Skip to main content
Top

27-11-2024

A Bayesian Method for Real-time Unsupervised Detection of Anomalous Road Vehicle Trajectories

Authors: Thinh Hoang Dinh, Vincent Martinez, Pierre Maréchal, Daniel Delahaye

Published in: International Journal of Intelligent Transportation Systems Research

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Anomaly detection is critical in Intelligent Transportation Systems (ITS) due to its significant impact on safety. This paper introduces a Bayesian probabilistic framework for identifying anomalous trajectories without explicitly modeling anomalies reliably. The framework can be adapted according to the sensor quality, balancing speed and accuracy, and avoids out-of-sample performance issues commonly encountered in deep learning methods. By reducing the dimensionality of time series data using Functional Principal Component Analysis (FPCA), a prior distribution of FPCA scores is learned and continuously updated in an online manner. We conducted numerical experiments to validate the method’s effectiveness in detecting common road hazards such as wrong-way driving, over-speeding, and sudden hard-braking. Results demonstrated reliable detection of all tested anomalies with a single detector. Our framework significantly reduced false alarms compared to the Local Outlier Factor (LOF) method, more responsive than Isolation Forest (IF) and successfully mitigated the out-of-sample unpredictability associated with deep learning approaches like VAE-LSTM. Furthermore, it requires low computational resources, making it suitable for implementation across various embedded driving platforms. By addressing the these issues, the method could gain human trust in automated safety systems, accelerating their adoption.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

ATZelectronics worldwide

ATZlectronics worldwide is up-to-speed on new trends and developments in automotive electronics on a scientific level with a high depth of information. 

Order your 30-days-trial for free and without any commitment.

