Skip to main content
SpringerLink
Log in

Intrusion detection for high-speed railways based on unsupervised anomaly detection models

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Intrusion detection for the high-speed railway is important for operational safety. Current detection methods based on deep learning use supervised learning paradigm, which heavily rely on large labeled datasets. However, real intrusion samples for railways are very rare and it is not possible to collect all types of intrusion objects. In this paper, we propose a new unsupervised intrusion detection method based on deep generative networks and auto-regression models. The deep generative network is train to reconstruct the input image, by learning the features, represented by the latent variables, from the input image. The auto-regression model is used to learn the probability distribution of the latent variables. The network is trained using just the normal samples to learn the features of normal samples. Therefore, the model can not reconstruct the abnormal images and the latent variable of abnormal image will have small likelihood probability according to the learned distribution. The anomaly is detected by a two-step mechanism, first the latent likelihood of the input image is computed, the second step is only performed when the likelihood is under a threshold. In the second step the model reconstructs the input image and the anomaly region is located by the difference of the reconstruction and the original input image. The proposed method is evaluated using a dataset built from realistic high-speed railway scenes. The results show that our method is able to detect the anomaly effectively, and has considerable improvement comparing to the current state-of-the-art anomaly detection methods also based on generative models.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Catalano A, Bruno FA, Galliano C, Pisco M, Persiano GV, Cutolo A, Cusano A (2017) An optical fiber intrusion detection system for railway security. Sens Actuator A Phys 253:91–100

    Article  Google Scholar 

  2. Cai H, Li F, Gao D, Yang Y, Li S, Gao K, Qin A, Hu C, Huang Z (2020) Foreign objects intrusion detection using millimeter wave radar on railway crossings. In: IEEE Conf. Syst., man, cybern., pp 2776–2781

  3. Rodriguez LA, Uribe J, Bonilla JFV (2012) Obstacle detection over rails using hough transform. In: 2012 XVII Symposium of image, signal processing, and artificial vision, pp 317–322

  4. Silar Z, Dobrovolny M (2013) The obstacle detection on the railway crossing based on optical flow and clustering. In: 2013 36Th international conference on telecommunications and signal processing, pp 755–759

  5. Zaman A, Ren B, Liu X (2019) Artificial intelligence-aided automated detection of railroad trespassing. Transp Res Rec 2673:25–37

    Article  Google Scholar 

  6. Alawad H, Kaewunruen S, An M (2020) A deep learning approach towards railway safety risk assessment. IEEE Access 8:102811–102832

    Article  Google Scholar 

  7. Zaman A, Liu X, Zhang Z (2018) Video analytics for railroad safety research: an artificial intelligence approach. Transp Res Rec 2672:269–277

    Article  Google Scholar 

  8. Guo B, Shi J, Zhu L, Yu Z (2019) High-speed railway clearance intrusion detection with improved ssd network. Appl Sci 9:2981

    Article  Google Scholar 

  9. García JJ, Ureña J, Hernandez Á, Mazo M, Jiménez JA, Álvarez FJ, De Marziani C, Jiménez A, Diaz MJ, Losada C, García E (2010) Efficient multisensory barrier for obstacle detection on railways. IEEE Trans Intell Trans Syst 11(3):702–713

    Article  Google Scholar 

  10. Ohta M (2005) Level crossings obstacle detection system using stereo cameras. Quarterly Report of Rtri 46:110–117

    Article  Google Scholar 

  11. Liu Q, Qin Y, Xie Z, Yang T, An G (2018) Intrusion detection for High-Speed railway perimeter obstacle. Springer, Singapore

    Book  Google Scholar 

  12. Chalapathy R, Chawla S (2019) Deep learning for anomaly detection: A survey. arXiv:1901.03407

  13. Schlegl T, Seeböck P, Waldstein SM, Schmidt-Erfurth U, Langs G (2017) Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In: International conference on information processing in medical imaging (IPMI)

  14. Baur C, Wiestler B, Albarqouni S, Navab N (2018) Deep autoencoding models for unsupervised anomaly segmentation in brain mr images. In: International MICCAI Brainlesion Workshop. Springer, pp 161–169

