A Bayesian Approach - Data Fusion for robust detection of Vandalism and Trespassing related events in the context of railway security

Michael Hubner; Kilian Wohlleben; Martin Litzenberger; Stephan Veigl; Andreas Opitz; Stefan Grebien

doi:10.23919/FUSION59988.2024.10706430

A Bayesian Approach - Data Fusion for robust detection of Vandalism and Trespassing related events in the context of railway security

Michael Hubner (Speaker)
, Kilian Wohlleben
, Martin Litzenberger
, Stephan Veigl
, Andreas Opitz
, Stefan Grebien
,

Joanneum Research Forschungsgesellschaft mbH

Research output: Chapter in Book or Conference Proceedings › Conference Proceedings with Oral Presentation › peer-review

Abstract

In the domain of railway infrastructure, monitoring
and securing the operational stability of the operation remains a
significant problem. Vandalism, trespassing, sabotage and theft
are constant threats, endangering the safety and integrity of the
entire system. At the same time monitoring of these systems
is becoming harder and harder as the systems grow and the
amount of data produced by the surveillance equipment scales accordingly. Additionally, since specific sensor modalities can have weaknesses in detecting one kind of threat, it is often necessary to install different sensors to get a better understanding of situation. In this paper we present our fusion model based on
Probabilistic Occupancy Maps (POM) and Bayesian Inference for environmental mapping of critical events such as vandalism and trespassing in the vicinity of railway infrastructure. We show that this approach helps to increase accuracy, while simultaneously decreasing the amount of false alarms generated by a system.

Original language	English
Title of host publication	Proceedings of ISIF International Conference on Information Fusion (FUSION 2024)
Pages	1-7
Volume	27
ISBN (Electronic)	978-1-7377497-6-9
DOIs	https://doi.org/10.23919/FUSION59988.2024.10706430
Publication status	Published - 15 Oct 2024
Event	27th International Conference on Information Fusion - San Giobbe Economics Campus Fondamenta San Giobbe, Cannaregio 873, Venice, Italy Duration: 8 Jul 2024 → 11 Jul 2024 https://fusion2024.org/

Conference

Conference	27th International Conference on Information Fusion
Abbreviated title	FUSION 2024
Country/Territory	Italy
City	Venice
Period	8/07/24 → 11/07/24
Internet address	https://fusion2024.org/

Research Field

Responsive Sensing & Analytics
Computer Vision

Keywords

Bayesian inference
Multi-modal information fusion
critical infrastructure protection
trust in fusion systems

Access to Document

10.23919/FUSION59988.2024.10706430

Cite this

Hubner, M., Wohlleben, K., Litzenberger, M., Veigl, S., Opitz, A., Grebien, S. (2024). A Bayesian Approach - Data Fusion for robust detection of Vandalism and Trespassing related events in the context of railway security. In Proceedings of ISIF International Conference on Information Fusion (FUSION 2024) (Vol. 27, pp. 1-7) https://doi.org/10.23919/FUSION59988.2024.10706430

@inproceedings{9a9d788b2caa406a99556296a5db1745,

title = "A Bayesian Approach - Data Fusion for robust detection of Vandalism and Trespassing related events in the context of railway security",

abstract = "In the domain of railway infrastructure, monitoring and securing the operational stability of the operation remains a significant problem. Vandalism, trespassing, sabotage and theft are constant threats, endangering the safety and integrity of the entire system. At the same time monitoring of these systems is becoming harder and harder as the systems grow and the amount of data produced by the surveillance equipment scales accordingly. Additionally, since specific sensor modalities can have weaknesses in detecting one kind of threat, it is often necessary to install different sensors to get a better understanding of situation. In this paper we present our fusion model based on Probabilistic Occupancy Maps (POM) and Bayesian Inference for environmental mapping of critical events such as vandalism and trespassing in the vicinity of railway infrastructure. We show that this approach helps to increase accuracy, while simultaneously decreasing the amount of false alarms generated by a system.",

keywords = "Bayesian inference, Multi-modal information fusion, critical infrastructure protection, trust in fusion systems",

author = "Michael Hubner and Kilian Wohlleben and Martin Litzenberger and Stephan Veigl and Andreas Opitz and Stefan Grebien",

