Edge Computing Driven Low-Light Image Dynamic Enhancement for Object Detection

With fast increase in volume of mobile multimedia data, how to apply powerful deep learning methods to process data with real-time response becomes a major issue. Meanwhile, edge computing structure helps improve response time and user experience by bringing flexible computation and storage capabili...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on network science and engineering Vol. 10; no. 5; pp. 3086 - 3098
Main Authors Wu, Yirui, Guo, Haifeng, Chakraborty, Chinmay, Khosravi, Mohammad R., Berretti, Stefano, Wan, Shaohua
Format Journal Article
LanguageEnglish
Published Piscataway IEEE 01.09.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Cloud computing
Computer networks
Edge computing
edge-driven deep learning method
Feature maps
Illumination
Image edge detection
Image enhancement
Light
Low-light image enhancement
Multimedia
Object detection
Object recognition
Performance evaluation
Response time (computers)
Task analysis
Time response
User experience
Online AccessGet full text

Cover

Abstract With fast increase in volume of mobile multimedia data, how to apply powerful deep learning methods to process data with real-time response becomes a major issue. Meanwhile, edge computing structure helps improve response time and user experience by bringing flexible computation and storage capabilities. Considering both technologies for successful AI-based applications, we propose an edge-computing driven and end-to-end framework to perform tasks of image enhancement and object detection under low-light conditions. The framework consists of a cloud-based enhancement and an edge-based detection stage. In the first stage, we establish connections between edge devices and cloud servers to input re-scaled illumination parts of low-light images, where enhancement subnetworks are dynamically and parallel coupled to compute enhanced illumination parts based on low-light context. During the edge-based detection stage, edge devices could accurately and rapidly detect objects based on cloud-computed informative feature map. Experimental results show the proposed method significantly improves detection performance in low-light conditions with low latency running on edge devices.
AbstractList With fast increase in volume of mobile multimedia data, how to apply powerful deep learning methods to process data with real-time response becomes a major issue. Meanwhile, edge computing structure helps improve response time and user experience by bringing flexible computation and storage capabilities. Considering both technologies for successful AI-based applications, we propose an edge-computing driven and end-to-end framework to perform tasks of image enhancement and object detection under low-light conditions. The framework consists of a cloud-based enhancement and an edge-based detection stage. In the first stage, we establish connections between edge devices and cloud servers to input re-scaled illumination parts of low-light images, where enhancement subnetworks are dynamically and parallel coupled to compute enhanced illumination parts based on low-light context. During the edge-based detection stage, edge devices could accurately and rapidly detect objects based on cloud-computed informative feature map. Experimental results show the proposed method significantly improves detection performance in low-light conditions with low latency running on edge devices.
Author Guo, Haifeng
Chakraborty, Chinmay
Wu, Yirui
Khosravi, Mohammad R.
Berretti, Stefano
Wan, Shaohua
Author_xml – sequence: 1
  givenname: Yirui
  orcidid: 0000-0003-3022-3718
  surname: Wu
  fullname: Wu, Yirui
  email: wuyirui@hhu.edu.cn
  organization: College of Computer and Information, Hohai University, Nanjing, China
– sequence: 2
  givenname: Haifeng
  surname: Guo
  fullname: Guo, Haifeng
  email: guo-haifeng@outlook.com
  organization: National Key Lab for Novel Software Technology, Nanjing University, Nanjing, China
– sequence: 3
  givenname: Chinmay
  orcidid: 0000-0002-4385-0975
  surname: Chakraborty
  fullname: Chakraborty, Chinmay
  email: cchakrabarty@bitmesra.ac.in
  organization: Department of Electronics and Communication Engineering, Birla Institute of Technology, Ranchi, India
– sequence: 4
  givenname: Mohammad R.
  orcidid: 0000-0002-2029-5067
  surname: Khosravi
  fullname: Khosravi, Mohammad R.
