Detecting Anomalous Vessel Trajectories: A Collaborative Clustering-Based Approach

• Cláudio Vasconcelos Ribeiro Universidade Federal Fluminense (UFF)
• Marcos Bedo Universidade Federal Fluminense (UFF)
• Ronaldo Mello Universidade Federal de Santa Catarina (UFSC) https://orcid.org/0000-0003-4262-5474
• Aline Paes Universidade Federal Fluminense (UFF)
• Daniel de Oliveira Universidade Federal Fluminense (UFF)

DOI: https://doi.org/10.5753/sbbd.2025.247003

Resumo

Thousands of vessels operating worldwide may present issues related to anomalous trajectories, often characterized by unexpected changes in course, speed, or navigation through restricted areas. Manually detecting these anomalies is impractical, evidencing the need for automated support for maritime surveillance agents. Although Automatic Identification Systems (AIS) enhance situational awareness, they are insufficient for detecting trajectory anomalies. Existing approaches already use AIS data to detect anomalous vessel trajectories, but they do not consider contextual variables (e.g., oil spills) or the domain expertise of maritime surveillance agents. This paper introduces INSTRUCTOR, a solution that combines AIS data with clustering algorithms to group vessel trajectories based on similar directions and movement patterns. This clustering output assists experts in collaboratively identifying anomalous trajectories, a process validated through the collective judgment of multiple domain specialists. Experiments conducted in partnership with the Brazilian Navy corroborate the effectiveness of INSTRUCTOR in detecting anomalous maritime trajectories.

Palavras-chave: AIS, Anomalous Trajectories

Referências

Dobrkovic, A. et al. (2015). Using machine learning for unsupervised maritime waypoint discovery from streaming ais data. In Proc. of i-KNOW ’15, pages 1–8.

Dobrkovic, A. et al. (2018). Maritime pattern extraction and route reconstruction from incomplete ais data. IJDSA, 5(2-3):111–136.

EMSA (2019). Annual overview of marine casualties and incidents. Technical report.

Fu, P., Wang, H., Liu, K., Hu, X., and Zhang, H. (2017). Finding abnormal vessel trajectories using feature learning. IEEE Access, 5:7898–7909.

Kowalska, K. and Peel, L. (2012). Maritime anomaly detection using gaussian process active learning. In 2012 FUSION, pages 1164–1171. IEEE.

Laxhammar, R. and Falkman, G. (2010). Conformal prediction for distribution-independent anomaly detection in streaming vessel data. In Proc. of StreamKDD ’10, pages 47–55.

Lei, P.-R. (2016). A framework for anomaly detection in maritime trajectory behavior. Knowledge and Information Systems, 47(1):189–214.

Liu, B. et al. (2015). Ship movement anomaly detection using specialized distance measures. In 2015 FUSION, pages 1113–1120. IEEE.

Mantecón, T. et al. (2019). Deep learning to enhance maritime situation awareness. In 2019 IRS, pages 1–8. IEEE.

Mazzarella, F. et al. (2014). Discovering vessel activities at sea using ais data: Mapping of fishing footprints. In 17th FUSION, pages 1–7. IEEE.

Nguyen, D. et al. (2018). A multi-task deep learning architecture for maritime surveillance using ais data streams. In 2018 IEEE DSAA, pages 331–340. IEEE.

Nishizaki, C. et al. (2018). Development of navigation support system to predict new course of ship. In 2018 WAC, pages 1–5. IEEE.

Osekowska, E., Axelsson, S., and Carlsson, B. (2013). Potential fields in maritime anomaly detection. In Proceedings of the 3rd international conference on models and technologies for intelligent transport systems. TUD Press.

Pallotta, G., Vespe, M., and Bryan, K. (2013a). Traffic knowledge discovery from ais data. In Proceedings of the 16th International Conference on Information Fusion, pages 1996–2003. IEEE.

