
  year: 2021
  end-page: 499
  article-title: Imaging‐based crack detection on concrete surfaces using You Only Look Once network
  publication-title: Structural Health Monitoring
– volume: 9
  issue: 5
  year: 2019
  article-title: Tunnel crack detection using coarse‐to‐fine region localization and edge detection
  publication-title: Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery
– start-page: 91
  year: 2021
  end-page: 101
– volume: 144
  issue: 12
  year: 2018
  article-title: Novel machine learning model for construction cost estimation taking into account economic variables and indices
  publication-title: Journal of Construction Engineering and Management
– volume: 37
  issue: 6
  year: 2020
  article-title: Deep learning techniques for recommender systems based on collaborative filtering
  publication-title: Expert Systems
– volume: 28
  start-page: 3074
  issue: 12
  year: 2017a
  end-page: 3083
  article-title: A new neural dynamic classification algorithm
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
– volume: 20
  start-page: 52
  issue: 1
  year: 2005
  end-page: 61
  article-title: Monitoring crack changes in concrete structures
  publication-title: Computer‐Aided Civil and Infrastructure Engineering
– start-page: 901
  year: 2006
  end-page: 904
  article-title: A method for crack detection on a concrete structure
– volume: 100
  start-page: 417
  year: 2017b
  end-page: 427
  article-title: NEEWS: A novel earthquake early warning model using neural dynamic classification and neural dynamic optimization
  publication-title: Soil Dynamics and Earthquake Engineering
– volume: 77
  start-page: 166
  year: 2018
  end-page: 176
  article-title: Deep learning based image recognition for crack and leakage defects of metro shield tunnel
  publication-title: Tunnelling and Underground Space Technology
– volume: 21
  start-page: 1525
  issue: 4
  year: 2019
  end-page: 1535
  article-title: Feature pyramid and hierarchical boosting network for pavement crack detection
  publication-title: IEEE Transactions on Intelligent Transportation Systems
– year: 2016
– volume: 19
  issue: 4
  year: 2019
  article-title: Cracking performance of an operational tunnel lining due to local construction defects
  publication-title: International Journal of Geomechanics
– volume: 35
  start-page: 549
  issue: 6
  year: 2020
  end-page: 564
  article-title: Real‐time crack assessment using deep neural networks with wall‐climbing unmanned aerial system
  publication-title: Computer‐Aided Civil and Infrastructure Engineering
– volume: 28
  start-page: 91
  year: 2015
  end-page: 99
  article-title: Faster R‐CNN: Towards real‐time object detection with region proposal networks
  publication-title: Advances in Neural Information Processing Systems
– start-page: 6105
  year: 2019
  end-page: 6114
– volume: 29
  start-page: 6864
  year: 2020
  end-page: 6872
  article-title: Multi‐atlas brain parcellation using squeeze‐and‐excitation fully convolutional networks
  publication-title: IEEE Transactions on Image Processing
– volume: 132
  year: 2021
  article-title: A deep learning‐based approach for refined crack evaluation from shield tunnel lining images
  publication-title: Automation in Construction
– volume: 36
  start-page: 1585
  issue: 12
  year: 2021
  end-page: 1599
  article-title: Autonomous detection of damage to multiple steel surfaces from 360° panoramas using deep neural networks
  publication-title: Computer‐Aided Civil and Infrastructure Engineering
– volume: 32
  start-page: 361
  issue: 5
  year: 2017
  end-page: 378
  article-title: Deep learning‐based crack damage detection using convolutional neural networks
