Vessel Trajectory Anomaly Detection Based on Multi-scale Convolutional Autoencoder

Traditional methods for detecting anomalies in vessel trajectories do not adequately account for the multidimensional characteristics of vessel behavior, and lack the ability to capture trajectory details. To address these issues, a method of vessel trajectory anomaly detection based on Multi-scale...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Ocean engineering Ročník 343; s. 123564
Hlavní autoři: Qi, Yuhao, Yang, Jiaxuan, Xu, Dongsheng, Shao, Ran, Duan, Yangyang, Wang, Yangjie
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 15.01.2026
Témata:
ISSN:0029-8018
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Traditional methods for detecting anomalies in vessel trajectories do not adequately account for the multidimensional characteristics of vessel behavior, and lack the ability to capture trajectory details. To address these issues, a method of vessel trajectory anomaly detection based on Multi-scale Convolutional Autoencoder (MCAE) is proposed, which fully leverages the multidimensional behavioral features of vessels to enhance the precision of anomaly detection. Firstly, a mechanism for generating multidimensional features information trajectory maps is presented. Secondly, an MCAE model capable of effectively capturing trajectory details is constructed. Building upon the autoencoder, local and global features of trajectory maps at various resolutions are extracted through multi-scale convolution and fused into intermediate decoder layers by skip connections, achieving an enhanced ability to capture trajectory details. Finally, an algorithm of vessel trajectory anomaly detection based on MCAE is proposed. The Structural Similarity Index Measure (SSIM) is applied to calculate anomaly scores for maps reconstructed by the model, and a threshold is set to achieve the anomaly detection of vessel trajectories. The Port of Tianjin is used as the study area, and experimental results demonstrate that the proposed method effectively detects anomaly vessel trajectories, closely matching actual conditions. Compared to other methods, it shows superior reconstruction accuracy and detection precision, offering robust support for port security management and maritime traffic safety. •A mechanism for generating multidimensional features trajectory maps is presented.•An MCAE model capable of effectively capturing trajectory details is constructed.•An algorithm of vessel trajectory anomaly detection based on MCAE is proposed.•The proposed method is verified through real case analysis and model comparison.
AbstractList Traditional methods for detecting anomalies in vessel trajectories do not adequately account for the multidimensional characteristics of vessel behavior, and lack the ability to capture trajectory details. To address these issues, a method of vessel trajectory anomaly detection based on Multi-scale Convolutional Autoencoder (MCAE) is proposed, which fully leverages the multidimensional behavioral features of vessels to enhance the precision of anomaly detection. Firstly, a mechanism for generating multidimensional features information trajectory maps is presented. Secondly, an MCAE model capable of effectively capturing trajectory details is constructed. Building upon the autoencoder, local and global features of trajectory maps at various resolutions are extracted through multi-scale convolution and fused into intermediate decoder layers by skip connections, achieving an enhanced ability to capture trajectory details. Finally, an algorithm of vessel trajectory anomaly detection based on MCAE is proposed. The Structural Similarity Index Measure (SSIM) is applied to calculate anomaly scores for maps reconstructed by the model, and a threshold is set to achieve the anomaly detection of vessel trajectories. The Port of Tianjin is used as the study area, and experimental results demonstrate that the proposed method effectively detects anomaly vessel trajectories, closely matching actual conditions. Compared to other methods, it shows superior reconstruction accuracy and detection precision, offering robust support for port security management and maritime traffic safety. •A mechanism for generating multidimensional features trajectory maps is presented.•An MCAE model capable of effectively capturing trajectory details is constructed.•An algorithm of vessel trajectory anomaly detection based on MCAE is proposed.•The proposed method is verified through real case analysis and model comparison.
ArticleNumber 123564
Author Xu, Dongsheng
Qi, Yuhao
Shao, Ran
