Learning and Adapting Robust Features for Satellite Image Segmentation on Heterogeneous Data Sets
This paper addresses the problem of training a deep neural network for satellite image segmentation so that it can be deployed over images whose statistics differ from those used for training. For example, in postdisaster damage assessment, the tight time constraints make it impractical to train a n...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on geoscience and remote sensing Jg. 57; H. 9; S. 6517 - 6529 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
New York
IEEE
01.09.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Schlagworte: | |
| ISSN: | 0196-2892, 1558-0644 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | This paper addresses the problem of training a deep neural network for satellite image segmentation so that it can be deployed over images whose statistics differ from those used for training. For example, in postdisaster damage assessment, the tight time constraints make it impractical to train a network from scratch for each image to be segmented. We propose a convolutional encoder-decoder network able to learn visual representations of increasing semantic level as its depth increases, allowing it to generalize over a wider range of satellite images. Then, we propose two additional methods to improve the network performance over each specific image to be segmented. First, we observe that updating the batch normalization layers' statistics over the target image improves the network performance without human intervention. Second, we show that refining a trained network over a few samples of the image boosts the network performance with minimal human intervention. We evaluate our architecture over three data sets of satellite images, showing the state-of-the-art performance in binary segmentation of previously unseen images and competitive performance with respect to more complex techniques in a multiclass segmentation task. |
|---|---|
| AbstractList | This paper addresses the problem of training a deep neural network for satellite image segmentation so that it can be deployed over images whose statistics differ from those used for training. For example, in postdisaster damage assessment, the tight time constraints make it impractical to train a network from scratch for each image to be segmented. We propose a convolutional encoder-decoder network able to learn visual representations of increasing semantic level as its depth increases, allowing it to generalize over a wider range of satellite images. Then, we propose two additional methods to improve the network performance over each specific image to be segmented. First, we observe that updating the batch normalization layers' statistics over the target image improves the network performance without human intervention. Second, we show that refining a trained network over a few samples of the image boosts the network performance with minimal human intervention. We evaluate our architecture over three data sets of satellite images, showing the state-of-the-art performance in binary segmentation of previously unseen images and competitive performance with respect to more complex techniques in a multiclass segmentation task. |
| Author | Ghassemi, Sina Francini, Gianluca Fiandrotti, Attilio Magli, Enrico |