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Show more products
Appendix
Available only for authorised users
Literature
1.
go back to reference Alexiadis, V.: Video-based vehicle trajectory data collection. In: Transportation Research Board 86th Annual Meeting. Citeseer (2006) Alexiadis, V.: Video-based vehicle trajectory data collection. In: Transportation Research Board 86th Annual Meeting. Citeseer (2006)
2.
go back to reference Amarbayasgalan, T., Pham, V.H., Theera-Umpon, N., Ryu, K.H.: Unsupervised anomaly detection approach for time-series in multi-domains using deep reconstruction error. Symmetry 12(8), 1251 (2020)CrossRef Amarbayasgalan, T., Pham, V.H., Theera-Umpon, N., Ryu, K.H.: Unsupervised anomaly detection approach for time-series in multi-domains using deep reconstruction error. Symmetry 12(8), 1251 (2020)CrossRef
3.
go back to reference Blázquez-García, A., Conde, A., Mori, U., Lozano, J.A.: A review on outlier/anomaly detection in time series data. ACM Comput. Surv. (CSUR) 54(3), 1–33 (2021)CrossRef Blázquez-García, A., Conde, A., Mori, U., Lozano, J.A.: A review on outlier/anomaly detection in time series data. ACM Comput. Surv. (CSUR) 54(3), 1–33 (2021)CrossRef
6.
go back to reference Chandra, R., Bhattacharya, U., Mittal, T., Bera, A., Manocha, D.: Cmetric: A driving behavior measure using centrality functions. arXiv:2003.04424 (2020) Chandra, R., Bhattacharya, U., Mittal, T., Bera, A., Manocha, D.: Cmetric: A driving behavior measure using centrality functions. arXiv:​2003.​04424 (2020)
7.
go back to reference Cheung, E., Bera, A., Kubin, E., Gray, K., Manocha, D.: Identifying driver behaviors using trajectory features for vehicle navigation. In: 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3445–3452. IEEE (2018) Cheung, E., Bera, A., Kubin, E., Gray, K., Manocha, D.: Identifying driver behaviors using trajectory features for vehicle navigation. In: 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3445–3452. IEEE (2018)
8.
go back to reference Choi, K., Yi, J., Park, C., Yoon, S.: Deep learning for anomaly detection in time-series data: Review, analysis, and guidelines. IEEE Access 9, 120043–120065 (2021)CrossRef Choi, K., Yi, J., Park, C., Yoon, S.: Deep learning for anomaly detection in time-series data: Review, analysis, and guidelines. IEEE Access 9, 120043–120065 (2021)CrossRef
9.
go back to reference Colyar, J., Halkias, J.: Us highway 101 dataset. federal highway administration research and technology fact sheet. publication number: Fhwa-hrt-07-030. Tech. Rep. (2007) Colyar, J., Halkias, J.: Us highway 101 dataset. federal highway administration research and technology fact sheet. publication number: Fhwa-hrt-07-030. Tech. Rep. (2007)
10.
go back to reference Dinh, T.H., Martinez, V., Delahaye, D.: Recognition of outlying driving behaviors: A data-driven perspective with applications to v2x collective perception. In: 2021 IEEE Vehicular Networking Conference (VNC), pp. 52–59. IEEE (2021) Dinh, T.H., Martinez, V., Delahaye, D.: Recognition of outlying driving behaviors: A data-driven perspective with applications to v2x collective perception. In: 2021 IEEE Vehicular Networking Conference (VNC), pp. 52–59. IEEE (2021)
12.
go back to reference Hinami, R., Mei, T., Satoh, S.: Joint detection and recounting of abnormal events by learning deep generic knowledge. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3619–3627 (2017) Hinami, R., Mei, T., Satoh, S.: Joint detection and recounting of abnormal events by learning deep generic knowledge. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3619–3627 (2017)
13.
go back to reference Hong, Y.: scikit-fda: Principal Component Analysis for Functional Data. B.S. thesis (2020) Hong, Y.: scikit-fda: Principal Component Analysis for Functional Data. B.S. thesis (2020)
14.
go back to reference Hu, W., Xiao, X., Fu, Z., Xie, D., Tan, T., Maybank, S.: A system for learning statistical motion patterns. IEEE Trans. Pattern Anal. Mach. Intell. 28(9), 1450–1464 (2006)CrossRef Hu, W., Xiao, X., Fu, Z., Xie, D., Tan, T., Maybank, S.: A system for learning statistical motion patterns. IEEE Trans. Pattern Anal. Mach. Intell. 28(9), 1450–1464 (2006)CrossRef
