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.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
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
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
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
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
Zaman A, Ren B, Liu X (2019) Artificial intelligence-aided automated detection of railroad trespassing. Transp Res Rec 2673:25–37
Alawad H, Kaewunruen S, An M (2020) A deep learning approach towards railway safety risk assessment. IEEE Access 8:102811–102832
Zaman A, Liu X, Zhang Z (2018) Video analytics for railroad safety research: an artificial intelligence approach. Transp Res Rec 2672:269–277
Guo B, Shi J, Zhu L, Yu Z (2019) High-speed railway clearance intrusion detection with improved ssd network. Appl Sci 9:2981
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
Ohta M (2005) Level crossings obstacle detection system using stereo cameras. Quarterly Report of Rtri 46:110–117
Liu Q, Qin Y, Xie Z, Yang T, An G (2018) Intrusion detection for High-Speed railway perimeter obstacle. Springer, Singapore
Chalapathy R, Chawla S (2019) Deep learning for anomaly detection: A survey. arXiv:1901.03407
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)
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
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
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
Zenati H, Foo CS, Lecouat B, Manek G, Chandrasekhar VR (2018) Efficient gan-based anomaly detection. arXiv:1802.06222
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
Kingma DP, Welling M (2013) Auto-Encoding Variational Bayes. arXiv:1312.6114
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
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
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
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
Pimentel MAF, Clifton DA, Clifton L, Tarassenko L (2014) A review of novelty detection. Signal Process 99:215–249
van den Oord A, Kalchbrenner N, Kavukcuoglu K (2016) Pixel recurrent neural networks. In: International conference on machine learning
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
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
Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. In: International conference on learning representations
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
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
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
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
Wang Y, Yu P (2021) A fast intrusion detection method for high-speed railway clearance based on low-cost embedded gpus Sensors 21(21)
Acknowledgements
This work is partially supported by National Natural Science Foundation of China (52072026).
Author information
Authors and Affiliations
Corresponding author
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
About this article
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
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03911-8