Vehicular Trajectory Classification and Traffic Anomaly Detection in Videos Using a Hybrid CNN-VAE Architecture
Visual surveillance has become indispensable in the evolution of Intelligent Transportation Systems (ITS). Video object trajectories are key to many of the visual surveillance applications. Classifying varying length time series data such as video object trajectories using conventional neural networ...
Uložené v:
| Vydané v: | IEEE transactions on intelligent transportation systems Ročník 23; číslo 8; s. 11891 - 11902 |
|---|---|
| Hlavní autori: | , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
New York
IEEE
01.08.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Predmet: | |
| ISSN: | 1524-9050, 1558-0016 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Visual surveillance has become indispensable in the evolution of Intelligent Transportation Systems (ITS). Video object trajectories are key to many of the visual surveillance applications. Classifying varying length time series data such as video object trajectories using conventional neural networks, can be challenging. In this paper, we propose trajectory classification and anomaly detection using a hybrid Convolutional Neural Network (CNN) and Variational Autoencoder (VAE) architecture. First, we introduce a high level features for varying length object trajectories using color gradient representation. In the next stage, a semi-supervised way to annotate moving object trajectories extracted using Temporally Incremental Gravitational Model (TIGM) is used for class labeling. For training, anomalous trajectories are identified using t-Distributed Stochastic Neighbor Embedding (t-SNE). Finally, a hybrid CNN-VAE architecture has been proposed for trajectory classification and anomaly detection. The results obtained using publicly available surveillance video datasets reveal that the proposed method can successfully identify traffic anomalies such as violations in lane driving, sudden speed variations, abrupt termination of vehicle during movement, and vehicles moving in wrong directions. The accuracy of trajectory classification improves by a margin of 1-6% against popular neural networks-based classifiers across various datasets using the proposed high-level features. The gradient representation also improves the anomaly detection accuracy significantly (30-35%). Code and dataset can be found at https://github.com/santhoshkelathodi/CNN-VAE . |
|---|---|
| AbstractList | Visual surveillance has become indispensable in the evolution of Intelligent Transportation Systems (ITS). Video object trajectories are key to many of the visual surveillance applications. Classifying varying length time series data such as video object trajectories using conventional neural networks, can be challenging. In this paper, we propose trajectory classification and anomaly detection using a hybrid Convolutional Neural Network (CNN) and Variational Autoencoder (VAE) architecture. First, we introduce a high level features for varying length object trajectories using color gradient representation. In the next stage, a semi-supervised way to annotate moving object trajectories extracted using Temporally Incremental Gravitational Model (TIGM) is used for class labeling. For training, anomalous trajectories are identified using t-Distributed Stochastic Neighbor Embedding (t-SNE). Finally, a hybrid CNN-VAE