year = "2024",

month = oct,

day = "15",

doi = "10.23919/FUSION59988.2024.10706430",

language = "English",

isbn = "979-8-3503-7142-0",

volume = "27",

pages = "1--7",

booktitle = "Proceedings of ISIF International Conference on Information Fusion (FUSION 2024)",

note = "27th International Conference on Information Fusion, FUSION 2024 ; Conference date: 08-07-2024 Through 11-07-2024",

url = "https://fusion2024.org/",

}

Hubner, M , Wohlleben, K , Litzenberger, M , Veigl, S, Opitz, A, Grebien, S 2024, A Bayesian Approach - Data Fusion for robust detection of Vandalism and Trespassing related events in the context of railway security. in Proceedings of ISIF International Conference on Information Fusion (FUSION 2024). vol. 27, pp. 1-7, 27th International Conference on Information Fusion, Venice, Italy, 8/07/24. https://doi.org/10.23919/FUSION59988.2024.10706430

A Bayesian Approach - Data Fusion for robust detection of Vandalism and Trespassing related events in the context of railway security. / Hubner, Michael (Speaker); Wohlleben, Kilian ; Litzenberger, Martin et al.
Proceedings of ISIF International Conference on Information Fusion (FUSION 2024). Vol. 27 2024. p. 1-7.

Research output: Chapter in Book or Conference Proceedings › Conference Proceedings with Oral Presentation › peer-review

TY - GEN

T1 - A Bayesian Approach - Data Fusion for robust detection of Vandalism and Trespassing related events in the context of railway security

AU - Wohlleben, Kilian

AU - Litzenberger, Martin

AU - Veigl, Stephan

AU - Opitz, Andreas

AU - Grebien, Stefan

A2 - Hubner, Michael

PY - 2024/10/15

Y1 - 2024/10/15

N2 - In the domain of railway infrastructure, monitoring and securing the operational stability of the operation remains a significant problem. Vandalism, trespassing, sabotage and theft are constant threats, endangering the safety and integrity of the entire system. At the same time monitoring of these systems is becoming harder and harder as the systems grow and the amount of data produced by the surveillance equipment scales accordingly. Additionally, since specific sensor modalities can have weaknesses in detecting one kind of threat, it is often necessary to install different sensors to get a better understanding of situation. In this paper we present our fusion model based on Probabilistic Occupancy Maps (POM) and Bayesian Inference for environmental mapping of critical events such as vandalism and trespassing in the vicinity of railway infrastructure. We show that this approach helps to increase accuracy, while simultaneously decreasing the amount of false alarms generated by a system.

AB - In the domain of railway infrastructure, monitoring and securing the operational stability of the operation remains a significant problem. Vandalism, trespassing, sabotage and theft are constant threats, endangering the safety and integrity of the entire system. At the same time monitoring of these systems is becoming harder and harder as the systems grow and the amount of data produced by the surveillance equipment scales accordingly. Additionally, since specific sensor modalities can have weaknesses in detecting one kind of threat, it is often necessary to install different sensors to get a better understanding of situation. In this paper we present our fusion model based on Probabilistic Occupancy Maps (POM) and Bayesian Inference for environmental mapping of critical events such as vandalism and trespassing in the vicinity of railway infrastructure. We show that this approach helps to increase accuracy, while simultaneously decreasing the amount of false alarms generated by a system.

KW - Bayesian inference

KW - Multi-modal information fusion

KW - critical infrastructure protection

KW - trust in fusion systems

UR - https://ieeexplore.ieee.org/document/10706430/references#references

U2 - 10.23919/FUSION59988.2024.10706430

DO - 10.23919/FUSION59988.2024.10706430

M3 - Conference Proceedings with Oral Presentation

SN - 979-8-3503-7142-0

VL - 27

SP - 1

EP - 7

BT - Proceedings of ISIF International Conference on Information Fusion (FUSION 2024)

T2 - 27th International Conference on Information Fusion

Y2 - 8 July 2024 through 11 July 2024

ER -

A Bayesian Approach - Data Fusion for robust detection of Vandalism and Trespassing related events in the context of railway security

Abstract

Conference

Research Field

Keywords

Access to Document

Other files and links

Fingerprint

Enhancing Maritime Situational Awareness through Multimodal Fusion: Insights from a Real-World Experiment

Text-based entity matching for entity resolution and data fusion applied to person descriptions

A Multimodal Fusion Architecture for Sensor Applications

Cite this