Wang, Yangjie
Yang, Jiaxuan
Duan, Yangyang
Author_xml – sequence: 1
  givenname: Yuhao
  orcidid: 0000-0002-1026-4427
  surname: Qi
  fullname: Qi, Yuhao
  email: qiyuhao@dlmu.edu.cn
  organization: Navigation College, Dalian Maritime University, Dalian, 116026, China
– sequence: 2
  givenname: Jiaxuan
  orcidid: 0000-0002-0672-1330
  surname: Yang
  fullname: Yang, Jiaxuan
  email: yangjiaxuan@dlmu.edu.cn
  organization: Navigation College, Dalian Maritime University, Dalian, 116026, China
– sequence: 3
  givenname: Dongsheng
  orcidid: 0009-0002-2901-0352
  surname: Xu
  fullname: Xu, Dongsheng
  email: xds2121@dlmu.edu.cn
  organization: Navigation College, Dalian Maritime University, Dalian, 116026, China
– sequence: 4
  givenname: Ran
  orcidid: 0009-0002-5438-0857
  surname: Shao
  fullname: Shao, Ran
  email: 851000166@qq.com
  organization: Navigation College, Dalian Maritime University, Dalian, 116026, China
– sequence: 5
  givenname: Yangyang
  surname: Duan
  fullname: Duan, Yangyang
  email: duanyy@dlmu.edu.cn
  organization: Navigation College, Dalian Maritime University, Dalian, 116026, China
– sequence: 6
  givenname: Yangjie
  surname: Wang
  fullname: Wang, Yangjie
  email: wangyangjie@dlmu.edu.cn
  organization: Navigation College, Dalian Maritime University, Dalian, 116026, China
BookMark eNqFkM1OwzAQhH0oEm3hFVBeIMFOYsu5UcqvBEJChau1sdfIkWsjO63UtydV4cxpV6uZ0ey3ILMQAxJyxWjFKBPXQxU1QsDwVdW05hWrGy7aGZlTWnelpEyek0XOA6VUCNrMyfsn5oy-2CQYUI8xHYpViFvwh-IOx-niYihuIaMppuV150dXZg0ei3UM--h3RwH4YrUbIwYdDaYLcmbBZ7z8nUvy8XC_WT-VL2-Pz-vVS6kZbduyBtvpVhioATrNOZjeNlZg2wDvGtZgq1uJQspe97wXVvadsZLpfpJwrrFZEnHK1SnmnNCq7-S2kA6KUXWkoQb1R0MdaagTjcl4czLi1G7vMKms3VQejUvTx8pE91_ED4M_cek
Cites_doi 10.1016/j.oceaneng.2024.119057
10.1016/j.knosys.2023.111313
10.1016/j.inffus.2024.102719
10.1016/j.patcog.2024.110917
10.1016/j.iot.2021.100436
10.1016/j.oceaneng.2024.119530
10.1016/j.eng.2025.02.018
10.1016/j.ijar.2013.03.012
10.1016/j.patrec.2022.09.011
10.1016/j.oceaneng.2023.116640
10.1016/j.compeleceng.2024.109654
10.1016/j.oceaneng.2024.119329
10.1016/j.eswa.2021.116087
10.1016/j.oceaneng.2023.113673
10.1016/j.neucom.2023.126920
10.1016/j.asoc.2023.111194
10.1016/j.engappai.2025.110006
10.1016/j.neucom.2021.04.089
10.1016/j.bspc.2024.106765
10.1109/TVT.2024.3382685
10.1016/j.oceaneng.2022.113099
10.1016/j.oceaneng.2023.116316
10.1016/j.ress.2024.110105
10.1016/j.compbiomed.2024.109204
10.1016/j.isatra.2021.02.030
10.1109/TITS.2022.3209903
10.1016/j.oceaneng.2023.116082
10.1016/j.engappai.2021.104652
10.3390/jmse13050849
10.1016/j.oceaneng.2023.114627
10.1016/j.apor.2024.103924
10.3390/su13158162
10.1016/j.oceaneng.2024.116766
10.3390/jmse11010056
10.1016/j.eswa.2023.120561
10.1016/j.artint.2024.104240
10.3390/jmse10010112
ContentType Journal Article
Copyright 2025 Elsevier Ltd
Copyright_xml – notice: 2025 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.oceaneng.2025.123564
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Oceanography
ExternalDocumentID 10_1016_j_oceaneng_2025_123564
S0029801825032469
GroupedDBID --K
--M
-~X
.DC
.~1
0R~
123
1B1
1~.
1~5
4.4
457
4G.
5VS
7-5
71M
8P~
9JM
9JN
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AATTM
AAXKI
AAXUO
AAYWO
ABFYP
ABJNI
ABLST
ABMAC
ACDAQ
ACGFS
ACLOT
ACRLP
ACVFH
ADBBV
ADCNI
ADEZE
ADTZH
AEBSH
AECPX
AEIPS
AEKER
AENEX
AEUPX
AFJKZ
AFPUW
AFTJW
AFXIZ
AGHFR
AGUBO
AGYEJ
AHEUO
AHHHB
AHJVU
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AKBMS
AKIFW
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
APXCP
AXJTR
BJAXD
BKOJK
BLECG
BLXMC
CS3
DU5
EBS
EFJIC
EFKBS
EFLBG
EO8
EO9
EP2
EP3
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
IHE
J1W
JJJVA
KCYFY
KOM
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
ROL
RPZ
SDF
SDG
SES
SEW
SPC
SPCBC
SSJ
SST
SSZ
T5K
TAE
TN5
XPP
ZMT
~02
~G-
~HD
29N
6TJ
9DU
AAQXK
AAYXX
ABFNM
ABWVN
ABXDB
ACKIV
ACNNM
ACRPL
ADMUD
ADNMO
AFFNX
AGQPQ
ASPBG
AVWKF
AZFZN
CITATION
EJD
FEDTE
FGOYB
G-2
HVGLF
HZ~
LY6
LY7
M41
R2-
SAC
SET
WUQ
ID FETCH-LOGICAL-c1044-2af9c46da2aa9c55adbf3f6e43a59313e4c48e688bcb5b6f8b9df81cb6e455ce3
ISSN 0029-8018
IngestDate Thu Nov 27 00:59:20 EST 2025
Sat Nov 29 17:05:16 EST 2025
IsPeerReviewed true
IsScholarly true
Keywords Multi-scale convolutional autoencoder
Vessel trajectory
Multidimensional features
Anomaly detection
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c1044-2af9c46da2aa9c55adbf3f6e43a59313e4c48e688bcb5b6f8b9df81cb6e455ce3
ORCID 0009-0002-2901-0352
0009-0002-5438-0857
0000-0002-1026-4427
0000-0002-0672-1330
ParticipantIDs crossref_primary_10_1016_j_oceaneng_2025_123564
elsevier_sciencedirect_doi_10_1016_j_oceaneng_2025_123564
PublicationCentury 2000