architecture has been proposed for trajectory classification and anomaly detection. The results obtained using publicly available surveillance video datasets reveal that the proposed method can successfully identify traffic anomalies such as violations in lane driving, sudden speed variations, abrupt termination of vehicle during movement, and vehicles moving in wrong directions. The accuracy of trajectory classification improves by a margin of 1-6% against popular neural networks-based classifiers across various datasets using the proposed high-level features. The gradient representation also improves the anomaly detection accuracy significantly (30-35%). Code and dataset can be found at https://github.com/santhoshkelathodi/CNN-VAE . |
| Author | Kumaran Santhosh, Kelathodi Dogra, Debi Prosad Mitra, Adway Roy, Partha Pratim |
| Author_xml | – sequence: 1 givenname: Kelathodi orcidid: 0000-0002-8100-8244 surname: Kumaran Santhosh fullname: Kumaran Santhosh, Kelathodi email: sk47@iitbbs.ac.in organization: School of Electrical Sciences, Indian Institute of Technology Bhubaneswar, Odisha, India – sequence: 2 givenname: Debi Prosad orcidid: 0000-0002-3904-732X surname: Dogra fullname: Dogra, Debi Prosad email: dpdogra@iitbbs.ac.in, adway@iitbbs.ac.in organization: School of Electrical Sciences, Indian Institute of Technology Bhubaneswar, Odisha, India – sequence: 3 givenname: Partha Pratim orcidid: 0000-0002-5735-5254 surname: Roy fullname: Roy, Partha Pratim email: proy.fcs@iitr.ac.in organization: Department of Computer Science and Engineering, Indian Institute of Technology, Roorkee, India – sequence: 4 givenname: Adway surname: Mitra fullname: Mitra, Adway email: adway@cai.iitkgp.ac.in organization: Centre of Excellence in Artificial Intelligence (AI), Indian Institute of Technology Kharagpur, Kharagpur, India |
| BookMark | eNp9kD9PwzAQxS1UJNrCB0AslphTfLGdP2NVCq2EykDbNXKcC3WVxsVOh3x7EloxMDDd6d7v3eneiAxqWyMh98AmACx9Wi_XH5OQhTDhwBLJxBUZgpRJwBhEg74PRZAyyW7IyPt9NxUSYEjsFndGnyrl6NqpPerGupbOKuW9KY1WjbE1VXXRq2U3oNPaHlTV0mdsOrhXTU23pkDr6cab-pMqumhzZwo6W62C7XROp07vTE-fHN6S61JVHu8udUw2L_P1bBG8vb8uZ9O3QIcpbwLQWhe84CJPQEHOsVTASpGnotRCQByLImEMUy6hSBlijmHUfSe0TPIkVJKPyeN579HZrxP6Jtvbk6u7k1kYMyYgkhF0VHymtLPeOywzbZqfnxunTJUBy_p0sz7drE83u6TbOeGP8-jMQbn2X8_D2WMQ8ZdPJQcZxfwbI-yHjg |
| CODEN | ITISFG |
| CitedBy_id | crossref_primary_10_3390_vehicles7030063 crossref_primary_10_3390_ijgi11090487 crossref_primary_10_1038_s41598_025_90118_9 crossref_primary_10_1007_s42979_024_02945_8 crossref_primary_10_1016_j_cose_2024_104130 crossref_primary_10_1109_TITS_2024_3421623 crossref_primary_10_1109_TITS_2024_3438263 crossref_primary_10_1007_s11760_025_04798_x crossref_primary_10_1145_3760525 crossref_primary_10_1016_j_iot_2024_101268 crossref_primary_10_7717_peerj_cs_1799 crossref_primary_10_1016_j_iot_2025_101561 crossref_primary_10_1109_TCE_2024_3523565 crossref_primary_10_3390_math11132910 crossref_primary_10_3390_machines12050309 crossref_primary_10_1016_j_jmsy_2024_10_016 crossref_primary_10_1016_j_knosys_2023_111313 crossref_primary_10_1016_j_neucom_2025_130516 crossref_primary_10_1016_j_array_2025_100471 crossref_primary_10_1016_j_autcon_2024_105332 crossref_primary_10_1016_j_rineng_2023_101026 crossref_primary_10_1109_ACCESS_2024_3422098 crossref_primary_10_1109_TITS_2023_3341457 crossref_primary_10_1109_JIOT_2024_3360294 crossref_primary_10_1049_itr2_12591 crossref_primary_10_1007_s11760_025_04002_0 crossref_primary_10_1109_TITS_2023_3290827 crossref_primary_10_1016_j_engappai_2024_108684 crossref_primary_10_1145_3719290 crossref_primary_10_1016_j_cja_2022_10_010 crossref_primary_10_1109_TCSVT_2023_3307655 crossref_primary_10_1016_j_trc_2025_105145 crossref_primary_10_1109_TITS_2024_3457569 crossref_primary_10_1016_j_knosys_2024_111387 crossref_primary_10_32604_cmes_2023_047065 crossref_primary_10_1109_TITS_2022_3209903 |
