Multi-Sensor Fusion for the Security Surveillance of Public Areas

Martin Litzenberger; Kilian Wohlleben; Michael Hubner; Bernhard Kohn

Multi-Sensor Fusion for the Security Surveillance of Public Areas

Martin Litzenberger (Speaker), Kilian Wohlleben, Michael Hubner, Bernhard Kohn

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

48 Downloads (Pure)

Abstract

Increasing security awareness in the public sector are leading to a more and more widespread use of surveillance applications. Although the available technologies like video processing are already well advanced, they still suffer from high false alarm rates when used under realistic conditions. We present a method for sensor fusion based on probability density maps and a rule engine. The system was tested in a public area using the combination of audio localization, audio classification and video detection using 79 simulated scenarios and 44 hours of sample data recorded over a period of several weeks. The false positive rate decreased by 60% and the event localization rate increased by 25% with the fusion approach compared to the detection performance of individual techniques.

Original language	English
Title of host publication	PROCEEDINGS OF SPIE
Subtitle of host publication	International Conference on Images, Signals, and Computing (ICISC 2023)
Place of Publication	P.O. Box 10, Bellingham, Washington 98227-0010 USA
Pages	127830E-1 - 127830E-7
Number of pages	7
Volume	12783
ISBN (Electronic)	9781510668171
Publication status	Published - 24 Aug 2023
Event	The 2023 International Conference on Images, Signals, and Computing - Chengdu, China Duration: 27 May 2023 → 29 May 2023

Conference

Conference	The 2023 International Conference on Images, Signals, and Computing
Abbreviated title	ICISC
Country/Territory	China
Period	27/05/23 → 29/05/23

Research Field

Former Research Field - New Sensor Technologies

Keywords

sensor fusion
acoustics
security

Access to Document

litzenberger-icisc-2023-submissionFinal published version, 469 KB

Cite this

@inproceedings{3fec67531c804e85a2e553563c8be5c8,

title = "Multi-Sensor Fusion for the Security Surveillance of Public Areas",

abstract = "Increasing security awareness in the public sector are leading to a more and more widespread use of surveillance applications. Although the available technologies like video processing are already well advanced, they still suffer from high false alarm rates when used under realistic conditions. We present a method for sensor fusion based on probability density maps and a rule engine. The system was tested in a public area using the combination of audio localization, audio classification and video detection using 79 simulated scenarios and 44 hours of sample data recorded over a period of several weeks. The false positive rate decreased by 60% and the event localization rate increased by 25% with the fusion approach compared to the detection performance of individual techniques.",

keywords = "sensor fusion, acoustics, security",

author = "Martin Litzenberger and Kilian Wohlleben and Michael Hubner and Bernhard Kohn",

year = "2023",

month = aug,

day = "24",

language = "English",

isbn = "9781510668171",

volume = "12783",

pages = "127830E--1 -- 127830E--7",

booktitle = "PROCEEDINGS OF SPIE",

note = "The 2023 International Conference on Images, Signals, and Computing, ICISC ; Conference date: 27-05-2023 Through 29-05-2023",

}

Litzenberger, M , Wohlleben, K , Hubner, M & Kohn, B 2023, Multi-Sensor Fusion for the Security Surveillance of Public Areas. in PROCEEDINGS OF SPIE: International Conference on Images, Signals, and Computing (ICISC 2023). vol. 12783, 127830E, P.O. Box 10, Bellingham, Washington 98227-0010 USA, pp. 127830E-1 - 127830E-7, The 2023 International Conference on Images, Signals, and Computing, China, 27/05/23.

Multi-Sensor Fusion for the Security Surveillance of Public Areas. / Litzenberger, Martin (Speaker); Wohlleben, Kilian ; Hubner, Michael et al.
PROCEEDINGS OF SPIE: International Conference on Images, Signals, and Computing (ICISC 2023). Vol. 12783 P.O. Box 10, Bellingham, Washington 98227-0010 USA, 2023. p. 127830E-1 - 127830E-7 127830E.

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

TY - GEN

T1 - Multi-Sensor Fusion for the Security Surveillance of Public Areas

AU - Wohlleben, Kilian

AU - Hubner, Michael

AU - Kohn, Bernhard

A2 - Litzenberger, Martin

PY - 2023/8/24

Y1 - 2023/8/24

N2 - Increasing security awareness in the public sector are leading to a more and more widespread use of surveillance applications. Although the available technologies like video processing are already well advanced, they still suffer from high false alarm rates when used under realistic conditions. We present a method for sensor fusion based on probability density maps and a rule engine. The system was tested in a public area using the combination of audio localization, audio classification and video detection using 79 simulated scenarios and 44 hours of sample data recorded over a period of several weeks. The false positive rate decreased by 60% and the event localization rate increased by 25% with the fusion approach compared to the detection performance of individual techniques.

AB - Increasing security awareness in the public sector are leading to a more and more widespread use of surveillance applications. Although the available technologies like video processing are already well advanced, they still suffer from high false alarm rates when used under realistic conditions. We present a method for sensor fusion based on probability density maps and a rule engine. The system was tested in a public area using the combination of audio localization, audio classification and video detection using 79 simulated scenarios and 44 hours of sample data recorded over a period of several weeks. The false positive rate decreased by 60% and the event localization rate increased by 25% with the fusion approach compared to the detection performance of individual techniques.

KW - sensor fusion

KW - acoustics

KW - security

M3 - Conference Proceedings with Oral Presentation

SN - 9781510668171

SN - 9781510668164

VL - 12783

SP - 127830E-1 - 127830E-7

BT - PROCEEDINGS OF SPIE

CY - P.O. Box 10, Bellingham, Washington 98227-0010 USA

T2 - The 2023 International Conference on Images, Signals, and Computing

Y2 - 27 May 2023 through 29 May 2023

ER -

Multi-Sensor Fusion for the Security Surveillance of Public Areas

Abstract

Conference

Research Field

Keywords

Access to Document

Fingerprint

Cite this