  email: m.r.khosravi.taut@gmail.com
  organization: Shiraz University of Technology, Shiraz, Iran
– sequence: 5
  givenname: Stefano
  orcidid: 0000-0003-1219-4386
  surname: Berretti
  fullname: Berretti, Stefano
  email: stefano.berretti@unifi.it
  organization: Department of Information Engineering (DINFO), University of Florence, Florence, Italy
– sequence: 6
  givenname: Shaohua
  orcidid: 0000-0001-7013-9081
  surname: Wan
  fullname: Wan, Shaohua
  email: shaohua.wan@ieee.org
  organization: Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen, China
BookMark eNp9kEtPAjEUhRujiYj8AOOmievBvubRpQFUkgksxMRd03Y6UMK02Cka_r0zgbhw4ercxfnuPffcgEvnnQHgDqMxxog_rhZvszFBhIwpTnGKyAUYEEpZQgn_uOxnkics4_k1GLXtFiGESZFRSgdgMavWBk58sz9E69ZwGuyXcbD030lp15sI543sDNOjk43VcOY20mnTGBdh7QNcqq3REU5N7MR6dwuuarlrzeisQ_D-PFtNXpNy-TKfPJWJpimPSSErU2FV4FwphpmuWM1rrlDVJUupTjXBKGOsKJCSGckLQ1PGsTKK1gWniNEheDjt3Qf_eTBtFFt_CK47KbrPMsYRS0nnyk8uHXzbBlMLbaPsc8Yg7U5gJPr-RN-f6PsT5_46Ev8h98E2Mhz_Ze5PjDXG_Pp5jhnCjP4AJ8h7oA
CODEN ITNSD5
CitedBy_id crossref_primary_10_1002_cpe_7664
crossref_primary_10_1049_ipr2_12772
crossref_primary_10_1109_JIOT_2022_3218150
crossref_primary_10_1109_TMM_2023_3318470
crossref_primary_10_3390_app13148509
crossref_primary_10_3390_app13126913
crossref_primary_10_1186_s13677_025_00726_z
crossref_primary_10_1016_j_jvcir_2024_104116
crossref_primary_10_1002_cpe_8232
crossref_primary_10_3390_s24030772
crossref_primary_10_1002_cpe_7142
crossref_primary_10_1145_3597210
crossref_primary_10_1007_s11265_023_01839_x
crossref_primary_10_1155_2023_8478457
crossref_primary_10_1007_s00530_023_01153_3
crossref_primary_10_1145_3561299
crossref_primary_10_1109_TII_2022_3173899
crossref_primary_10_1155_2023_4685563
crossref_primary_10_1007_s42979_024_02710_x
crossref_primary_10_1016_j_jpi_2023_100341
crossref_primary_10_1007_s00521_023_08645_3
crossref_primary_10_1007_s12065_023_00847_x
crossref_primary_10_3390_app13020852
crossref_primary_10_1109_TCE_2023_3318150
crossref_primary_10_3390_math10193679
crossref_primary_10_3390_app13084883
crossref_primary_10_1007_s42979_023_02145_w
crossref_primary_10_1049_ipr2_12785
crossref_primary_10_1109_TIM_2024_3350120
crossref_primary_10_3390_electronics13173527
crossref_primary_10_1109_TITS_2022_3178848
crossref_primary_10_1007_s11263_024_01995_y
crossref_primary_10_1109_TSC_2024_3377156
crossref_primary_10_3390_app122110939
crossref_primary_10_1109_TITS_2022_3157254
crossref_primary_10_1038_s41598_025_86860_9
crossref_primary_10_26599_TST_2023_9010008
crossref_primary_10_1038_s41598_022_20411_4
crossref_primary_10_1109_TNSM_2024_3436674
crossref_primary_10_1016_j_eswa_2024_124011
crossref_primary_10_1109_JSTARS_2024_3367713
crossref_primary_10_3390_s22155836
crossref_primary_10_3390_s22218416
crossref_primary_10_3390_app13169222
crossref_primary_10_1007_s40747_024_01681_z
crossref_primary_10_3390_electronics12030767
crossref_primary_10_1080_21681163_2023_2193649
crossref_primary_10_1080_21681163_2023_2228914
crossref_primary_10_3390_agriculture15050510
crossref_primary_10_1007_s42979_023_02066_8
crossref_primary_10_1109_TCSS_2022_3165559
crossref_primary_10_1007_s00530_023_01110_0
crossref_primary_10_1088_1361_6501_ad5f50
crossref_primary_10_1109_ACCESS_2025_3550947
crossref_primary_10_3389_fpls_2023_1102855
crossref_primary_10_1016_j_patrec_2022_12_020
crossref_primary_10_1109_TCC_2024_3525076
crossref_primary_10_1007_s13389_023_00343_z
crossref_primary_10_1109_ACCESS_2024_3450580
crossref_primary_10_3390_app13169211
crossref_primary_10_3390_s23020661
crossref_primary_10_3390_s24196330
crossref_primary_10_1080_17538947_2023_2239765
crossref_primary_10_1049_ipr2_13092
crossref_primary_10_1109_TMC_2024_3514214
crossref_primary_10_1186_s13677_022_00359_6
crossref_primary_10_1155_2022_4037053
crossref_primary_10_3389_fpsyg_2023_1155490
crossref_primary_10_1145_3591206
