Kalman filter-based aggressive behaviour detection for indoor environment

Mohd Asyraf Zulkifley, Nur Syazwani Samanu, Nik Ahmad Akram Nik Zulkepeli, Zulaikha Kadim, Hon Hock Woon

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

The Automated video surveillance system is a very important modern tool, especially with the rising popularity of Internet of Things (IoT). The number of connected video cameras available for surveillance application keeps increasing, where even a low resolution mobile phone camera has been used to serve this purpose. For an enclosed room, one of the most important surveillance functions is to detect automatically aggressive behaviour, so that any verbal or physical fight can be stopped immediately. Moreover, an automated aggressive behaviour detection system is also suitable to be implemented in confinement room and prison, where an aggressive behaviour is more likely to occur. Aggressive behaviour can simply be defined as any behaviour that can potentially cause harm to the victim, either physically or mentally. Thus, this paper proposes a Kalman filter-based automated aggressive behaviour detection system by using average optical flow information. A filtered optical flow velocity by using background subtraction will be the input to Gaussian distribution to model the tracker observation. A bi-state tracker; normal and aggressive states will be tracked throughout the video, where the detection decision of each frame is dependent on either the smoothed normal state or smoothed aggressive state is bigger. Accuracy of the proposed system is moderate as the best performance is just 0.75, while the sensitivity performance is good with the highest value of 0.85. Hence, the system can be further improved by applying better decision module by embedding spatial information of the optical flow.

Original languageEnglish
Title of host publicationLecture Notes in Electrical Engineering
PublisherSpringer Verlag
Pages829-837
Number of pages9
Volume376
ISBN (Print)9789811005565
DOIs
Publication statusPublished - 2016
EventInternational Conference on Information Science and Applications, ICISA 2016 - Minh City, Viet Nam
Duration: 15 Feb 201618 Feb 2016

Publication series

NameLecture Notes in Electrical Engineering
Volume376
ISSN (Print)18761100
ISSN (Electronic)18761119

Other

OtherInternational Conference on Information Science and Applications, ICISA 2016
CountryViet Nam
CityMinh City
Period15/2/1618/2/16

Fingerprint

Optical flows
Kalman filters
Prisons
Gaussian distribution
Video cameras
Mobile phones
Flow velocity
Cameras

Keywords

  • Aggressive behaviour detection
  • Gaussian modelling
  • Kalman filter
  • Optical flow
  • Video surveillance

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Cite this

Zulkifley, M. A., Samanu, N. S., Nik Zulkepeli, N. A. A., Kadim, Z., & Woon, H. H. (2016). Kalman filter-based aggressive behaviour detection for indoor environment. In Lecture Notes in Electrical Engineering (Vol. 376, pp. 829-837). (Lecture Notes in Electrical Engineering; Vol. 376). Springer Verlag. https://doi.org/10.1007/978-981-10-0557-2_79

Kalman filter-based aggressive behaviour detection for indoor environment. / Zulkifley, Mohd Asyraf; Samanu, Nur Syazwani; Nik Zulkepeli, Nik Ahmad Akram; Kadim, Zulaikha; Woon, Hon Hock.

Lecture Notes in Electrical Engineering. Vol. 376 Springer Verlag, 2016. p. 829-837 (Lecture Notes in Electrical Engineering; Vol. 376).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zulkifley, MA, Samanu, NS, Nik Zulkepeli, NAA, Kadim, Z & Woon, HH 2016, Kalman filter-based aggressive behaviour detection for indoor environment. in Lecture Notes in Electrical Engineering. vol. 376, Lecture Notes in Electrical Engineering, vol. 376, Springer Verlag, pp. 829-837, International Conference on Information Science and Applications, ICISA 2016, Minh City, Viet Nam, 15/2/16. https://doi.org/10.1007/978-981-10-0557-2_79
Zulkifley MA, Samanu NS, Nik Zulkepeli NAA, Kadim Z, Woon HH. Kalman filter-based aggressive behaviour detection for indoor environment. In Lecture Notes in Electrical Engineering. Vol. 376. Springer Verlag. 2016. p. 829-837. (Lecture Notes in Electrical Engineering). https://doi.org/10.1007/978-981-10-0557-2_79
Zulkifley, Mohd Asyraf ; Samanu, Nur Syazwani ; Nik Zulkepeli, Nik Ahmad Akram ; Kadim, Zulaikha ; Woon, Hon Hock. / Kalman filter-based aggressive behaviour detection for indoor environment. Lecture Notes in Electrical Engineering. Vol. 376 Springer Verlag, 2016. pp. 829-837 (Lecture Notes in Electrical Engineering).
@inproceedings{f0ad76ebb63146448216bd7f731528e1,
title = "Kalman filter-based aggressive behaviour detection for indoor environment",
abstract = "The Automated video surveillance system is a very important modern tool, especially with the rising popularity of Internet of Things (IoT). The number of connected video cameras available for surveillance application keeps increasing, where even a low resolution mobile phone camera has been used to serve this purpose. For an enclosed room, one of the most important surveillance functions is to detect automatically aggressive behaviour, so that any verbal or physical fight can be stopped immediately. Moreover, an automated aggressive behaviour detection system is also suitable to be implemented in confinement room and prison, where an aggressive behaviour is more likely to occur. Aggressive behaviour can simply be defined as any behaviour that can potentially cause harm to the victim, either physically or mentally. Thus, this paper proposes a Kalman filter-based automated aggressive behaviour detection system by using average optical flow information. A filtered optical flow velocity by using background subtraction will be the input to Gaussian distribution to model the tracker observation. A bi-state tracker; normal and aggressive states will be tracked throughout the video, where the detection decision of each frame is dependent on either the smoothed normal state or smoothed aggressive state is bigger. Accuracy of the proposed system is moderate as the best performance is just 0.75, while the sensitivity performance is good with the highest value of 0.85. Hence, the system can be further improved by applying better decision module by embedding spatial information of the optical flow.",
keywords = "Aggressive behaviour detection, Gaussian modelling, Kalman filter, Optical flow, Video surveillance",
author = "Zulkifley, {Mohd Asyraf} and Samanu, {Nur Syazwani} and {Nik Zulkepeli}, {Nik Ahmad Akram} and Zulaikha Kadim and Woon, {Hon Hock}",
year = "2016",
doi = "10.1007/978-981-10-0557-2_79",
language = "English",
isbn = "9789811005565",
volume = "376",
series = "Lecture Notes in Electrical Engineering",
publisher = "Springer Verlag",
pages = "829--837",
booktitle = "Lecture Notes in Electrical Engineering",