15.
go back to reference Jarry, G., Couellan, N., Delahaye, D.: On the use of generative adversarial networks for aircraft trajectory generation and atypical approach detection. In: Air Traffic Management and Systems IV: Selected Papers of the 6th ENRI International Workshop on ATM/CNS (EIWAC2019) 6, pp. 227–243. Springer (2021) Jarry, G., Couellan, N., Delahaye, D.: On the use of generative adversarial networks for aircraft trajectory generation and atypical approach detection. In: Air Traffic Management and Systems IV: Selected Papers of the 6th ENRI International Workshop on ATM/CNS (EIWAC2019) 6, pp. 227–243. Springer (2021)
16.
go back to reference Jarry, G., Delahaye, D., Nicol, F., Feron, E.: Aircraft atypical approach detection using functional principal component analysis. J. Air Transp. Manag. 84, 101787 (2020)CrossRef Jarry, G., Delahaye, D., Nicol, F., Feron, E.: Aircraft atypical approach detection using functional principal component analysis. J. Air Transp. Manag. 84, 101787 (2020)CrossRef
17.
go back to reference Jin, X., Zhang, Y., Li, L., Hu, J.: Robust pca-based abnormal traffic flow pattern isolation and loop detector fault detection. Tsinghua Sci. Technol. 13(6), 829–835 (2008)CrossRef Jin, X., Zhang, Y., Li, L., Hu, J.: Robust pca-based abnormal traffic flow pattern isolation and loop detector fault detection. Tsinghua Sci. Technol. 13(6), 829–835 (2008)CrossRef
19.
go back to reference Lee, S., Kim, H.G., Ro, Y.M.: Stan: Spatio-temporal adversarial networks for abnormal event detection. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 1323–1327. IEEE (2018) Lee, S., Kim, H.G., Ro, Y.M.: Stan: Spatio-temporal adversarial networks for abnormal event detection. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 1323–1327. IEEE (2018)
20.
go back to reference Li, C., Han, Z., Ye, Q., Jiao, J.: Visual abnormal behavior detection based on trajectory sparse reconstruction analysis. Neurocomputing 119, 94–100 (2013)CrossRef Li, C., Han, Z., Ye, Q., Jiao, J.: Visual abnormal behavior detection based on trajectory sparse reconstruction analysis. Neurocomputing 119, 94–100 (2013)CrossRef
21.
go back to reference Li, N., Oyler, D.W., Zhang, M., Yildiz, Y., Kolmanovsky, I., Girard, A.R.: Game theoretic modeling of driver and vehicle interactions for verification and validation of autonomous vehicle control systems. IEEE Trans. Control Syst. Technol. 26(5), 1782–1797 (2017)CrossRef Li, N., Oyler, D.W., Zhang, M., Yildiz, Y., Kolmanovsky, I., Girard, A.R.: Game theoretic modeling of driver and vehicle interactions for verification and validation of autonomous vehicle control systems. IEEE Trans. Control Syst. Technol. 26(5), 1782–1797 (2017)CrossRef
22.
go back to reference Li, Y., Liu, W., Huang, Q.: Traffic anomaly detection based on image descriptor in videos. Multimed. Tools Appl. 75(5), 2487–2505 (2016)CrossRef Li, Y., Liu, W., Huang, Q.: Traffic anomaly detection based on image descriptor in videos. Multimed. Tools Appl. 75(5), 2487–2505 (2016)CrossRef
23.
go back to reference Lin, S., Clark, R., Birke, R., Schönborn, S., Trigoni, N., Roberts, S.: Anomaly detection for time series using vae-lstm hybrid model. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4322–4326. IEEE (2020) Lin, S., Clark, R., Birke, R., Schönborn, S., Trigoni, N., Roberts, S.: Anomaly detection for time series using vae-lstm hybrid model. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4322–4326. IEEE (2020)
24.
go back to reference Lin, W.C., Tsai, C.F.: Missing value imputation: a review and analysis of the literature (2006–2017). Artif. Intell. Rev. 53, 1487–1509 (2020)CrossRef Lin, W.C., Tsai, C.F.: Missing value imputation: a review and analysis of the literature (2006–2017). Artif. Intell. Rev. 53, 1487–1509 (2020)CrossRef
25.
go back to reference Liu, S.W., Ngan, H.Y., Ng, M.K., Simske, S.J.: Accumulated relative density outlier detection for large scale traffic data. Electron. Imaging 2018(9), 239–1 (2018) Liu, S.W., Ngan, H.Y., Ng, M.K., Simske, S.J.: Accumulated relative density outlier detection for large scale traffic data. Electron. Imaging 2018(9), 239–1 (2018)
26.