crossref_primary_10_1145_3587038
crossref_primary_10_1177_00405175241268771
crossref_primary_10_1007_s11042_024_19918_x
crossref_primary_10_3390_electronics13173383
crossref_primary_10_1155_2023_8984451
Cites_doi 10.1109/CVPR46437.2021.01042
10.1109/LGRS.2019.2919755
10.1023/B:VISI.0000013087.49260.fb
10.1007/978-3-319-10602-1_48
10.1109/tpami.2016.2577031
10.1109/TII.2020.2967768
10.1109/CVPR.2018.00347
10.1145/3072959.3073592
10.1155/2018/6235379
10.1109/ICCV.2017.324
10.1109/TPAMI.2018.2858826
10.1609/aaai.v34i07.7013
10.1109/CVPR.2016.91
10.1007/978-3-319-24574-4_28
10.1109/HPEC.2018.8547574
10.1109/ICCVW.2017.356
10.1109/ICCV.2017.244
10.1145/3318216.3363304
10.1016/j.cviu.2018.10.010
10.1109/CVPR.2018.00424
10.1109/TITS.2020.3025687
10.1109/jiot.2022.3143529
10.1007/978-3-642-15549-9_1
10.1109/tip.2021.3051462
10.1109/TII.2020.3001054
10.1145/3447993.3483274
10.1145/3430505
10.1109/TGRS.2020.3016820
10.1007/978-3-319-46448-0_2
10.1109/tits.2014.2345663
10.1109/TNET.2020.2983119
10.1109/TGRS.2020.3015157
10.1109/CVPR46437.2021.00493
10.1109/CVPR46437.2021.00871
10.1109/CVPRW.2019.00084
10.1109/CVPR46437.2021.00407
10.1109/SEC50012.2020.00016
10.1109/TGRS.2019.2897139
10.1016/j.patcog.2021.108146
10.1109/CVPRW.2017.151
10.1145/3447993.3448628
10.1007/s00521-019-04609-8
10.1145/3307334.3328589
10.1109/TII.2020.2987994
10.1109/CVPR42600.2020.01079
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/TNSE.2022.3151502
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005-present
IEEE All-Society Periodicals Package (ASPP) 1998-Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
DatabaseTitleList Computer and Information Systems Abstracts
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2334-329X
EndPage 3098
ExternalDocumentID 10_1109_TNSE_2022_3151502
9714014
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 62172438
  funderid: 10.13039/501100001809
– fundername: National Key R&D Program of China
  grantid: 2021YFB3900601
GroupedDBID 0R~
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABJNI
ABQJQ
ABVLG
AGQYO
AGSQL
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
IEDLZ
IFIPE
IPLJI
JAVBF
M43
OCL
PQQKQ
RIA
RIE
AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c359t-8aded1b817bb414cd4f9f9b0d00153c5c210644880ba6278e35491beb3f893043
IEDL.DBID RIE
ISSN 2327-4697
IngestDate Mon Jun 30 08:39:02 EDT 2025
Tue Jul 01 03:10:44 EDT 2025
Thu Apr 24 23:13:01 EDT 2025
Wed Aug 27 02:24:54 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 5
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 DirectLink
MergedId FETCHMERGED-LOGICAL-c359t-8aded1b817bb414cd4f9f9b0d00153c5c210644880ba6278e35491beb3f893043
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-4385-0975
0000-0001-7013-9081
0000-0003-3022-3718
0000-0002-2029-5067
0000-0003-1219-4386
PQID 2866490452
PQPubID 2040409
PageCount 13
ParticipantIDs crossref_citationtrail_10_1109_TNSE_2022_3151502
proquest_journals_2866490452
crossref_primary_10_1109_TNSE_2022_3151502
ieee_primary_9714014
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2023-09-01
PublicationDateYYYYMMDD 2023-09-01
PublicationDate_xml – month: 09
  year: 2023
  text: 2023-09-01
  day: 01
PublicationDecade 2020
PublicationPlace Piscataway
PublicationPlace_xml – name: Piscataway
PublicationTitle IEEE transactions on network science and engineering
PublicationTitleAbbrev TNSE
PublicationYear 2023
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref12
ref15
ref11
ref10
ref17
ref16
Wei (ref14) 2018
ref19
ref18
Tan (ref6) 2019; 97
Xu (ref3) 2021
ref46
ref45
ref48
ref47
ref42
ref41
ref44
ref43
ref49
ref8
ref7
ref9
ref5
ref40
ref35
ref34
ref37
ref36
ref31
ref30
ref33
ref32
ref2
ref1
ref39
ref38
ref24
ref23
ref26
ref25
ref20
ref22
ref21
ref28
ref27
ref29
Bhardwaj (ref4) 2020
References_xml – volume: 97
  start-page: 6105
  volume-title: Proc. Int. Conf. Mach. Learn.