  publication-title: Computer‐Aided Civil and Infrastructure Engineering
– volume: 2225
  start-page: 89
  issue: 1
  year: 2011
  end-page: 98
  article-title: Dynamic programming and connected component analysis for an enhanced pavement distress segmentation algorithm
  publication-title: Transportation Research Record
– year: 2006
– volume: 108
  year: 2021
  article-title: A novel tunnel‐lining crack recognition system based on digital image technology
  publication-title: Tunnelling and Underground Space Technology
– start-page: 8759
  year: 2018
  end-page: 8768
  article-title: Path aggregation network for instance segmentation
– volume: 30
  start-page: 3212
  issue: 11
  year: 2019
  end-page: 3232
  article-title: Object detection with deep learning: A review
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
– volume: 119
  year: 2020
  article-title: A spatial‐channel hierarchical deep learning network for pixel‐level automated crack detection
  publication-title: Automation in Construction
– start-page: 779
  year: 2016
  end-page: 788
  article-title: You only look once: Unified, real‐time object detection
– volume: 63
  start-page: 54
  year: 2017
  end-page: 68
  article-title: Development and application of the integrated sealant test apparatus for sealing gaskets in tunnel segmental joints
  publication-title: Tunnelling and Underground Space Technology
– volume: 580
  start-page: 1218
  year: 2014
  end-page: 1222
– year: 2017
– volume: 37
  start-page: 1904
  issue: 9
  year: 2015
  end-page: 1916
  article-title: Spatial pyramid pooling in deep convolutional networks for visual recognition
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
– volume: 127
  start-page: 1030
  issue: 3
  year: 2016
  end-page: 1033
  article-title: Detection crack in image using Otsu method and multiple filtering in image processing techniques
  publication-title: Optik
– volume: 115
  year: 2021
  article-title: Sealing performance of a precast tunnel gasketed joint under high hydrostatic pressures: Site investigation and detailed numerical modeling
  publication-title: Tunnelling and Underground Space Technology
– ident: e_1_2_10_4_1
  doi: 10.1007/s00521-019-04359-7
– ident: e_1_2_10_7_1
  doi: 10.1061/(ASCE)CP.1943-5487.0000516
– ident: e_1_2_10_39_1
  doi: 10.1109/TNNLS.2017.2682102
– ident: e_1_2_10_14_1
  doi: 10.1109/ICPR.2006.98
– ident: e_1_2_10_16_1
  doi: 10.1109/CVPR.2014.81
– ident: e_1_2_10_50_1
  doi: 10.1109/TIP.2020.2994445
– ident: e_1_2_10_20_1
  doi: 10.1016/j.tust.2018.04.002
– ident: e_1_2_10_52_1
– ident: e_1_2_10_34_1
  doi: 10.1109/TSMC.1979.4310076
– ident: e_1_2_10_25_1
  doi: 10.1002/widm.1308
– ident: e_1_2_10_58_1
  doi: 10.1111/mice.12367
– ident: e_1_2_10_3_1
  doi: 10.3233/ICA-2010-0345
– ident: e_1_2_10_30_1
  doi: 10.1111/mice.12686
– volume-title: Detection of crack‐like indications in digital radiography by global optimisation of a probabilistic estimation function
  year: 2006
  ident: e_1_2_10_5_1
– ident: e_1_2_10_12_1
  doi: 10.1007/s11554-021-01130-x
– ident: e_1_2_10_42_1
  doi: 10.1109/CVPR.2017.690
– ident: e_1_2_10_65_1
  doi: 10.1016/j.autcon.2021.103934
– ident: e_1_2_10_6_1
  doi: 10.1111/mice.12263
– ident: e_1_2_10_36_1
  doi: 10.1111/mice.12613
– ident: e_1_2_10_43_1
– ident: e_1_2_10_54_1
  doi: 10.1061/AJRUA6.0000989
– ident: e_1_2_10_19_1
– start-page: 779
  volume-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
  year: 2016
  ident: e_1_2_10_44_1
– ident: e_1_2_10_10_1
  doi: 10.1177/1475921720938486
– ident: e_1_2_10_17_1
  doi: 10.1016/j.tust.2017.05.010
– year: 2020