| Author_xml | – sequence: 1 givenname: Sina orcidid: 0000-0002-5046-3842 surname: Ghassemi fullname: Ghassemi, Sina email: sina.ghassemi@polito.it organization: Electronics and Telecommunication Department, Polytechnic University of Turin, Turin, Italy – sequence: 2 givenname: Attilio surname: Fiandrotti fullname: Fiandrotti, Attilio organization: Electronics and Telecommunication Department, Polytechnic University of Turin, Turin, Italy – sequence: 3 givenname: Gianluca orcidid: 0000-0002-2350-8849 surname: Francini fullname: Francini, Gianluca organization: Telecom Italia, Turin, Italy – sequence: 4 givenname: Enrico orcidid: 0000-0002-0901-0251 surname: Magli fullname: Magli, Enrico organization: Electronics and Telecommunication Department, Polytechnic University of Turin, Turin, Italy |
| BookMark | eNp9kU1rwzAMhs3oYG23HzB2Meyczh_58rF06wcUBm3vwYmVkJLane0c9u_nkLLDDgOBEHpeCb2aoYk2GhB6pmRBKRFvp83huGCEigUTJE1zcYemNEnyiKRxPEHT0Ekjlgv2gGbOnQmhcUKzKZJ7kFa3usFSK7xU8uqH4mDK3nm8Bul7Cw7XxuKj9NB1rQe8u8gG8BGaC2gvfWs0DrEFD9Y0oMH0Dr9LLwPi3SO6r2Xn4OmW5-i0_jitttH-c7NbLfdRxQT3Ea9kncQlxIxUlJacZJAlMuaU8nCNyAWAUCVnUuWKphVRdUVqkpSZUqLknM_R6zj2as1XD84XZ9NbHTYWjOUB4EkaByobqcoa5yzURdWOF3gr266gpBjsLAY7i8HO4mZnUNI_yqttL9J-_6t5GTUtAPzyeSp4eAr_AQktg0M |
| CODEN | IGRSD2 |
| CitedBy_id | crossref_primary_10_3390_aerospace10100880 crossref_primary_10_1049_ipr2_70017 crossref_primary_10_1007_s12530_025_09736_3 crossref_primary_10_3390_rs13040683 crossref_primary_10_1016_j_isprsjprs_2021_09_005 crossref_primary_10_1109_JSTARS_2021_3119001 crossref_primary_10_1016_j_ecoinf_2021_101370 crossref_primary_10_1109_TMI_2020_3024923 crossref_primary_10_1109_LGRS_2020_3010591 crossref_primary_10_1109_TNNLS_2020_3041646 crossref_primary_10_1109_TGRS_2020_3006161 crossref_primary_10_1016_j_isprsjprs_2020_07_001 crossref_primary_10_3390_ijgi9100601 crossref_primary_10_3390_rs14010190 crossref_primary_10_1109_TSC_2024_3470341 crossref_primary_10_1109_JSTARS_2021_3105421 crossref_primary_10_1007_s11277_020_07247_9 crossref_primary_10_1145_3746224 crossref_primary_10_1007_s11831_023_09939_4 crossref_primary_10_1016_j_isprsjprs_2022_08_012 crossref_primary_10_1016_j_isprsjprs_2023_01_018 crossref_primary_10_1109_JSTARS_2021_3053067 crossref_primary_10_1109_TGRS_2020_2980417 crossref_primary_10_1109_LGRS_2020_2982783 crossref_primary_10_1016_j_isprsjprs_2020_09_019 crossref_primary_10_1109_TGRS_2021_3105182 crossref_primary_10_1016_j_jvcir_2021_103141 crossref_primary_10_1109_ACCESS_2021_3078742 crossref_primary_10_1016_j_earscirev_2025_105070 crossref_primary_10_4018_IJIRR_289951 |
| Cites_doi | 10.1109/TGRS.2006.876704 10.1109/TGRS.2015.2503885 10.1109/CVPR.2016.350 10.1109/5.726791 10.1109/TGRS.2007.910220 10.1109/TPAMI.2012.231 10.1117/12.829645 10.1007/s11263-014-0733-5 10.1109/CVPR.2015.7298965 10.1109/TGRS.2015.2449736 10.1109/TGRS.2018.2868851 10.1109/JPROC.2012.2229082 10.23919/EUSIPCO.2018.8553545 10.1109/TGRS.2007.912445 10.1007/978-3-319-46487-9_32 10.1109/LGRS.2017.2691013 10.1109/IGARSS.2008.4778790 10.1109/IGARSS.2017.8127684 10.1109/CVPR.2016.90 10.1109/TPAMI.2017.2699184 10.1109/MGRS.2016.2548504 10.1109/TGRS.2004.831865 10.1109/JSTARS.2012.2202881 10.1109/TGRS.2009.2019636 10.1127/1432-8364/2010/0041 10.1109/IGARSS.2018.8518525 10.1109/JSTARS.2016.2582921 10.1109/JSTARS.2017.2711360 10.1109/TGRS.2016.2616585 10.1016/j.isprsjprs.2017.11.009 10.1109/TGRS.2016.2523563 10.1109/JSTARS.2011.2168195 10.1109/CVPR.2010.5539957 10.1109/TGRS.2011.2162339 10.1109/TGRS.2014.2377785 10.1109/CVPRW.2016.90 10.1109/CVPRW.2015.7301381 10.1109/CVPR.2015.7298594 10.1109/TGRS.2004.842478 10.1109/72.279181 10.1016/j.patcog.2014.12.016 10.3390/rs9050446 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019 |