| Cites_doi | 10.3390/s16010115 10.1109/TMM.2017.2666540 10.1109/ITSC.2016.7795922 10.1109/CVPR.2015.7298878 10.1109/TCYB.2019.2931139 10.1109/TCYB.2018.2838668 10.1145/2499621 10.1145/2733373.2806222 10.1007/s41060-016-0014-1 10.1109/ICC.2018.8422402 10.1109/ICMLA.2018.00207 10.1109/TITS.2014.2340701 10.1109/TPAMI.2012.59 10.1109/CISP-BMEI.2016.7852681 10.1109/TITS.2018.2835308 10.1145/3417989 10.1109/ICASSP.2013.6639345 10.1007/978-3-319-10590-1_53 10.1109/ITSC.2017.8317618 10.1109/CVPR.2015.7299178 10.1145/1390156.1390290 10.1109/TPAMI.2017.2691769 10.1109/ACPR.2015.7486592 10.1109/CVPR.2011.5995407 10.1145/3097983.3098052 10.1109/ICCV.2013.338 10.1109/CVPR.2019.00895 10.1145/882082.882086 10.1109/CVPR.2015.7299101 10.1109/CVPR.2011.5995733 10.1109/ICCV.2015.492 10.1109/TITS.2018.2834958 10.1007/978-3-319-59081-3_23 10.1162/neco.1997.9.8.1735 10.1109/CVPR.2013.392 10.1007/s10479-011-0841-3 10.1609/aaai.v33i01.33019428 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022 |
| DBID | 97E RIA RIE AAYXX CITATION 7SC 7SP 8FD FR3 JQ2 KR7 L7M L~C L~D |
| DOI | 10.1109/TITS.2021.3108504 |
| 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 Electronics & Communications 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 Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Civil Engineering Abstracts |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE/IET Electronic Library (IEL) (UW System Shared) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1558-0016 |
| EndPage | 11902 |
| ExternalDocumentID | 10_1109_TITS_2021_3108504 9531567 |
| Genre | orig-research |
| GroupedDBID | -~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AETIX AGQYO AGSQL AHBIQ AIBXA AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P PQQKQ RIA RIE RNS ZY4 AAYXX CITATION 7SC 7SP 8FD FR3 JQ2 KR7 L7M L~C L~D |
| ID | FETCH-LOGICAL-c293t-1cccd3d34b81a1b3efa10f4b94fc441774d800e9351d90eebe269054c58b82a53 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 50 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000732310700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1524-9050 |
| IngestDate | Mon Jun 30 04:16:48 EDT 2025 Tue Nov 18 22:11:51 EST 2025 Sat Nov 29 06:34:58 EST 2025 Wed Aug 27 02:23:34 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 8 |
| 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-1cccd3d34b81a1b3efa10f4b94fc441774d800e9351d90eebe269054c58b82a53 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-8100-8244 0000-0002-5735-5254 0000-0002-3904-732X |
| PQID | 2700416561 |
| PQPubID | 75735 |
| PageCount | 12 |
| ParticipantIDs | crossref_citationtrail_10_1109_TITS_2021_3108504 ieee_primary_9531567 proquest_journals_2700416561 crossref_primary_10_1109_TITS_2021_3108504 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-08-01 |
| PublicationDateYYYYMMDD | 2022-08-01 |
| PublicationDate_xml | – month: 08 year: 2022 text: 2022-08-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE transactions on intelligent transportation systems |