  ident: e_1_2_10_53_1
  article-title: Slender object detection: Diagnoses and improvements
  publication-title: arXiv preprint
– ident: e_1_2_10_59_1
  doi: 10.1111/mice.12731
– volume: 2021
  start-page: 8846442
  year: 2021
  ident: e_1_2_10_55_1
  article-title: Automatic identification and location of tunnel lining cracks
  publication-title: Advances in Civil Engineering
  doi: 10.1155/2021/8846442
– ident: e_1_2_10_57_1
  doi: 10.1016/j.patcog.2019.01.006
– ident: e_1_2_10_27_1
  doi: 10.1016/j.imavis.2011.10.003
– ident: e_1_2_10_23_1
  doi: 10.1016/j.tust.2020.103724
– start-page: 6105
  volume-title: International Conference on Machine Learning
  year: 2019
  ident: e_1_2_10_49_1
– ident: e_1_2_10_29_1
  doi: 10.1007/978-3-319-46448-0_2
– ident: e_1_2_10_56_1
  doi: 10.1016/j.autcon.2019.102920
– ident: e_1_2_10_60_1
  doi: 10.1109/TITS.2019.2910595
– ident: e_1_2_10_40_1
  doi: 10.1016/j.soildyn.2017.05.013
– ident: e_1_2_10_38_1
  doi: 10.1061/(ASCE)CO.1943-7862.0001047
– volume: 28
  start-page: 91
  year: 2015
  ident: e_1_2_10_45_1
  article-title: Faster R‐CNN: Towards real‐time object detection with region proposal networks
  publication-title: Advances in Neural Information Processing Systems
– ident: e_1_2_10_35_1
  doi: 10.1016/j.autcon.2020.103357
– start-page: 1440
  volume-title: Proceedings of the IEEE International Conference on Computer Vision
  year: 2015
  ident: e_1_2_10_15_1
– ident: e_1_2_10_62_1
  doi: 10.1016/j.tust.2020.103594
– ident: e_1_2_10_11_1
  doi: 10.1016/j.tust.2016.12.008
– ident: e_1_2_10_63_1
  doi: 10.28991/cej-2019-03091316
– ident: e_1_2_10_8_1
  doi: 10.1111/mice.12564
– ident: e_1_2_10_47_1
  doi: 10.1111/j.1467-8667.2005.00376.x
– ident: e_1_2_10_66_1
  doi: 10.1109/TNNLS.2018.2876865
– ident: e_1_2_10_21_1
  doi: 10.3141/2225-10
– ident: e_1_2_10_24_1
  doi: 10.1016/j.tust.2021.104082
– ident: e_1_2_10_46_1
  doi: 10.1111/mice.12580
– ident: e_1_2_10_31_1
  doi: 10.1111/exsy.12647
– ident: e_1_2_10_48_1
  doi: 10.1016/j.ijleo.2015.09.147
– ident: e_1_2_10_28_1
  doi: 10.1109/CVPR.2018.00913
– ident: e_1_2_10_33_1
  doi: 10.1109/ICPR.2006.479
– ident: e_1_2_10_13_1
  doi: 10.1061/(ASCE)GM.1943-5622.0001371
– ident: e_1_2_10_51_1
– ident: e_1_2_10_32_1
  doi: 10.1007/978-981-15-5093-5_9
– ident: e_1_2_10_26_1
  doi: 10.1109/CISP.2008.13
– ident: e_1_2_10_9_1
  doi: 10.1111/mice.12497
– ident: e_1_2_10_61_1
  doi: 10.1016/j.tust.2020.103658
– ident: e_1_2_10_41_1
  doi: 10.1061/(ASCE)CO.1943-7862.0001570
– ident: e_1_2_10_22_1
  doi: 10.1111/mice.12519
– ident: e_1_2_10_2_1
  doi: 10.1002/stc.2187
– ident: e_1_2_10_64_1
  doi: 10.4028/www.scientific.net/AMM.580-583.1218
– ident: e_1_2_10_18_1
  doi: 10.1109/TPAMI.2015.2389824
– ident: e_1_2_10_37_1
  doi: 10.1007/s00521-019-04146-4
SSID ssj0000443
Score 2.6445987
Snippet Aiming to solve the challenges of low detection accuracy, poor anti‐interference ability, and slow detection speed in the traditional tunnel lining defect...
SourceID proquest
crossref
wiley
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 762
SubjectTerms Accuracy
Defects
Inspection
Service tunnels
Tunnel linings
Title Automatic detection method of tunnel lining multi‐defects via an enhanced You Only Look Once network
URI https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fmice.12836
https://www.proquest.com/docview/2726037923
Volume 37
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVEBS
  databaseName: EBSCOhost Academic Search Ultimate
  customDbUrl: https://search.ebscohost.com/login.aspx?authtype=ip,shib&custid=s3936755&profile=ehost&defaultdb=asn
  eissn: 1467-8667
  dateEnd: 20241105
  omitProxy: true