  year: 2019
  ident: ref6
  article-title: EfficientNet: Rethinking model scaling for convolutional neural networks
– start-page: 155
  volume-title: Proc. Brit. Mach. Vis. Conf.
  year: 2018
  ident: ref14
  article-title: Deep retinex decomposition for low-light enhancement
– ident: ref17
  doi: 10.1109/CVPR46437.2021.01042
– ident: ref38
  doi: 10.1109/LGRS.2019.2919755
– ident: ref33
  doi: 10.1023/B:VISI.0000013087.49260.fb
– ident: ref44
  doi: 10.1007/978-3-319-10602-1_48
– ident: ref34
  doi: 10.1109/tpami.2016.2577031
– ident: ref21
  doi: 10.1109/TII.2020.2967768
– ident: ref15
  doi: 10.1109/CVPR.2018.00347
– ident: ref13
  doi: 10.1145/3072959.3073592
– ident: ref29
  doi: 10.1155/2018/6235379
– ident: ref46
  doi: 10.1109/ICCV.2017.324
– ident: ref41
  doi: 10.1109/TPAMI.2018.2858826
– ident: ref16
  doi: 10.1609/aaai.v34i07.7013
– ident: ref36
  doi: 10.1109/CVPR.2016.91
– ident: ref42
  doi: 10.1007/978-3-319-24574-4_28
– ident: ref9
  doi: 10.1109/HPEC.2018.8547574
– ident: ref12
  doi: 10.1109/ICCVW.2017.356
– ident: ref19
  doi: 10.1109/ICCV.2017.244
– ident: ref31
  doi: 10.1145/3318216.3363304
– ident: ref43
  doi: 10.1016/j.cviu.2018.10.010
– ident: ref45
  doi: 10.1109/CVPR.2018.00424
– ident: ref26
  doi: 10.1109/TITS.2020.3025687
– ident: ref23
  doi: 10.1109/jiot.2022.3143529
– ident: ref49
  doi: 10.1007/978-3-642-15549-9_1
– ident: ref20
  doi: 10.1109/tip.2021.3051462
– ident: ref25
  doi: 10.1109/TII.2020.3001054
– ident: ref8
  doi: 10.1145/3447993.3483274
– ident: ref28
  doi: 10.1145/3430505
– ident: ref39
  doi: 10.1109/TGRS.2020.3016820
– ident: ref35
  doi: 10.1007/978-3-319-46448-0_2
– ident: ref22
  doi: 10.1109/tits.2014.2345663
– ident: ref24
  doi: 10.1109/TNET.2020.2983119
– ident: ref40
  doi: 10.1109/TGRS.2020.3015157
– ident: ref18
  doi: 10.1109/CVPR46437.2021.00493
– ident: ref2
  doi: 10.1109/CVPR46437.2021.00871
– ident: ref10
  doi: 10.1109/CVPRW.2019.00084
– ident: ref1
  doi: 10.1109/CVPR46437.2021.00407
– ident: ref32
  doi: 10.1109/SEC50012.2020.00016
– ident: ref37
  doi: 10.1109/TGRS.2019.2897139
– ident: ref27
  doi: 10.1016/j.patcog.2021.108146
– ident: ref47
  doi: 10.1109/CVPRW.2017.151
– ident: ref11
  doi: 10.1145/3447993.3448628
– start-page: 459
  volume-title: Proc. USENIX Annu. Tech. Conf.