| DBID | 97E RIA RIE AAYXX CITATION 7UA 8FD C1K F1W FR3 H8D H96 KR7 L.G L7M |
| DOI | 10.1109/TGRS.2019.2906689 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Water Resources Abstracts Technology Research Database Environmental Sciences and Pollution Management ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Aerospace Database Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Advanced Technologies Database with Aerospace |
| DatabaseTitle | CrossRef Aerospace Database Civil Engineering Abstracts Aquatic Science & Fisheries Abstracts (ASFA) Professional Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources Technology Research Database ASFA: Aquatic Sciences and Fisheries Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Water Resources Abstracts Environmental Sciences and Pollution Management |
| DatabaseTitleList | Aerospace Database |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Physics Statistics |
| EISSN | 1558-0644 |
| EndPage | 6529 |
| ExternalDocumentID | 10_1109_TGRS_2019_2906689 8693644 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: TIM |
| GroupedDBID | -~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AETIX AFRAH AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IBMZZ ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS RXW TAE TN5 VH1 Y6R AAYXX CITATION 7UA 8FD C1K F1W FR3 H8D H96 KR7 L.G L7M RIG |
| ID | FETCH-LOGICAL-c293t-3caf54be420c11b307e75a43113689989ee9db32ad8d16c0dfc0f05b7dd9b333 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 32 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000484209000019&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0196-2892 |
| IngestDate | Mon Jun 30 08:26:38 EDT 2025 Sat Nov 29 02:49:59 EST 2025 Tue Nov 18 20:45:18 EST 2025 Wed Aug 27 02:46:12 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 9 |
| 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-c293t-3caf54be420c11b307e75a43113689989ee9db32ad8d16c0dfc0f05b7dd9b333 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-0901-0251 0000-0002-2350-8849 0000-0002-5046-3842 |
| PQID | 2283333564 |
| PQPubID | 85465 |
| PageCount | 13 |
| ParticipantIDs | proquest_journals_2283333564 crossref_primary_10_1109_TGRS_2019_2906689 crossref_citationtrail_10_1109_TGRS_2019_2906689 ieee_primary_8693644 |
| PublicationCentury | 2000 |
| PublicationDate | 2019-09-01 |
| PublicationDateYYYYMMDD | 2019-09-01 |
| PublicationDate_xml | – month: 09 year: 2019 text: 2019-09-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE transactions on geoscience and remote sensing |
| PublicationTitleAbbrev | TGRS |
| PublicationYear | 2019 |
| 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 ref14 ref52 ref11 ref10 ref17 ref16 ref18 ref51 ref50 ganin (ref20) 2016; 17 ref46 ref45 ref48 ref42 ronneberger (ref25) 2015 ref44 ref43 nair (ref40) 2010 ref49 ref8 ref7 chen (ref47) 2018 ref4 ioffe (ref41) 2015; 37 ref3 ref6 krizhevsky (ref1) 2012 ref35 ref34 ref37 ref36 ref31 ref30 ref33 ref32 goodfellow (ref19) 2014 ref2 ref39 ref38 ref23 ref26 sugiyama (ref9) 2017 ref22 ref21 audebert (ref5) 2016 glorot (ref24) 2010 ref28 ref27 ref29 |