}

TY - GEN

T1 - Kalman filter-based aggressive behaviour detection for indoor environment

AU - Zulkifley, Mohd Asyraf

AU - Samanu, Nur Syazwani

AU - Nik Zulkepeli, Nik Ahmad Akram

AU - Kadim, Zulaikha

AU - Woon, Hon Hock

PY - 2016

Y1 - 2016

N2 - The Automated video surveillance system is a very important modern tool, especially with the rising popularity of Internet of Things (IoT). The number of connected video cameras available for surveillance application keeps increasing, where even a low resolution mobile phone camera has been used to serve this purpose. For an enclosed room, one of the most important surveillance functions is to detect automatically aggressive behaviour, so that any verbal or physical fight can be stopped immediately. Moreover, an automated aggressive behaviour detection system is also suitable to be implemented in confinement room and prison, where an aggressive behaviour is more likely to occur. Aggressive behaviour can simply be defined as any behaviour that can potentially cause harm to the victim, either physically or mentally. Thus, this paper proposes a Kalman filter-based automated aggressive behaviour detection system by using average optical flow information. A filtered optical flow velocity by using background subtraction will be the input to Gaussian distribution to model the tracker observation. A bi-state tracker; normal and aggressive states will be tracked throughout the video, where the detection decision of each frame is dependent on either the smoothed normal state or smoothed aggressive state is bigger. Accuracy of the proposed system is moderate as the best performance is just 0.75, while the sensitivity performance is good with the highest value of 0.85. Hence, the system can be further improved by applying better decision module by embedding spatial information of the optical flow.

AB - The Automated video surveillance system is a very important modern tool, especially with the rising popularity of Internet of Things (IoT). The number of connected video cameras available for surveillance application keeps increasing, where even a low resolution mobile phone camera has been used to serve this purpose. For an enclosed room, one of the most important surveillance functions is to detect automatically aggressive behaviour, so that any verbal or physical fight can be stopped immediately. Moreover, an automated aggressive behaviour detection system is also suitable to be implemented in confinement room and prison, where an aggressive behaviour is more likely to occur. Aggressive behaviour can simply be defined as any behaviour that can potentially cause harm to the victim, either physically or mentally. Thus, this paper proposes a Kalman filter-based automated aggressive behaviour detection system by using average optical flow information. A filtered optical flow velocity by using background subtraction will be the input to Gaussian distribution to model the tracker observation. A bi-state tracker; normal and aggressive states will be tracked throughout the video, where the detection decision of each frame is dependent on either the smoothed normal state or smoothed aggressive state is bigger. Accuracy of the proposed system is moderate as the best performance is just 0.75, while the sensitivity performance is good with the highest value of 0.85. Hence, the system can be further improved by applying better decision module by embedding spatial information of the optical flow.

KW - Aggressive behaviour detection

KW - Gaussian modelling

KW - Kalman filter

KW - Optical flow

KW - Video surveillance

UR - http://www.scopus.com/inward/record.url?scp=84959118430&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959118430&partnerID=8YFLogxK

U2 - 10.1007/978-981-10-0557-2_79

DO - 10.1007/978-981-10-0557-2_79

M3 - Conference contribution

AN - SCOPUS:84959118430

SN - 9789811005565

VL - 376

T3 - Lecture Notes in Electrical Engineering

SP - 829

EP - 837

BT - Lecture Notes in Electrical Engineering

PB - Springer Verlag

ER -