Pallotta, G., Vespe, M., and Bryan, K. (2013b). Vessel pattern knowledge discovery from ais data: A framework for anomaly detection and route prediction. Entropy, 15(6):2218–2245.

Pallotta, G. a. (2014). Context-enhanced vessel prediction based on ornstein-uhlenbeck processes using historical ais traffic patterns: Real-world experimental results. In 17th FUSION, pages 1–7. IEEE.

Radon, A. N., Wang, K., Glässer, U., Wehn, H., and Westwell-Roper, A. (2015). Contextual verification for false alarm reduction in maritime anomaly detection. In 2015 IEEE International Conference on Big Data (Big Data), pages 1123–1133. IEEE.

Ribeiro, C. V., Paes, A., and de Oliveira, D. (2023). Ais-based maritime anomaly traffic detection: A review. Expert Systems with Applications, page 120561.

Riveiro, M. et al. (2018). Maritime anomaly detection: A review. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 8(5):e1266.

Riveiro, M. and Falkman, G. (2009). Interactive visualization of normal behavioral models and expert rules for maritime anomaly detection. In CGIV ’09, pages 459–466. IEEE.

Sidibé, A. and Shu, G. (2017). Study of automatic anomalous behaviour detection techniques for maritime vessels. The journal of Navigation, 70(4):847–858.

Silveira, P. et al. (2013). Use of ais data to characterise marine traffic patterns and ship collision risk off the coast of portugal. The Journal of Navigation, 66(6):879–898.

Smith, M. et al. (2012). Online maritime abnormality detection using gaussian processes and extreme value theory. In 2012 ICDM, pages 645–654. IEEE.

Soleimani, B. H. et al. (2015). Anomaly detection in maritime data based on geometrical analysis of trajectories. In 2015 FUSION, pages 1100–1105. IEEE.

Spaccapietra, S. et al. (2008). A conceptual view on trajectories. Data & knowledge engineering, 65(1):126–146.

UNCTAD (2019). Handbook of Statistics. UN Conference on Trade and Develop. Available at [link].

Venskus, J. et al. (2017). Integration of a self-organizing map and a virtual pheromone for real-time abnormal movement detection in marine traffic. Informatica, 28(2):359–374.

Venskus, J. et al. (2019). Real-time maritime traffic anomaly detection based on sensors and history data embedding. Sensors, 19(17):3782.

Wang, X. et al. (2014). Vessel route anomaly detection with hadoop mapreduce. In 2014 IEEE Big Data, pages 25–30. IEEE.

Weng, J. et al. (2018). Combining zero-inflated negative binomial regression with mlrt techniques: an approach to evaluating shipping accident casualties. Ocean Engineering, 166:135–144.

Wohlin, C. (2014). Guidelines for snowballing in systematic literature studies and a replication in software engineering. In Proc. of EASE’14, pages 1–10.

Yan, W. et al. (2016). Vessel movement analysis and pattern discovery using density-based clustering approach. In 2016 IEEE Big Data, pages 3798–3806. IEEE.

Zhang, S.-k. et al. (2018). Data-driven based automatic maritime routing from massive ais trajectories in the face of disparity. Ocean Engineering, 155:240–250.

Zhao, L. and Shi, G. (2019). Maritime anomaly detection using density-based clustering and recurrent neural network. The Journal of Navigation, 72(4):894–916.

Zhen, R., Jin, Y., Hu, Q., Shao, Z., and Nikitakos, N. (2017). Maritime anomaly detection within coastal waters based on vessel trajectory clustering and naı̈ve bayes classifier. The Journal of Navigation, 70(3):648–670.

Zissis, D., Xidias, E. K., and Lekkas, D. (2015). A cloud based architecture capable of perceiving and predicting multiple vessel behaviour. App. Soft Computing, 35:652–661.

Zor, C. and Kittler, J. (2017). Maritime anomaly detection in ferry tracks. In Int. Conf. on Acoustics, Speech and Signal Processing, pages 2647–2651. IEEE.