| References_xml | – ident: ref29 doi: 10.1109/TGRS.2006.876704 – ident: ref12 doi: 10.1109/TGRS.2015.2503885 – start-page: 807 year: 2010 ident: ref40 article-title: Rectified linear units improve restricted Boltzmann machines publication-title: Proc Int Conf Int Conf Mach Learn (ICML) – ident: ref46 doi: 10.1109/CVPR.2016.350 – ident: ref2 doi: 10.1109/5.726791 – ident: ref17 doi: 10.1109/TGRS.2007.910220 – ident: ref34 doi: 10.1109/TPAMI.2012.231 – ident: ref14 doi: 10.1117/12.829645 – ident: ref45 doi: 10.1007/s11263-014-0733-5 – ident: ref35 doi: 10.1109/CVPR.2015.7298965 – start-page: 1097 year: 2012 ident: ref1 article-title: Imagenet classification with deep convolutional neural networks publication-title: Proc Adv Neural Inf Process Syst – ident: ref16 doi: 10.1109/TGRS.2015.2449736 – ident: ref44 doi: 10.1109/TGRS.2018.2868851 – ident: ref30 doi: 10.1109/JPROC.2012.2229082 – ident: ref26 doi: 10.23919/EUSIPCO.2018.8553545 – ident: ref13 doi: 10.1109/TGRS.2007.912445 – ident: ref36 doi: 10.1007/978-3-319-46487-9_32 – ident: ref38 doi: 10.1109/LGRS.2017.2691013 – ident: ref43 doi: 10.1109/IGARSS.2008.4778790 – ident: ref48 doi: 10.1109/IGARSS.2017.8127684 – volume: 37 start-page: 448 year: 2015 ident: ref41 article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift publication-title: Proceedings of the 32nd Intl Conf on Machine Learning – start-page: 833 year: 2018 ident: ref47 article-title: Encoder-decoder with atrous separable convolution for semantic image segmentation publication-title: Proc Eur Conf Comput Vis – ident: ref22 doi: 10.1109/CVPR.2016.90 – ident: ref37 doi: 10.1109/TPAMI.2017.2699184 – start-page: 2672 year: 2014 ident: ref19 article-title: Generative adversarial nets publication-title: Proc Adv Neural Inf Process Syst – ident: ref10 doi: 10.1109/MGRS.2016.2548504 – year: 2017 ident: ref9 publication-title: Dataset Shift in Machine Learning – ident: ref33 doi: 10.1109/TGRS.2004.831865 – ident: ref18 doi: 10.1109/JSTARS.2012.2202881 – start-page: 180 year: 2016 ident: ref5 article-title: Semantic segmentation of earth observation data using multimodal and multi-scale deep networks publication-title: Proc Asian Conf Comput Vis – ident: ref11 doi: 10.1109/TGRS.2009.2019636 – ident: ref52 doi: 10.1127/1432-8364/2010/0041 – ident: ref49 doi: 10.1109/IGARSS.2018.8518525 – ident: ref8 doi: 10.1109/JSTARS.2016.2582921 – ident: ref21 doi: 10.1109/JSTARS.2017.2711360 – ident: ref4 doi: 10.1109/TGRS.2016.2616585 – ident: ref6 doi: 10.1016/j.isprsjprs.2017.11.009 – ident: ref7 doi: 10.1109/TGRS.2016.2523563 – volume: 17 start-page: 2030 year: 2016 ident: ref20 article-title: Domain-adversarial training of neural networks publication-title: J Mach Learn Res – ident: ref28 doi: 10.1109/JSTARS.2011.2168195 – ident: ref42 doi: 10.1109/CVPR.2010.5539957 – start-page: 249 year: 2010 ident: ref24 article-title: Understanding the difficulty of training deep feedforward neural networks publication-title: Proc 13th Int Conf Artif Intell Statist – ident: ref31 doi: 10.1109/TGRS.2011.2162339 – ident: ref15 doi: 10.1109/TGRS.2014.2377785 – ident: ref3 doi: 10.1109/CVPRW.2016.90 – ident: ref50 doi: 10.1109/CVPRW.2015.7301381 – ident: ref39 doi: 10.1109/CVPR.2015.7298594 – ident: ref27 doi: 10.1109/TGRS.2004.842478 – ident: ref23 doi: 10.1109/72.279181 – start-page: 234 year: 2015 ident: ref25 article-title: U-net: Convolutional networks for biomedical image segmentation publication-title: Proc Int Conf Med Image Comput Comput -Assist Intervent – ident: ref32 doi: 10.1016/j.patcog.2014.12.016 – ident: ref51 doi: 10.3390/rs9050446 |