  15. Akcay S, Atapour-Abarghouei A, Breckon TP (2018) Ganomaly: Semi-supervised anomaly detection via adversarial training. In: Asian conference on computer vision. Springer, pp 622–637

  16. Kiran BR, Thomas DM, Parakkal R (2018) An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos. Journal of Imaging 4(2):36

    Article  Google Scholar 

  17. Zenati H, Foo CS, Lecouat B, Manek G, Chandrasekhar VR (2018) Efficient gan-based anomaly detection. arXiv:1802.06222

  18. Oord Avd, Kalchbrenner N, Vinyals O, Espeholt L, Graves A, Kavukcuoglu K (2016) Conditional image generation with pixelcnn decoders. In: Proceedings of the 30th International conference on neural information processing systems, pp 4797–4805

  19. Kingma DP, Welling M (2013) Auto-Encoding Variational Bayes. arXiv:1312.6114

  20. Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: International conference on neural information processing systems, pp 2672–2680

  21. van den Oord A, Vinyals O, Kavukcuoglu K (2017) Neural discrete representation learning. In: Proceedings of the 31st International conference on neural information processing systems, pp 6309–6318

  22. Kimura M, Yanagihara T (2018) Anomaly detection using gans for visual inspection in noisy training data. In: Asian Conference on Computer Vision. Springer, pp 373–385

  23. Liu Y, Li Z, Zhou C, Jiang Y, Sun J, Wang M, He X (2019) Generative adversarial active learning for unsupervised outlier detection. IEEE Trans Knowl Data Eng 32(8):1517–1528

    Google Scholar 

  24. Pimentel MAF, Clifton DA, Clifton L, Tarassenko L (2014) A review of novelty detection. Signal Process 99:215–249

    Article  Google Scholar 

  25. van den Oord A, Kalchbrenner N, Kavukcuoglu K (2016) Pixel recurrent neural networks. In: International conference on machine learning

  26. Sun J, Li H, He X (2011) Efficient image denoising by mrf approximation with uniform-sampled multi-spanning-tree. In: 2011 Sixth international conference on image and graphics, pp 88–93

  27. Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L et al (2019) Pytorch: An imperative style, high-performance deep learning library. In: Advances in neural information processing systems, vol 32, pp 8026–8037

  28. Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. In: International conference on learning representations

  29. Bradley AP (1997) The use of the area under the roc curve in the evaluation of machine learning algorithms. Pattern Recogn 30(7):1145–1159

    Article  Google Scholar 

  30. Tian R, Shi H, Guo B, Zhu L (2022) Multi-scale object detection for high-speed railway clearance intrusion. Appl Intell 52(4):3511–3526

    Article  Google Scholar 

  31. Ye T, Zhang Z, Zhang X, Zhou F (2020) Autonomous railway traffic object detection using feature-enhanced single-shot detector. IEEE Access 8:145182–145193

    Article  Google Scholar 

  32. Ye T, Wang B, Song P, Li J (2018) Automatic railway traffic object detection system using feature fusion refine neural network under shunting mode. Sensors 18

  33. Wang Y, Yu P (2021) A fast intrusion detection method for high-speed railway clearance based on low-cost embedded gpus Sensors 21(21)

Download references

Acknowledgements

This work is partially supported by National Natural Science Foundation of China (52072026).

Author information

Authors and Affiliations

  1. School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing, 100044, China

    Yao Wang, Zujun Yu & Liqiang Zhu

  2. Frontiers Science Center for Smart High-speed Railway System, Beijing Jiaotong University, Beijing, 100044, China

    Yao Wang, Zujun Yu & Liqiang Zhu

Authors
  1. Yao Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zujun Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Liqiang Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yao Wang.

Additional information

Availability of Data and Materials

Data will be made available on reasonable request.

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, Y., Yu, Z. & Zhu, L. Intrusion detection for high-speed railways based on unsupervised anomaly detection models. Appl Intell 53, 8453–8466 (2023). https://doi.org/10.1007/s10489-022-03911-8

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-03911-8

Keywords

Search

Navigation