| PublicationTitleAbbrev | TITS |
| PublicationYear | 2022 |
| 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 | Loy (ref7) ref13 ref35 ref34 ref15 ref37 ref14 ref36 ref31 ref33 ref10 ref32 ref2 Kingma (ref39) ref1 Hammerla (ref5) 2016 Goodfellow (ref38) 2016; 1 ref17 ref16 ref19 Plötz (ref11) ref18 Zimmerer (ref30) 2018 ref24 ref46 ref23 ref45 ref26 ref25 ref20 Kingma (ref40) ref42 ref41 ref22 ref44 ref21 ref43 ref28 ref27 ref29 ref8 ref9 ref4 Yang (ref3) ref6 Krizhevsky (ref12) |
| References_xml | – ident: ref43 doi: 10.3390/s16010115 – ident: ref21 doi: 10.1109/TMM.2017.2666540 – ident: ref4 doi: 10.1109/ITSC.2016.7795922 – ident: ref19 doi: 10.1109/CVPR.2015.7298878 – ident: ref35 doi: 10.1109/TCYB.2019.2931139 – ident: ref32 doi: 10.1109/TCYB.2018.2838668 – start-page: 2672 volume-title: Proc. ICLR ident: ref40 article-title: Auto-encoding variational Bayes – ident: ref8 doi: 10.1145/2499621 – ident: ref20 doi: 10.1145/2733373.2806222 – ident: ref22 doi: 10.1007/s41060-016-0014-1 – ident: ref29 doi: 10.1109/ICC.2018.8422402 – ident: ref31 doi: 10.1109/ICMLA.2018.00207 – ident: ref1 doi: 10.1109/TITS.2014.2340701 – year: 2016 ident: ref5 article-title: Deep, convolutional, and recurrent models for human activity recognition using wearables publication-title: arXiv:1604.08880 – ident: ref14 doi: 10.1109/TPAMI.2012.59 – ident: ref36 doi: 10.1109/CISP-BMEI.2016.7852681 – ident: ref2 doi: 10.1109/TITS.2018.2835308 – ident: ref6 doi: 10.1145/3417989 – ident: ref15 doi: 10.1109/ICASSP.2013.6639345 – ident: ref13 doi: 10.1007/978-3-319-10590-1_53 – ident: ref16 doi: 10.1109/ITSC.2017.8317618 – ident: ref25 doi: 10.1109/CVPR.2015.7299178 – start-page: 1 volume-title: Proc. NIPS ident: ref12 article-title: ImageNet classification with deep convolutional neural networks – ident: ref10 doi: 10.1145/1390156.1390290 – ident: ref26 doi: 10.1109/TPAMI.2017.2691769 – ident: ref33 doi: 10.1109/ACPR.2015.7486592 – ident: ref23 doi: 10.1109/CVPR.2011.5995407 – ident: ref28 doi: 10.1145/3097983.3098052 – volume: 1 volume-title: Deep Learning year: 2016 ident: ref38 – year: 2018 ident: ref30 article-title: Context-encoding variational autoencoder for unsupervised anomaly detection publication-title: arXiv:1812.05941 – ident: ref44 doi: 10.1109/ICCV.2013.338 – ident: ref24 doi: 10.1109/CVPR.2019.00895 – start-page: 600 volume-title: Proc. ICLR ident: ref39 article-title: Adam: A method for stochastic optimization – ident: ref9 doi: 10.1145/882082.882086 – volume-title: Proc. ECCV ident: ref7 article-title: From local temporal correlation to global anomaly detection – start-page: 3995 volume-title: Proc. IJCAI ident: ref3 article-title: Deep convolutional neural networks on multichannel time series for human activity recognition – ident: ref18 doi: 10.1109/CVPR.2015.7299101 – ident: ref42 doi: 10.1109/CVPR.2011.5995733 – ident: ref41 doi: 10.1109/ICCV.2015.492 – ident: ref34 doi: 10.1109/TITS.2018.2834958 – start-page: 1729 volume-title: Proc. IJCAI ident: ref11 article-title: Feature learning for activity recognition in ubiquitous computing – ident: ref45 doi: 10.1007/978-3-319-59081-3_23 – ident: ref17 doi: 10.1162/neco.1997.9.8.1735 – ident: ref46 doi: 10.1109/CVPR.2013.392 – ident: ref37 doi: 10.1007/s10479-011-0841-3 – ident: ref27 doi: 10.1609/aaai.v33i01.33019428 |
| SSID | ssj0014511 |