PublicationDate 2026-01-15
PublicationDateYYYYMMDD 2026-01-15
PublicationDate_xml – month: 01
  year: 2026
  text: 2026-01-15
  day: 15
PublicationDecade 2020
PublicationTitle Ocean engineering
PublicationYear 2026
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Sánchez Pedroche, García Herrero, Molina López (bib28) 2024; 563
Wolsing, Roepert, Bauer, Wehrle (bib37) 2022; 10
Chen, Chen, Chen, Song, Wang (bib2) 2023; 280
Toloue, Jahan (bib32) 2018
Zhu, Yu, Qi, Cong, Li, Li, Gao (bib47) 2024; 182
Ribeiro, Paes, Oliveira (bib26) 2023; 231
Xie, Bai, Xu, Xiao (bib38) 2024; 293
Tao, Gong, Zhang, Yan, Adak (bib31) 2022; 71
Schulze, Peppert, Schütte, Sunkara (bib29) 2025; 338
Yan, Wang (bib40) 2019
Xing, Wei, Zhang, Zhang (bib39) 2025; 157
Han, Armenakis, Jadidi (bib7) 2021; 13
Hu, Kaur, Lin, Wang, Hassan, Razzak, Hammoudeh (bib9) 2023; 24
Munia, Abdar, Hasan, Jalali, Banerjee, Khosravi, Hossain, Fu, Frangi (bib24) 2025; 115
Zhou, Liang, Zhang, Zhang, Song (bib46) 2021; 453
Karataş, Karagoz, Ayran (bib10) 2021; 16
Liu, Gan, Chen, Shu (bib20) 2023; 11
Nikolopoulos, Kalogeris, Papadopoulos (bib25) 2022; 109
Wang, Liu, Lin, Hu, Kaur, Hossain (bib35) 2023; 24
Zhang, Liu, Guo, Liu (bib44) 2023; 288
Wang, Wang, Peng, Chen (bib34) 2024; 120
Czaplewski, Dzwonkowski (bib3) 2022; 119
Li, Shang, Liu, Shen, Jin (bib15) 2024; 152
Liang, Weng, Gao, Li, Du (bib18) 2024; 284
Wang, Liu, Liu, Liu, Yuan (bib36) 2023; 271
Kong, Lin, Jiang, Shen (bib11) 2024; 73
Smith, Reece, Roberts, Rezek (bib30) 2012
Dong, Zhang, Wang, Guo, Deng, Li (bib4) 2025; 143
Guo, Qiang, Xie, Peng (bib6) 2024; 146
Du, Zhang, Guo, Zhou, Kan, Jia, Liang, Chen, Zhan (bib5) 2024; 98
Lin, Chen, Kuruoglu, Zhou (bib19) 2022; 163
Bakurov, Buzzelli, Schettini, Castelli, Vanneschi (bib1) 2022; 189
Van Loi, Kien, Hop, Van Khuong (bib33) 2020
Yang, Rey Castillo, Zou, Wotherspoon, Yang, Li (bib41) 2025; 51
Laxhammar, Falkman, Sviestins (bib13) 2009
Li, Li, Wang, Yang, Guan, Zhang (bib17) 2024; 313
Mascaro, Nicholso, Korb (bib23) 2014; 55
Hou, Zhou, Grifoll, Zhou, Liu, Ye, Zheng (bib8) 2025; 13
Ye, Chen, Zhang, Zhang, Liu (bib42) 2024; 312
Zhao, Qin, Bai, Yang (bib45) 2024
Liu, Liu, Li, Qi (bib22) 2022; 266
Zaman, Marijan, Kholodna (bib43) 2024; 312
Rong, Teixeira, Guedes Soares (bib27) 2024; 247
Lee, Park (bib14) 2024; 294
Liu, Jia, Li, Liu, Qi (bib21) 2023; 290
Laxhammar (bib12) 2008
Li (bib16) 2021
Schulze (10.1016/j.oceaneng.2025.123564_bib29) 2025; 338
Xie (10.1016/j.oceaneng.2025.123564_bib38) 2024; 293
Zhang (10.1016/j.oceaneng.2025.123564_bib44) 2023; 288
Zaman (10.1016/j.oceaneng.2025.123564_bib43) 2024; 312
Kong (10.1016/j.oceaneng.2025.123564_bib11) 2024; 73
Nikolopoulos (10.1016/j.oceaneng.2025.123564_bib25) 2022; 109
Li (10.1016/j.oceaneng.2025.123564_bib15) 2024; 152
Toloue (10.1016/j.oceaneng.2025.123564_bib32) 2018
Wolsing (10.1016/j.oceaneng.2025.123564_bib37) 2022; 10
Mascaro (10.1016/j.oceaneng.2025.123564_bib23) 2014; 55
Wang (10.1016/j.oceaneng.2025.123564_bib34) 2024; 120
Hou (10.1016/j.oceaneng.2025.123564_bib8) 2025; 13
Rong (10.1016/j.oceaneng.2025.123564_bib27) 2024; 247
Xing (10.1016/j.oceaneng.2025.123564_bib39) 2025; 157
Bakurov (10.1016/j.oceaneng.2025.123564_bib1) 2022; 189
Laxhammar (10.1016/j.oceaneng.2025.123564_bib12) 2008
Laxhammar (10.1016/j.oceaneng.2025.123564_bib13) 2009
Liu (10.1016/j.oceaneng.2025.123564_bib22) 2022; 266
Lin (10.1016/j.oceaneng.2025.123564_bib19) 2022; 163
Van Loi (10.1016/j.oceaneng.2025.123564_bib33) 2020
Yan (10.1016/j.oceaneng.2025.123564_bib40) 2019
Chen (10.1016/j.oceaneng.2025.123564_bib2) 2023; 280
Liang (10.1016/j.oceaneng.2025.123564_bib18) 2024; 284
Du (10.1016/j.oceaneng.2025.123564_bib5) 2024; 98
Smith (10.1016/j.oceaneng.2025.123564_bib30) 2012
Czaplewski (10.1016/j.oceaneng.2025.123564_bib3) 2022; 119
Liu (10.1016/j.oceaneng.2025.123564_bib21) 2023; 290
Zhu (10.1016/j.oceaneng.2025.123564_bib47) 2024; 182
Zhou (10.1016/j.oceaneng.2025.123564_bib46) 2021; 453
Yang (10.1016/j.oceaneng.2025.123564_bib41) 2025; 51
Ribeiro (10.1016/j.oceaneng.2025.123564_bib26) 2023; 231
Ye (10.1016/j.oceaneng.2025.123564_bib42) 2024; 312
Liu (10.1016/j.oceaneng.2025.123564_bib20) 2023; 11
Tao (10.1016/j.oceaneng.2025.123564_bib31) 2022; 71
Li (10.1016/j.oceaneng.2025.123564_bib16) 2021
Lee (10.1016/j.oceaneng.2025.123564_bib14) 2024; 294
Sánchez Pedroche (10.1016/j.oceaneng.2025.123564_bib28) 2024; 563
Guo (10.1016/j.oceaneng.2025.123564_bib6) 2024; 146
Wang (10.1016/j.oceaneng.2025.123564_bib35) 2023; 24
Wang (10.1016/j.oceaneng.2025.123564_bib36) 2023; 271
Hu (10.1016/j.oceaneng.2025.123564_bib9) 2023; 24
Zhao (10.1016/j.oceaneng.2025.123564_bib45) 2024