  year: 2021
  ident: ref3
  article-title: Video analytics with zero-streaming cameras
– year: 2020
  ident: ref4
  article-title: Ekya: Continuous learning of video analytics models on edge compute servers
– ident: ref48
  doi: 10.1007/s00521-019-04609-8
– ident: ref5
  doi: 10.1145/3307334.3328589
– ident: ref30
  doi: 10.1109/TII.2020.2987994
– ident: ref7
  doi: 10.1109/CVPR42600.2020.01079
SSID ssj0001286333
Score 2.5819845
Snippet With fast increase in volume of mobile multimedia data, how to apply powerful deep learning methods to process data with real-time response becomes a major...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 3086
SubjectTerms Cloud computing
Computer networks
Edge computing
edge-driven deep learning method
Feature maps
Illumination
Image edge detection
Image enhancement
Light
Low-light image enhancement
Multimedia
Object detection
Object recognition
Performance evaluation
Response time (computers)
Task analysis
Time response
User experience
Title Edge Computing Driven Low-Light Image Dynamic Enhancement for Object Detection
URI https://ieeexplore.ieee.org/document/9714014
https://www.proquest.com/docview/2866490452
Volume 10
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3dS8MwEA9zT_rg1xSnU_Lgk9itbdKvR3GTKdt8cIO9lSa5KqidzA7Bv967thtDRXwrJSEhd8nd73K5H2PnQvqORkNoge25ljSusFSA-zEACSZyUhAJhQaGI78_kXdTb1pjl6u3MABQJJ9Bmz6Lu3wz0wsKlXUiqi5HrNUbCNzKt1pr8ZTQF0JUF5eOHXXGo4ceAkDXRVyKVrsKnCxNT8Gl8uMALqzKzQ4bLudTJpM8txe5auvPb6Ua_zvhXbZduZf8qtSHPVaDbJ9trRUdbLBRzzwCL9kc8AfvzunA44PZhzUgpM5vX_GM4d2Sqp73sidSDBqIo4PL7xVFbngX8iKJKztgk5ve-LpvVawKlhZelFthYsA4KnQCpaQjtZFplEbKNuQ-Ce1pBIEE2kJbJb4bhCAQQjoKQXeKvo0txSGrZ7MMjhinJ-gGhPKS0Jd-ohSkElxAp0OjXQydJrOXCx7rquQ4MV-8xAX0sKOYZBSTjOJKRk12seryVtbb-Ktxg9Z81bBa7iZrLaUaVzvyPcap-jKiAvLHv_c6YZtEJV_mj7VYPZ8v4BQdjlydFZr2BX6P0Q0
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT8MwDLYQHIADb8R45sAJ0dE2adceERsasI0DQ-JWNYkLEtAh6ITEr8duuwkBQtyqKlGi2In9OY4_gEOpQs-QIXTQDXxHWV86ukX7sYUKbexlKFMODfQHYfdWXd4FdzNwPH0Lg4hl8hk2-bO8y7cjM-ZQ2UnM1eWYtXqO7H7gV6-1vkRUolBKWV9dem58MhzcdAgC-j4hU7LbdehkYnxKNpUfR3BpV86XoT-ZUZVO8tgcF7ppPr4Va_zvlFdgqXYwxWmlEaswg_kaLH4pO7gOg469R1HxOdAP0X7lI0_0Ru9Oj7G6uHimU0a0K7J60ckfWDV4IEEurrjWHLsRbSzKNK58A27PO8OzrlPzKjhGBnHhRKlF6-nIa2mtPGWsyuIs1q5lB0qawBAMZNgWuToN_VaEkkCkpwl2Z-TduEpuwmw-ynELBD9Ctyh1kEahClOtMVPoI7kdhixj5DXAnSx4Yuqi48x98ZSU4MONE5ZRwjJKahk14Gja5aWquPFX43Ve82nDerkbsDuRalLvybeEphqqmEvIb__e6wDmu8N-L-ldDK52YIGJ5atssl2YLV7HuEfuR6H3S637BJQd1Fc
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=Edge+Computing+Driven+Low-Light+Image+Dynamic+Enhancement+for+Object+Detection&rft.jtitle=IEEE+transactions+on+network+science+and+engineering&rft.au=Wu%2C+Yirui&rft.au=Guo%2C+Haifeng&rft.au=Chakraborty%2C+Chinmay&rft.au=Khosravi%2C+Mohammad+R.&rft.date=2023-09-01&rft.pub=IEEE&rft.eissn=2334-329X&rft.volume=10&rft.issue=5&rft.spage=3086&rft.epage=3098&rft_id=info:doi/10.1109%2FTNSE.2022.3151502&rft.externalDocID=9714014
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2327-4697&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2327-4697&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2327-4697&client=summon