| Score | 2.571297 |
| Snippet | Visual surveillance has become indispensable in the evolution of Intelligent Transportation Systems (ITS). Video object trajectories are key to many of the... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 11891 |
| SubjectTerms | Anomalies Anomaly detection Artificial neural networks Classification Convolutional neural network Convolutional neural networks Datasets deep learning Dirichlet process mixture model Feature extraction Image color analysis Intelligent transportation systems Movement Moving object recognition Neural networks Representations Surveillance traffic anomaly detection Traffic speed Training data Trajectories Trajectory trajectory classification Transportation networks variational autoencoder Videos visual surveillance |
| Title | Vehicular Trajectory Classification and Traffic Anomaly Detection in Videos Using a Hybrid CNN-VAE Architecture |
| URI | https://ieeexplore.ieee.org/document/9531567 https://www.proquest.com/docview/2700416561 |
| Volume | 23 |
| WOSCitedRecordID | wos000732310700001&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/IET Electronic Library (IEL) (UW System Shared) customDbUrl: eissn: 1558-0016 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014511 issn: 1524-9050 databaseCode: RIE dateStart: 20000101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT9wwEB0B6gEOpRRQF2jlA6eqhvhrEx9XFASXVSW2K26RY0_EIkgqdqm0_x6PN7sCgSr1Fil2FOVNPB7PmzcAx4pkxaIlcBnXPq6tC9wVWHD0daaMkzLPQmo2kQ-Hxc2N_bUGP1a1MIiYyGd4Qpcplx9a_0RHZac2Gozp5-uwnuf9Ra3WKmNAOltJG1VqbjOzzGCKzJ6OrkbXMRKUIgaopNCmX_mg1FTlzUqc3MvF9v-92Cf42G0j2WCB-w6sYfMZtl6IC-5CO8bbSWKZsuiQ7tLp_JylJphED0qIMNcEuks6EmzQtA_ufs5-4izxsxo2adh4ErCdssQsYI5dzqnCi50Nh3w8OGeDF2mIPfh9cT46u-RdewXuo4-fceG9DyooXRXCiUph7URW68rq2lNjslyHuJtEq4wINsOItoyhtNHeFFUhnVH7sNG0DX4B5lRl-lWuC4FOV74uVHyOrFGGGpVwpgfZ8oOXvtMepxYY92WKQTJbEkYlYVR2GPXg-2rKn4Xwxr8G7xIoq4EdHj04WqJadr_mtKRMuybNIXHw_qxD2JRU45BYfkewMXt8wq_wwf-dTaaP35LVPQM5BtSb |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fa9RAEB5qFdQHf1XxtOo--CSu3Z9N9vGoLVesQfA8-hY2uxM8qYn0rsL99-7s5Y6KIvgWyG4I-SY7OzvffAPwWpOsWLIErtLax43zkfsSS46hFdp6pQoRc7OJoqrK83P3aQfebmthEDGTz_AdXeZcfuzDFR2VHbhkMPawuAE3rTFKrKu1tjkDUtrK6qjKcCfsJocphTuYnk4_p1hQyRSikkab-c0L5bYqf6zF2cGc3P-_V3sA94aNJBuvkX8IO9g9grvX5AX3oJ_h13nmmbLkkr7l8_kVy20wiSCUMWG-i3SXlCTYuOu_-4sVe4_LzNDq2Lxjs3nEfsEyt4B5NllRjRc7qio-Gx-z8bVExGP4cnI8PZrwocECD8nLL7kMIUQdtWlK6WWjsfVStKZxpg3UmqwwMe0n0WkroxOY8FYpmLYm2LIplbf6Cex2fYdPgXnd2MOmMKVEb5rQljo9R7WoYotaejsCsfngdRjUx6kJxkWdoxDhasKoJozqAaMRvNlO-bGW3vjX4D0CZTtwwGME-xtU6-HnXNSUazekOiSf_X3WK7g9mX48q89Oqw_P4Y6iiofM-duH3eXlFb6AW-Hncr64fJkt8Bdu2dfi |
| 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=Vehicular+Trajectory+Classification+and+Traffic+Anomaly+Detection+in+Videos+Using+a+Hybrid+CNN-VAE+Architecture&rft.jtitle=IEEE+transactions+on+intelligent+transportation+systems&rft.au=Kumaran+Santhosh%2C+Kelathodi&rft.au=Dogra%2C+Debi+Prosad&rft.au=Roy%2C+Partha+Pratim&rft.au=Mitra%2C+Adway&rft.date=2022-08-01&rft.issn=1524-9050&rft.eissn=1558-0016&rft.volume=23&rft.issue=8&rft.spage=11891&rft.epage=11902&rft_id=info:doi/10.1109%2FTITS.2021.3108504&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TITS_2021_3108504 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1524-9050&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1524-9050&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1524-9050&client=summon |