Karataş (10.1016/j.oceaneng.2025.123564_bib10) 2021; 16
Li (10.1016/j.oceaneng.2025.123564_bib17) 2024; 313
Dong (10.1016/j.oceaneng.2025.123564_bib4) 2025; 143
Han (10.1016/j.oceaneng.2025.123564_bib7) 2021; 13
Munia (10.1016/j.oceaneng.2025.123564_bib24) 2025; 115
References_xml – volume: 71
  start-page: 1
  year: 2022
  end-page: 21
  ident: bib31
  article-title: Deep learning for unsupervised Anomaly localization in industrial images: a survey
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 13
  start-page: 849
  year: 2025
  ident: bib8
  article-title: A Transformer–VAE approach for detecting ship trajectory anomalies in cross-sea bridge areas
  publication-title: J. Mar. Sci. Eng.
– start-page: 756
  year: 2009
  end-page: 763
  ident: bib13
  article-title: Anomaly detection in sea traffic-a comparison of the Gaussian mixture model and the kernel density estimator
  publication-title: 2009 12th International Conference on Information Fusion
– volume: 338
  year: 2025
  ident: bib29
  article-title: Chimeric U-Net – modifying the standard U-Net towards explainability
  publication-title: Artif. Intell.
– volume: 231
  year: 2023
  ident: bib26
  article-title: AIS-based maritime anomaly traffic detection: a review
  publication-title: Expert Syst. Appl.
– volume: 109
  year: 2022
  ident: bib25
  article-title: Non-intrusive surrogate modeling for parametrized time-dependent partial differential equations using convolutional autoencoders
  publication-title: Eng. Appl. Artif. Intell.
– volume: 563
  year: 2024
  ident: bib28
  article-title: Context learning from a ship trajectory cluster for anomaly detection
  publication-title: Neurocomputing
– volume: 120
  year: 2024
  ident: bib34
  article-title: MSA-Net: multi-scale feature fusion network with enhanced attention module for 3D medical image segmentation
  publication-title: Comput. Electr. Eng.
– volume: 312
  year: 2024
  ident: bib42
  article-title: An adaptive trajectory segmentation and simplification algorithm based on vessel behavioral features
  publication-title: Ocean Eng.
– volume: 119
  start-page: 1
  year: 2022
  end-page: 16
  ident: bib3
  article-title: A novel approach exploiting properties of convolutional neural networks for vessel movement anomaly detection and classification
  publication-title: ISA Transactions
– volume: 293
  year: 2024
  ident: bib38
  article-title: An anomaly detection method based on ship behavior trajectory
  publication-title: Ocean Eng.
– volume: 24
  start-page: 4631
  year: 2023
  end-page: 4640
  ident: bib35
  article-title: AI-Empowered trajectory anomaly detection for intelligent transportation systems: a hierarchical federated learning approach
  publication-title: IEEE Trans. Intell. Transport. Syst.
– volume: 290
  year: 2023
  ident: bib21
  article-title: The model of vessel trajectory abnormal behavior detection based on graph attention prediction and reconstruction network
  publication-title: Ocean Eng.
– volume: 24
  start-page: 2382
  year: 2023
  end-page: 2391
  ident: bib9
  article-title: Intelligent anomaly detection of trajectories for IoT empowered maritime transportation systems
  publication-title: IEEE Trans. Intell. Transport. Syst.
– start-page: 143
  year: 2020
  end-page: 147
  ident: bib33
  article-title: Abnormal moving speed detection using combination of kernel density estimator and DBSCAN for coastal surveillance radars
  publication-title: 2020 7th International Conference on Signal Processing and Integrated Networks (SPIN)
– start-page: 29
  year: 2019
  end-page: 37
  ident: bib40
  article-title: Study of data-driven Methods for Vessel Anomaly Detection Based on AIS Data, Smart Transportation Systems 2019
– start-page: 1709
  year: 2024
  end-page: 1713
  ident: bib45
  article-title: A CAE-based method for anomaly detection in ship trajectories
  publication-title: 2024 9th International Conference on Intelligent Computing and Signal Processing (ICSP)
– volume: 51
  start-page: 311
  year: 2025
  end-page: 326
  ident: bib41
  article-title: Automated concrete bridge damage detection using an efficient vision transformer-enhanced anchor-free YOLO
  publication-title: Engineering
– start-page: 645
  year: 2012
  end-page: 654
  ident: bib30
  article-title: Online maritime abnormality detection using gaussian processes and extreme value theory
  publication-title: 2012 IEEE 12th International Conference on Data Mining
– volume: 313
  year: 2024
  ident: bib17
  article-title: STAD: ship trajectory anomaly detection in ocean with dynamic pattern clustering
  publication-title: Ocean Eng.