| SSID | ssj0014517 |
| Score | 2.4511263 |
| Snippet | This paper addresses the problem of training a deep neural network for satellite image segmentation so that it can be deployed over images whose statistics... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 6517 |
| SubjectTerms | Artificial neural networks Coders Convolutional neural network (CNN) Damage assessment Datasets deep learning domain adaptation encoder–decoder architecture Human performance Image processing Image segmentation Neural networks satellite image segmentation Satellite imagery Spaceborne remote sensing Statistical methods Statistics Target recognition Training |
| Title | Learning and Adapting Robust Features for Satellite Image Segmentation on Heterogeneous Data Sets |
| URI | https://ieeexplore.ieee.org/document/8693644 https://www.proquest.com/docview/2283333564 |
| Volume | 57 |
| WOSCitedRecordID | wos000484209000019&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-0644 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014517 issn: 0196-2892 databaseCode: RIE dateStart: 19800101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9wwEB4tqJXgUFqgYgtFPvRUNeBHEq-PCArLZYV298At8mOCkEqCSNLfX9trVkhUSEQ55DCOony2Z8Yz8w3AD2-DM-pcmalaT7LccZkZzk1mneGSo_Y2iovNJuRsNrm9VTcj-LWuhUHEmHyGJ-ExxvJda4dwVHY6KZXw-nsDNqSUq1qtdcQgL1gqjS4z70TwFMFkVJ0ur-aLkMSlTgK3eRk6ur_QQbGpyqudOKqXy533fdhn-JTMSHK2wv0LjLDZhe0X5IK78DEmd9puD3QiUb0junHkzOnHkOtM5q0Zup4EI3DwTjfx5itZ6MjQ2SO5fvA7DVng3UOqTmqIv6che6b1kw7boSMXutdepO_2YXn5e3k-zVJrhcx6_d5nwuq6yA3mnFrGjF_oKAvtjQkmyuCBKUTljODaTRwrLXW1pTUtjHROGSHEV9hs2gYPgEhuHFOWY6D2ExS1slRbZ71rbZmoyzHQ539d2UQ7Hrpf_Kmi-0FVFeCpAjxVgmcMP9dDHlecG28J7wU81oIJijEcPQNapVXZVYHqx19FmX_7_6hD2ArvXuWQHcFm_zTgd_hg__b33dNxnHD_AEfG04A |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9wwEB5RaFU4UApUXR7Fh56qBvzIY31EvBYBq4rdA7fIjwlCggSRpL8f22tWSFSViHLIYaxE-WzPjGfmG4CfzgZn1No8kZUaJqnlRaI514mxmhcclbNRbGg2UYzHw5sb-WcBfs9rYRAxJJ_hvn8MsXzbmN4flR0Mcymc_v4AS1macjar1prHDNKMxeLoPHFuBI8xTEblwfTseuLTuOS-ZzfPfU_3V1ootFV5sxcHBXP65X2ftgar0ZAkhzPkv8IC1uuw8opecB0-hfRO026AijSqt0TVlhxa9eizncl1o_u2I94M7J3bTZwBSyYqcHR2SM4f3F5DJnj7EOuTauLukc-fady0w6ZvybHqlBPp2k2Ynp5Mj0ZJbK6QGKfhu0QYVWWpxpRTw5h2Sx2LTDlzgonc-2ASUVotuLJDy3JDbWVoRTNdWCu1EOIbLNZNjd-BFFxbJg1HT-4nKCppqDLWOOfaMFHlA6Av_7o0kXjc97-4L4MDQmXp4Sk9PGWEZwC_5kMeZ6wb_xPe8HjMBSMUA9h5AbSM67ItPdmPu7I83fr3qD34PJpeXZaX5-OLbVj275lllO3AYvfU4y58NH-7u_bpR5h8z2-m1sc |
| 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=Learning+and+Adapting+Robust+Features+for+Satellite+Image+Segmentation+on+Heterogeneous+Data+Sets&rft.jtitle=IEEE+transactions+on+geoscience+and+remote+sensing&rft.au=Ghassemi%2C+Sina&rft.au=Fiandrotti%2C+Attilio&rft.au=Francini%2C+Gianluca&rft.au=Magli%2C+Enrico&rft.date=2019-09-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0196-2892&rft.eissn=1558-0644&rft.volume=57&rft.issue=9&rft.spage=6517&rft_id=info:doi/10.1109%2FTGRS.2019.2906689&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0196-2892&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0196-2892&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0196-2892&client=summon |