go back to reference Lu, C., Shi, J., Jia, J.: Abnormal event detection at 150 fps in matlab. In: Proceedings of the IEEE international conference on computer vision, pp. 2720–2727 (2013) Lu, C., Shi, J., Jia, J.: Abnormal event detection at 150 fps in matlab. In: Proceedings of the IEEE international conference on computer vision, pp. 2720–2727 (2013)
27.
go back to reference Ngan, H.Y., Yung, N.H., Yeh, A.G.: Outlier detection in traffic data based on the dirichlet process mixture model. IET Intell. Transp. Syst. 9(7), 773–781 (2015)CrossRef Ngan, H.Y., Yung, N.H., Yeh, A.G.: Outlier detection in traffic data based on the dirichlet process mixture model. IET Intell. Transp. Syst. 9(7), 773–781 (2015)CrossRef
28.
go back to reference Nguyen, V., Gupta, S., Rana, S., Li, C., Venkatesh, S.: A bayesian nonparametric approach for multi-label classification. In: Asian conference on machine learning, pp. 254–269. PMLR (2016) Nguyen, V., Gupta, S., Rana, S., Li, C., Venkatesh, S.: A bayesian nonparametric approach for multi-label classification. In: Asian conference on machine learning, pp. 254–269. PMLR (2016)
29.
go back to reference Niu, Z., Yu, K., Wu, X.: Lstm-based vae-gan for time-series anomaly detection. Sensors 20(13), 3738 (2020)CrossRef Niu, Z., Yu, K., Wu, X.: Lstm-based vae-gan for time-series anomaly detection. Sensors 20(13), 3738 (2020)CrossRef
30.
go back to reference Owens, J., Hunter, A.: Application of the self-organising map to trajectory classification. In: Proceedings Third IEEE International Workshop on Visual Surveillance, pp. 77–83. IEEE (2000) Owens, J., Hunter, A.: Application of the self-organising map to trajectory classification. In: Proceedings Third IEEE International Workshop on Visual Surveillance, pp. 77–83. IEEE (2000)
31.
go back to reference Ramanishka, V., Chen, Y.T., Misu, T., Saenko, K.: Toward driving scene understanding: A dataset for learning driver behavior and causal reasoning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7699–7707 (2018) Ramanishka, V., Chen, Y.T., Misu, T., Saenko, K.: Toward driving scene understanding: A dataset for learning driver behavior and causal reasoning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7699–7707 (2018)
32.
go back to reference Ramsay, J., Silverman, B.: Principal components analysis for functional data. Functional data analysis pp. 147–172 (2005) Ramsay, J., Silverman, B.: Principal components analysis for functional data. Functional data analysis pp. 147–172 (2005)
33.
go back to reference Ramsay, J.O., Silverman, B.W.: Applied functional data analysis: methods and case studies, vol. 77. Springer (2002) Ramsay, J.O., Silverman, B.W.: Applied functional data analysis: methods and case studies, vol. 77. Springer (2002)
34.
go back to reference Song, R.: Driver intention prediction using model-added Bayesian network. Proc. Inst. Mech. Eng. Pt. D J. Automobile Eng. 235(5), 1236–1244 (2021)CrossRef Song, R.: Driver intention prediction using model-added Bayesian network. Proc. Inst. Mech. Eng. Pt. D J. Automobile Eng. 235(5), 1236–1244 (2021)CrossRef
36.
go back to reference Xu, D., Ricci, E., Yan, Y., Song, J., Sebe, N.: Learning deep representation of appearance and motion for anomalous event detection. arXiv:1510.01553 (2015) Xu, D., Ricci, E., Yan, Y., Song, J., Sebe, N.: Learning deep representation of appearance and motion for anomalous event detection. arXiv:​1510.​01553 (2015)
38.
go back to reference Zhao, B., Fei-Fei, L., Xing, E.P.: Online detection of unusual events in videos via dynamic sparse coding. In: CVPR 2011, pp. 3313–3320. IEEE (2011) Zhao, B., Fei-Fei, L., Xing, E.P.: Online detection of unusual events in videos via dynamic sparse coding. In: CVPR 2011, pp. 3313–3320. IEEE (2011)
Metadata
Title
A Bayesian Method for Real-time Unsupervised Detection of Anomalous Road Vehicle Trajectories
Authors
Thinh Hoang Dinh
Vincent Martinez
Pierre Maréchal
Daniel Delahaye
Publication date
27-11-2024
Publisher
Springer US
Published in
International Journal of Intelligent Transportation Systems Research
Print ISSN: 1348-8503
Electronic ISSN: 1868-8659
DOI
https://doi.org/10.1007/s13177-024-00446-9

Premium Partners