– volume: 55
  start-page: 84
  year: 2014
  end-page: 98
  ident: bib23
  article-title: Anomaly detection in vessel tracks using Bayesian networks
  publication-title: Int. J. Approx. Reason.
– volume: 98
  year: 2024
  ident: bib5
  article-title: DERE-Net: a dual-encoder residual enhanced U-Net for muscle fiber segmentation of H&E images
  publication-title: Biomed. Signal Process Control
– volume: 10
  start-page: 112
  year: 2022
  ident: bib37
  article-title: Anomaly detection in maritime AIS tracks: a review of recent approaches
  publication-title: J. Mar. Sci. Eng.
– volume: 152
  year: 2024
  ident: bib15
  article-title: Inverse distance weighting and radial basis function based surrogate model for high-dimensional expensive multi-objective optimization
  publication-title: Appl. Soft Comput.
– volume: 294
  year: 2024
  ident: bib14
  article-title: Collision evasive action timing for MASS using CNN–LSTM-based ship trajectory prediction in restricted area
  publication-title: Ocean Eng.
– volume: 271
  year: 2023
  ident: bib36
  article-title: Data-driven methods for detection of abnormal ship behavior: progress and trends
  publication-title: Ocean Eng.
– volume: 73
  start-page: 9800
  year: 2024
  end-page: 9811
  ident: bib11
  article-title: Anomalous sub-trajectory detection with graph contrastive self-supervised learning
  publication-title: IEEE Trans. Veh. Technol.
– volume: 115
  year: 2025
  ident: bib24
  article-title: Attention-guided hierarchical fusion U-Net for uncertainty-driven medical image segmentation
  publication-title: Inf. Fusion
– volume: 247
  year: 2024
  ident: bib27
  article-title: A framework for ship abnormal behaviour detection and classification using AIS data
  publication-title: Reliab. Eng. Syst. Saf.
– volume: 16
  year: 2021
  ident: bib10
  article-title: Trajectory pattern extraction and anomaly detection for maritime vessels
  publication-title: Internet of Things
– volume: 182
  year: 2024
  ident: bib47
  article-title: Lightweight medical image segmentation network with multi-scale feature-guided fusion
  publication-title: Comput. Biol. Med.
– volume: 189
  year: 2022
  ident: bib1
  article-title: Structural similarity index (SSIM) revisited: a data-driven approach
  publication-title: Expert Syst. Appl.
– volume: 143
  year: 2025
  ident: bib4
  article-title: Inspection of cracking in stamping parts surfaces using anomaly detection
  publication-title: Eng. Appl. Artif. Intell.
– volume: 284
  year: 2024
  ident: bib18
  article-title: Unsupervised maritime anomaly detection for intelligent situational awareness using AIS data
  publication-title: Knowl. Base Syst.
– start-page: 1
  year: 2021
  end-page: 8
  ident: bib16
  article-title: Typical trajectory extraction method for ships based on ais data and trajectory clustering
  publication-title: 2021 2nd International Conference on Artificial Intelligence and Information Systems
– start-page: 1
  year: 2008
  end-page: 8
  ident: bib12
  article-title: Anomaly detection for sea surveillance
  publication-title: 2008 11th International Conference on Information Fusion
– volume: 163
  start-page: 10
  year: 2022
  end-page: 16
  ident: bib19
  article-title: Robust structural similarity index measure for images with Non-Gaussian distortions
  publication-title: Pattern Recognit. Lett.
– volume: 312
  year: 2024
  ident: bib43
  article-title: Online ornstein–uhlenbeck based anomaly detection and behavior classification using AIS data in maritime
  publication-title: Ocean Eng.
– volume: 288
  year: 2023
  ident: bib44
  article-title: A novel ship trajectory clustering analysis and anomaly detection method based on AIS data
  publication-title: Ocean Eng.
– volume: 13
  start-page: 8162
  year: 2021
  ident: bib7
  article-title: Modeling vessel behaviours by clustering ais data using optimized dbscan
  publication-title: Sustainability
– volume: 11
  start-page: 56
  year: 2023
  ident: bib20
  article-title: Research on fault early warning of marine diesel engine based on CNN-BiGRU
  publication-title: J. Mar. Sci. Eng.
– volume: 453
  start-page: 131
  year: 2021
  end-page: 140
  ident: bib46
  article-title: VAE-based deep SVDD for anomaly detection
  publication-title: Neurocomputing
– volume: 266
  year: 2022
  ident: bib22
  article-title: Research on detection mechanism of vessel abnormal behavior based on immune genetic spectral clustering algorithm
  publication-title: Ocean Eng.
– start-page: 10
  year: 2018
  end-page: 12
  ident: bib32
  article-title: Anomalous behavior detection of marine vessels based on hidden Markov model
  publication-title: 2018 6th Iranian Joint Congress on Fuzzy and Intelligent Systems (CFIS)
– volume: 146
  year: 2024
  ident: bib6
  article-title: Unsupervised knowledge discovery framework: from AIS data processing to maritime traffic networks generating
  publication-title: Appl. Ocean Res.
