Journal of Korean Society of Industrial and Systems Engineering (산업경영시스템학회지)

Society of Korea Industrial and System Engineering (한국산업경영시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Detection of Abnormal Vessel Trajectories with Convolutional Autoencoder

합성곱 오토인코더를 이용한 이상거동 선박 식별

  • Received : 2020.11.26
  • Accepted : 2020.12.23
  • Published : 2020.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recently there was an incident that military radars, coastal CCTVs and other surveillance equipment captured a small rubber boat smuggling a group of illegal immigrants into South Korea, but guards on duty failed to notice it until after they reached the shore and fled. After that, the detection of such vessels before it reach to the Korean shore has emerged as an important issue to be solved. In the fields of marine navigation, Automatic Identification System (AIS) is widely equipped in vessels, and the vessels incessantly transmits its position information. In this paper, we propose a method of automatically identifying abnormally behaving vessels with AIS using convolutional autoencoder (CAE). Vessel anomaly detection can be referred to as the process of detecting its trajectory that significantly deviated from the majority of the trajectories. In this method, the normal vessel trajectory is gridded as an image, and CAE are trained with images from historical normal vessel trajectories to reconstruct the input image. Features of normal trajectories are captured into weights in CAE. As a result, images of the trajectories of abnormal behaving vessels are poorly reconstructed and end up with large reconstruction errors. We show how correctly the model detects simulated abnormal trajectories shifted a few pixel from normal trajectories. Since the proposed model identifies abnormally behaving ships using actual AIS data, it is expected to contribute to the strengthening of security level when it is applied to various maritime surveillance systems.

Keywords

References

  1. Besse, P., Guillouet, B., Loubes, J., and Royer, F., Review and Perspective for Distance Clustering of Vehicle Trajectories, IEEE Transactions on Intelligence Transportation Systems, 2016, Vol. 17, No. 11, pp. 3306-3317. https://doi.org/10.1109/TITS.2016.2547641
  2. Chen, L. and Ng, R., On the Marriage of Lp-norms and Edit Distance, Proceeding of the International Conference on Very Large Data Bases, 2004, pp. 1040-1049.
  3. Chen, L., Ozsu, M., and Oria, V., Robust and Fast Similarity Search for Moving Object Trajectories, Proceedings of the International Conference on Management of Data, 2005, pp. 491-502.
  4. Fu, P., Wang, H., Liu, K., Hu, X., and Zhang, H., Finding Abnormal Vessel Trajectories Using Feature Learning, IEEE Access, 2017, Vol. 5, pp. 7898-7909. https://doi.org/10.1109/ACCESS.2017.2698208
  5. Han, H., Armenakis, C., and Jaddi, M., DBSCAN Optimization for Improving Marine Trajectory Clustering and Anomaly Detection, International Archives of Photogrammetry, Remote Sensing and Spatial Information Science, 2020, Vol. XLIII-B4-2020, pp. 445-461.
  6. Iltanan, H., Maritime Anomaly Detection using Autoencoders and OPTICS-OF [Mastre's Thesis], [Helsinki, Finland] : University of Helsinki, 2020.
  7. Kim, H. and Kim, J., A Heuristic Algorithm for a Ship Speed and Bunkering Decision Problem, Journal of Society of Korea Industrial and Systems Engineering, 2016, Vol. 39, No. 2, pp. 19-27. https://doi.org/10.11627/jkise.2016.39.2.019
  8. Kim, H. and Kim, J., Determining Economic Ship Speeds and Fleet Sizes Considering Greenhouse Gas Emissions, Journal of Society of Korea Industrial and Systems Engineering, 2011, Vol. 34, No. 2, pp. 49-59.
  9. Kim, K., Development of Ship Safety Navigation Alarm System using AIS, Journal of Korean Institute of Information Technology, 2013, Vol. 11, No. 4, pp. 69-75.
  10. Kwon, S.H. and Oh, H.S., Reduction of Simulation Number for Ship Handling Safety Assessment, Journal of Society of Korea Industrial and Systems Engineering, 2012, Vol. 35, No. 1, pp. 101-106.
  11. Nguyen, D., Vadaine, R., Hajduch, G.,Garello, R., and Fablet, R., A Multi-task Deep Learning Architecture for Maritime Surveillance using AIS Data Streams, IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA), 2018.
  12. Oh, J-Y., Kim, Y-J., and Park, S-K., Detection of Ship Movement Anomaly using AIS Data : A Study, Journal of Korean Navigation and Port Research, 2018, Vol. 42, No. 4, pp. 277-282.
  13. Oh, J-Y., Kim, Y-J., and Park, S-K., Development of a Decision Support System based on Autoencoder for Vessel Traffic Service, KIISE Transactions on Computing Practices, 2018, Vol. 24, No. 12, pp. 642-648. https://doi.org/10.5626/ktcp.2018.24.12.642
  14. Palliotta, G. and Jousselme, A-L., Data-driven Detection and Context-based Classification of Maritime Anomalies, The 18th International Conference on Information Fusion, 2015, pp. 1152-1159.
  15. Pallotta, G., Vespe, M., and Bryan, K., Traffic Knowledge Discovery from AIS data, Proceedings of the 16th International Conference on Information Fusion, 2013, pp. 1996-2003.
  16. Park, J. and Kim, S., Maritime Anomaly Detection Based on VAE-CUSUM Monitoring System, Journal of the Korean Institute of Industrial Engineers, 2020, Vol. 46, No. 4, pp. 432-442. https://doi.org/10.7232/JKIIE.2020.46.4.432
  17. Vlachos, M., Kollios, G., and Gunopulos, D., Discovering Similar Multidimensional Trajectories, Proceeding of the International Conference on Data Engineering, 2002, pp. 673-684.
  18. Yu, J.Y., Sghaier, M.O., and Grabowiecka, Z., Deep Learning Approaches for AIS Data Association in the Context of Maritime Domain Awareness, IEEE 23rd International Conference on Information Fusion, 2020, pp. 1-8.