  ssIdentifier: ssj0000443
  issn: 1093-9687
  databaseCode: ABDBF
  dateStart: 19980101
  isFulltext: true
  titleUrlDefault: https://search.ebscohost.com/direct.asp?db=asn
  providerName: EBSCOhost
– providerCode: PRVEBS
  databaseName: Inspec with Full Text
  customDbUrl:
  eissn: 1467-8667
  dateEnd: 20241105
  omitProxy: false
  ssIdentifier: ssj0000443
  issn: 1093-9687
  databaseCode: ADMLS
  dateStart: 19980101
  isFulltext: true
  titleUrlDefault: https://www.ebsco.com/products/research-databases/inspec-full-text
  providerName: EBSCOhost
– providerCode: PRVWIB
  databaseName: Wiley Online Library - Core collection (SURFmarket)
  issn: 1093-9687
  databaseCode: DR2
  dateStart: 19970101
  customDbUrl:
  isFulltext: true
  eissn: 1467-8667
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000443
  providerName: Wiley-Blackwell
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3LSsQwFL2IK134FscXAd0odOgkaToFNyKKiA8QBTdS8rhBceiI0xF05Sf4jX6JSdrqKCLoLoQ0tElOcm45ORdg08UUmFmBkXeDi3g3iR2klIko1x2TJhpNkPyfnIrDS350lVyNwU5zF6byh_j44eaREfZrD3CpBiMg99na2253Zd5vu8NEiKfOR7yjeK2uz1iUiW5ae5N6Gc_no19Po0-KOUpUw0lzMA3XzTtWApO79rBUbf38zb7xvx8xA1M1BSW71ZqZhTEs5mC6pqOkBvvAVTUZH5q6OZgcsS-cB7s7LPvB8pUYLIOmqyBVSmrSt6Qceg0N6YUUFCQoF99eXg0GAQl5vJVEFgSLm6BBIG7bIWdF74kcO9rvShpJUUnUF-DyYP9i7zCq8zZE2vu_RZmhJqUaqTCZYyucat1BgzJlaWriRDoGpLVQgkoXnJqYMR0naLsi41wZLi1bhPGiX-ASEBrbRAluFWbS9dORyJnk3DIVayvRtGCrmb9c16bmPrdGL2-CGz_CeRjhFmx8tL2vrDx-bLXaLIO8hvMgp6kL-5i3WmzBdpjPX3rIHX72Q2n5L41XYIL6qxVBTLkK4-XDENcc4SnVeljY73vh_gQ
linkProvider Wiley-Blackwell
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1da9swFL107cPWh7XrNpr1Y4LtZQMHR5Ll-LGUhLRNOhgt9M3I0hUbC05p7EL3tJ-w37hfUkmWG6-MwfYmhCywpCudK47OAXhvcwrMjMDIqcFFfJjENqQKHVGuBjpNFGpP-Z-di8klP71KrgI3x72FafQhHi7cXGT4_doFuLuQ7kS5s2vv2-2ViSewwYVNVBwm-txRj-KBX5-xKBPDNKiTOiLP6tvfz6MVyOxCVX_WjLcaQ9Wllyh0FJNv_boq-ur7IwHH__6NbXgeUCg5apbNC1jDcge2AiIlId6Xtqo1fWjrdmCzo2D4EsxRXS286ivRWHlaV0kaV2qyMKSqHY2GzL0LBfHkxV8_fmr0HBJy-1USWRIsv3gaArE7D_lUzu_I1CJ_W1JIyoal_goux6OL40kUrBsi5STgokxTnVKFVOjMAhZOlRqgRpmyNNVxIi0IUkoUgkqbn-qYMRUnaIYi47zQXBr2GtbLRYm7QGhskkJwU2AmbT8DiZxJzg0rYmUk6h58aCcwV0HX3NlrzPM2v3EjnPsR7sG7h7bXjZrHH1vtt-sgDxG9zGlqMz_m1BZ78NFP6F96yG0IjXzpzb80fgtPJxezaT49OT_bg2fUvbTw3Mp9WK9uajyw-KcqDv0qvwdc-wI0
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1dSxwxFL1UC6IPtX7hWlsD9UVhltkkk9l5FHWx9aMiCr4NmeQGS5fZxZ0V7JM_wd_YX2KSyehaRNC3EJLAJLnJucPJOQCbNqfAzAiMnBpcxLtJbEOq0BHlqqPTRKH2lP_jE3FwwX9eJpeBm-PewtT6EI8_3Fxk-PPaBTgOtZmIcmfX3rbHKxNT8JEnWdcx-vbOJtSjeODXZyzKRDcN6qSOyPPU9_l99AQyJ6Gqv2t687Wh6shLFDqKyZ_2uCra6u9_Ao7v_ozP8CmgULJTb5sF-IDlIswHREpCvI9sVWP60NQtwtyEguESmJ1xNfCqr0Rj5WldJaldqcnAkGrsaDSk710oiCcv_ru71-g5JOTmtySyJFheeRoCsScP-VX2b8mRRf62pJCUNUt9GS56--e7B1GwboiUk4CLMk11ShVSoTMLWDhVqoMaZcrSVMeJtCBIKVEIKm1-qmPGVJyg6YqM80JzadgKTJeDEleB0NgkheCmwEzacToSOZOcG1bEykjULdhqFjBXQdfc2Wv08ya_cTOc-xluwffHtsNazePFVuvNPshDRI9ymtrMjzm1xRZs-wV9ZYTchtC-L629pfEGzJzu9fKjHyeHX2CWuocWnlq5DtPV9Ri_WvhTFd_8Jn8AAp0BuA
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=Automatic+detection+method+of+tunnel+lining+multi%E2%80%90defects+via+an+enhanced+You+Only+Look+Once+network&rft.jtitle=Computer-aided+civil+and+infrastructure+engineering&rft.au=Zhou%2C+Zhong&rft.au=Zhang%2C+Junjie&rft.au=Gong%2C+Chenjie&rft.date=2022-05-01&rft.issn=1093-9687&rft.eissn=1467-8667&rft.volume=37&rft.issue=6&rft.spage=762&rft.epage=780&rft_id=info:doi/10.1111%2Fmice.12836&rft.externalDBID=n%2Fa&rft.externalDocID=10_1111_mice_12836
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1093-9687&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1093-9687&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1093-9687&client=summon