– volume: 280
  year: 2023
  ident: bib2
  article-title: Vessel sailing route extraction and analysis from satellite-based AIS data using density clustering and probability algorithms
  publication-title: Ocean Eng.
– volume: 157
  year: 2025
  ident: bib39
  article-title: Multi-scale feature extraction and fusion with attention interaction for RGB-T tracking
  publication-title: Pattern Recogn.
– volume: 312
  year: 2024
  ident: 10.1016/j.oceaneng.2025.123564_bib43
  article-title: Online ornstein–uhlenbeck based anomaly detection and behavior classification using AIS data in maritime
  publication-title: Ocean Eng.
  doi: 10.1016/j.oceaneng.2024.119057
– volume: 284
  year: 2024
  ident: 10.1016/j.oceaneng.2025.123564_bib18
  article-title: Unsupervised maritime anomaly detection for intelligent situational awareness using AIS data
  publication-title: Knowl. Base Syst.
  doi: 10.1016/j.knosys.2023.111313
– start-page: 1
  year: 2008
  ident: 10.1016/j.oceaneng.2025.123564_bib12
  article-title: Anomaly detection for sea surveillance
– volume: 115
  year: 2025
  ident: 10.1016/j.oceaneng.2025.123564_bib24
  article-title: Attention-guided hierarchical fusion U-Net for uncertainty-driven medical image segmentation
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2024.102719
– volume: 157
  year: 2025
  ident: 10.1016/j.oceaneng.2025.123564_bib39
  article-title: Multi-scale feature extraction and fusion with attention interaction for RGB-T tracking
  publication-title: Pattern Recogn.
  doi: 10.1016/j.patcog.2024.110917
– volume: 16
  year: 2021
  ident: 10.1016/j.oceaneng.2025.123564_bib10
  article-title: Trajectory pattern extraction and anomaly detection for maritime vessels
  publication-title: Internet of Things
  doi: 10.1016/j.iot.2021.100436
– volume: 313
  year: 2024
  ident: 10.1016/j.oceaneng.2025.123564_bib17
  article-title: STAD: ship trajectory anomaly detection in ocean with dynamic pattern clustering
  publication-title: Ocean Eng.
  doi: 10.1016/j.oceaneng.2024.119530
– volume: 51
  start-page: 311
  year: 2025
  ident: 10.1016/j.oceaneng.2025.123564_bib41
  article-title: Automated concrete bridge damage detection using an efficient vision transformer-enhanced anchor-free YOLO
  publication-title: Engineering
  doi: 10.1016/j.eng.2025.02.018
– start-page: 1
  year: 2021
  ident: 10.1016/j.oceaneng.2025.123564_bib16
  article-title: Typical trajectory extraction method for ships based on ais data and trajectory clustering
– volume: 55
  start-page: 84
  issue: 1
  year: 2014
  ident: 10.1016/j.oceaneng.2025.123564_bib23
  article-title: Anomaly detection in vessel tracks using Bayesian networks
  publication-title: Int. J. Approx. Reason.
  doi: 10.1016/j.ijar.2013.03.012
– volume: 71
  start-page: 1
  year: 2022
  ident: 10.1016/j.oceaneng.2025.123564_bib31
  article-title: Deep learning for unsupervised Anomaly localization in industrial images: a survey
  publication-title: IEEE Trans. Instrum. Meas.
– volume: 163
  start-page: 10
  year: 2022
  ident: 10.1016/j.oceaneng.2025.123564_bib19
  article-title: Robust structural similarity index measure for images with Non-Gaussian distortions
  publication-title: Pattern Recognit. Lett.
  doi: 10.1016/j.patrec.2022.09.011
– volume: 293
  year: 2024
  ident: 10.1016/j.oceaneng.2025.123564_bib38
  article-title: An anomaly detection method based on ship behavior trajectory
  publication-title: Ocean Eng.
  doi: 10.1016/j.oceaneng.2023.116640
– volume: 120
  year: 2024
  ident: 10.1016/j.oceaneng.2025.123564_bib34
  article-title: MSA-Net: multi-scale feature fusion network with enhanced attention module for 3D medical image segmentation
  publication-title: Comput. Electr. Eng.
  doi: 10.1016/j.compeleceng.2024.109654
– volume: 312
  year: 2024
  ident: 10.1016/j.oceaneng.2025.123564_bib42
  article-title: An adaptive trajectory segmentation and simplification algorithm based on vessel behavioral features
  publication-title: Ocean Eng.
  doi: 10.1016/j.oceaneng.2024.119329
– volume: 189
  year: 2022
  ident: 10.1016/j.oceaneng.2025.123564_bib1
  article-title: Structural similarity index (SSIM) revisited: a data-driven approach
  publication-title: Expert Syst. Appl.
  doi: 10.1016/j.eswa.2021.116087
– volume: 271
  year: 2023
  ident: 10.1016/j.oceaneng.2025.123564_bib36
  article-title: Data-driven methods for detection of abnormal ship behavior: progress and trends
  publication-title: Ocean Eng.
  doi: 10.1016/j.oceaneng.2023.113673
– volume: 563
  year: 2024
  ident: 10.1016/j.oceaneng.2025.123564_bib28
  article-title: Context learning from a ship trajectory cluster for anomaly detection
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2023.126920
– volume: 152
  year: 2024
  ident: 10.1016/j.oceaneng.2025.123564_bib15
  article-title: Inverse distance weighting and radial basis function based surrogate model for high-dimensional expensive multi-objective optimization
  publication-title: Appl. Soft Comput.
