Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jun 25;24(13):4118.
doi: 10.3390/s24134118.

Robust Detection of Critical Events in the Context of Railway Security Based on Multimodal Sensor Data Fusion

Michael Hubner  1 , Kilian Wohlleben  1 , Martin Litzenberger  1 , Stephan Veigl  1 , Andreas Opitz  1 , Stefan Grebien  2 , Franz Graf  2 , Andreas Haderer  3 , Susanne Rechbauer  3 , Sebastian Poltschak  3
Affiliations

Robust Detection of Critical Events in the Context of Railway Security Based on Multimodal Sensor Data Fusion

Michael Hubner et al. Sensors (Basel). .

Abstract

Effective security surveillance is crucial in the railway sector to prevent security incidents, including vandalism, trespassing, and sabotage. This paper discusses the challenges of maintaining seamless surveillance over extensive railway infrastructure, considering both technological advances and the growing risks posed by terrorist attacks. Based on previous research, this paper discusses the limitations of current surveillance methods, particularly in managing information overload and false alarms that result from integrating multiple sensor technologies. To address these issues, we propose a new fusion model that utilises Probabilistic Occupancy Maps (POMs) and Bayesian fusion techniques. The fusion model is evaluated on a comprehensive dataset comprising three use cases with a total of eight real life critical scenarios. We show that, with this model, the detection accuracy can be increased while simultaneously reducing the false alarms in railway security surveillance systems. This way, our approach aims to enhance situational awareness and reduce false alarms, thereby improving the effectiveness of railway security measures.

Keywords: multi-sensor fusion; sensor data fusion; surveillance of critical infrastructure.

PubMed Disclaimer

Conflict of interest statement

The authors Andreas Haderer, Susanne Rechbauer and Sebastian Poltschak were employed by the company Joby Austria GmBH. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Example of sensor observations and ground truth. Orange small circles—radar observations; green small polygons—thermal observations; blue big polygon—acoustic observation; black big circle—ground truth observation.
Figure 2
Figure 2
Picture of the 64-ary MEMS array.
Figure 3
Figure 3
24 GHz radar sensor with 3D-printed pyramidal horn antennas.
Figure 4
Figure 4
Sensor setup, field of views (FoV) and region of interest (ROI). Green—thermal cameras; blue—acoustic sensor; orange—radar sensor; black—region of interest.
Figure 5
Figure 5
Progression of a scenario in the example group committing graffiti.
Figure 6
Figure 6
Illustration of the reasoning of the evaluation methodology. The blue polygons represent the area of a sensor observation at a specific time. Grey circles represent the area of the ground truth.
See this image and copyright information in PMC

References

    1. Killen A., Coxon D.S., Napper D.R. A Review of the Literature on Mitigation Strategies for Vandalism in Rail Environments; Auckland, New Zealand. 2017. [(accessed on 9 May 2024)]. Available online: https://api.semanticscholar.org/CorpusID:168167086.
    1. Zhang T., Aftab W., Mihaylova L., Langran-Wheeler C., Rigby S., Fletcher D., Maddock S., Bosworth G. Recent Advances in Video Analytics for Rail Network Surveillance for Security, Trespass and Suicide Prevention—A Survey. Sensors. 2022;22:4324. doi: 10.3390/s22124324. - DOI - PMC - PubMed
    1. Grabušić S., Barić D. A Systematic Review of Railway Trespassing: Problems and Prevention Measures. Sustainability. 2023;15:13878. doi: 10.3390/su151813878. - DOI
    1. Fogaça J., Brandão T., Ferreira J.C. Deep Learning-Based Graffiti Detection: A Study Using Images from the Streets of Lisbon. Appl. Sci. 2023;13:2249. doi: 10.3390/app13042249. - DOI
    1. Cao Z., Qin Y., Xie Z., Liu Q., Zhang E., Wu Z., Yu Z. An effective railway intrusion detection method using dynamic intrusion region and lightweight neural network. Measurement. 2022;191:110564. doi: 10.1016/j.measurement.2021.110564. - DOI

LinkOut - more resources