  doi: 10.1016/j.asoc.2023.111194
– volume: 143
  year: 2025
  ident: 10.1016/j.oceaneng.2025.123564_bib4
  article-title: Inspection of cracking in stamping parts surfaces using anomaly detection
  publication-title: Eng. Appl. Artif. Intell.
  doi: 10.1016/j.engappai.2025.110006
– volume: 453
  start-page: 131
  year: 2021
  ident: 10.1016/j.oceaneng.2025.123564_bib46
  article-title: VAE-based deep SVDD for anomaly detection
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2021.04.089
– volume: 98
  year: 2024
  ident: 10.1016/j.oceaneng.2025.123564_bib5
  article-title: DERE-Net: a dual-encoder residual enhanced U-Net for muscle fiber segmentation of H&E images
  publication-title: Biomed. Signal Process Control
  doi: 10.1016/j.bspc.2024.106765
– start-page: 29
  year: 2019
  ident: 10.1016/j.oceaneng.2025.123564_bib40
– start-page: 10
  year: 2018
  ident: 10.1016/j.oceaneng.2025.123564_bib32
  article-title: Anomalous behavior detection of marine vessels based on hidden Markov model
– volume: 73
  start-page: 9800
  issue: 7
  year: 2024
  ident: 10.1016/j.oceaneng.2025.123564_bib11
  article-title: Anomalous sub-trajectory detection with graph contrastive self-supervised learning
  publication-title: IEEE Trans. Veh. Technol.
  doi: 10.1109/TVT.2024.3382685
– volume: 266
  year: 2022
  ident: 10.1016/j.oceaneng.2025.123564_bib22
  article-title: Research on detection mechanism of vessel abnormal behavior based on immune genetic spectral clustering algorithm
  publication-title: Ocean Eng.
  doi: 10.1016/j.oceaneng.2022.113099
– volume: 290
  year: 2023
  ident: 10.1016/j.oceaneng.2025.123564_bib21
  article-title: The model of vessel trajectory abnormal behavior detection based on graph attention prediction and reconstruction network
  publication-title: Ocean Eng.
  doi: 10.1016/j.oceaneng.2023.116316
– volume: 247
  year: 2024
  ident: 10.1016/j.oceaneng.2025.123564_bib27
  article-title: A framework for ship abnormal behaviour detection and classification using AIS data
  publication-title: Reliab. Eng. Syst. Saf.
  doi: 10.1016/j.ress.2024.110105
– volume: 182
  year: 2024
  ident: 10.1016/j.oceaneng.2025.123564_bib47
  article-title: Lightweight medical image segmentation network with multi-scale feature-guided fusion
  publication-title: Comput. Biol. Med.
  doi: 10.1016/j.compbiomed.2024.109204
– volume: 119
  start-page: 1
  year: 2022
  ident: 10.1016/j.oceaneng.2025.123564_bib3
  article-title: A novel approach exploiting properties of convolutional neural networks for vessel movement anomaly detection and classification
  publication-title: ISA Transactions
  doi: 10.1016/j.isatra.2021.02.030
– volume: 24
  start-page: 4631
  issue: 4
  year: 2023
  ident: 10.1016/j.oceaneng.2025.123564_bib35
  article-title: AI-Empowered trajectory anomaly detection for intelligent transportation systems: a hierarchical federated learning approach
  publication-title: IEEE Trans. Intell. Transport. Syst.
  doi: 10.1109/TITS.2022.3209903
– volume: 288
  year: 2023
  ident: 10.1016/j.oceaneng.2025.123564_bib44
  article-title: A novel ship trajectory clustering analysis and anomaly detection method based on AIS data
  publication-title: Ocean Eng.
  doi: 10.1016/j.oceaneng.2023.116082
– volume: 109
  year: 2022
  ident: 10.1016/j.oceaneng.2025.123564_bib25
  article-title: Non-intrusive surrogate modeling for parametrized time-dependent partial differential equations using convolutional autoencoders
  publication-title: Eng. Appl. Artif. Intell.
  doi: 10.1016/j.engappai.2021.104652
– volume: 13
  start-page: 849
  issue: 5
  year: 2025
  ident: 10.1016/j.oceaneng.2025.123564_bib8
  article-title: A Transformer–VAE approach for detecting ship trajectory anomalies in cross-sea bridge areas
  publication-title: J. Mar. Sci. Eng.
  doi: 10.3390/jmse13050849
– start-page: 143
  year: 2020
  ident: 10.1016/j.oceaneng.2025.123564_bib33
  article-title: Abnormal moving speed detection using combination of kernel density estimator and DBSCAN for coastal surveillance radars
– volume: 280
  year: 2023
  ident: 10.1016/j.oceaneng.2025.123564_bib2
  article-title: Vessel sailing route extraction and analysis from satellite-based AIS data using density clustering and probability algorithms
  publication-title: Ocean Eng.
  doi: 10.1016/j.oceaneng.2023.114627
– start-page: 756
  year: 2009
  ident: 10.1016/j.oceaneng.2025.123564_bib13
  article-title: Anomaly detection in sea traffic-a comparison of the Gaussian mixture model and the kernel density estimator
– volume: 146
  year: 2024
  ident: 10.1016/j.oceaneng.2025.123564_bib6
  article-title: Unsupervised knowledge discovery framework: from AIS data processing to maritime traffic networks generating
  publication-title: Appl. Ocean Res.
  doi: 10.1016/j.apor.2024.103924
– start-page: 645
  year: 2012
  ident: 10.1016/j.oceaneng.2025.123564_bib30
  article-title: Online maritime abnormality detection using gaussian processes and extreme value theory
– volume: 13
  start-page: 8162
  issue: 15
  year: 2021
  ident: 10.1016/j.oceaneng.2025.123564_bib7
  article-title: Modeling vessel behaviours by clustering ais data using optimized dbscan
  publication-title: Sustainability
  doi: 10.3390/su13158162
– volume: 294
  year: 2024
  ident: 10.1016/j.oceaneng.2025.123564_bib14
  article-title: Collision evasive action timing for MASS using CNN–LSTM-based ship trajectory prediction in restricted area
  publication-title: Ocean Eng.
  doi: 10.1016/j.oceaneng.2024.116766
– volume: 11
  start-page: 56
  issue: 1
  year: 2023
  ident: 10.1016/j.oceaneng.2025.123564_bib20
  article-title: Research on fault early warning of marine diesel engine based on CNN-BiGRU
  publication-title: J. Mar. Sci. Eng.
  doi: 10.3390/jmse11010056
– volume: 231
  year: 2023
  ident: 10.1016/j.oceaneng.2025.123564_bib26
  article-title: AIS-based maritime anomaly traffic detection: a review
  publication-title: Expert Syst. Appl.
  doi: 10.1016/j.eswa.2023.120561
– volume: 338
  year: 2025
  ident: 10.1016/j.oceaneng.2025.123564_bib29
  article-title: Chimeric U-Net – modifying the standard U-Net towards explainability
  publication-title: Artif. Intell.
  doi: 10.1016/j.artint.2024.104240
– start-page: 1709
  year: 2024
  ident: 10.1016/j.oceaneng.2025.123564_bib45
  article-title: A CAE-based method for anomaly detection in ship trajectories
– volume: 24
  start-page: 2382
  issue: 2
  year: 2023
  ident: 10.1016/j.oceaneng.2025.123564_bib9
  article-title: Intelligent anomaly detection of trajectories for IoT empowered maritime transportation systems
  publication-title: IEEE Trans. Intell. Transport. Syst.
– volume: 10
  start-page: 112
  issue: 1
  year: 2022
  ident: 10.1016/j.oceaneng.2025.123564_bib37
  article-title: Anomaly detection in maritime AIS tracks: a review of recent approaches
  publication-title: J. Mar. Sci. Eng.
  doi: 10.3390/jmse10010112
SSID ssj0006603
Score 2.437435
Snippet Traditional methods for detecting anomalies in vessel trajectories do not adequately account for the multidimensional characteristics of vessel behavior, and...
SourceID crossref
elsevier
SourceType Index Database
Publisher
StartPage 123564
SubjectTerms Anomaly detection
Multi-scale convolutional autoencoder
Multidimensional features
Vessel trajectory
Title Vessel Trajectory Anomaly Detection Based on Multi-scale Convolutional Autoencoder
URI https://dx.doi.org/10.1016/j.oceaneng.2025.123564
Volume 343
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: ScienceDirect database
  issn: 0029-8018
  databaseCode: AIEXJ
  dateStart: 19950101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.sciencedirect.com
  omitProxy: false
  ssIdentifier: ssj0006603
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LT9wwELZa4NAioUJblUcrH7ih0E1sJ_aRIqoWVYB4VNtTZDsOsKJZxG7Q8u87fuQBRW059BJFUTxJ_H07npmdGSO0SY2SwN1BpGKdRDRWg0hkkkZEl0oSkxmqXXf9b9nBAR8OxVEIZU_cdgJZVfHZTFz_V6jhGoBtS2efAHcrFC7AOYAOR4Adjv8E_HfbDfzKdi0fuYj83Ra4-D_l1R3olqnxO4N_grWrsP8TuPrbaAJA2e3rqtvwZha3ejq2TS6LkL4bDNhDbUP3puti2EZOXVrAj_pCjltNEmLR-5dyVncsHNbecq_OJxemE3ACIx3g4c4QikhcKMIXY7alAcIuebyvXgklPQVpS3N92_LfdLcPI4y2x_ZD4PHgvCdsuxtwv1n2g0WsTS1sstZGeSMnt3JyL-c5mk8yJkD9ze983Rvut4t2mg5Ikw1kv6BXTP74Gz1ux_Rsk9NXaCk4FXjHk2EZPTPVCnrZazW5ghYdcKE_-Wt07FmCO5bgwBLcsgQ7lmA46bEE32MJ7rHkDTr7vHe6-yUK22tEGnxwGiWyFJqmhUykFJoxWaiSlKmhRDJBYgI_U8pNyrnSiqm05EoUJY-1glsY04a8RXPVuDLvEI5jw3RSaBbzgqZKKloKA3MldWLApZar6GMzWfm176KS_xmoVSSaOc2DLehtvBzo8pexa09-2jp60fF5A81Nb2rzHi3o2-nl5OZD4MovBDuGHQ
linkProvider Elsevier
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=Vessel+Trajectory+Anomaly+Detection+Based+on+Multi-scale+Convolutional+Autoencoder&rft.jtitle=Ocean+engineering&rft.au=Qi%2C+Yuhao&rft.au=Yang%2C+Jiaxuan&rft.au=Xu%2C+Dongsheng&rft.au=Shao%2C+Ran&rft.date=2026-01-15&rft.issn=0029-8018&rft.volume=343&rft.spage=123564&rft_id=info:doi/10.1016%2Fj.oceaneng.2025.123564&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_oceaneng_2025_123564
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0029-8018&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0029-8018&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0029-8018&client=summon