Sudden fall classification using motion features

Nor Surayahani Suriani, Aini Hussain

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

8 Citations (Scopus)

Abstract

Monitoring of abnormal activities under video surveillance research area is important due to providing comfort and safety living for the society. The popular scenario is to learn pattern of normal activity, and subsequently detect abnormal events in the scene. Instead of detecting abnormal event, we propose to model the sudden change in the event specifically fall event that deviates from the normal activities. We learn the motion features namely, motion history histogram (MHH) and motion geometric distribution (MGD) across image in the frame sequence. Then, we propose a classification strategy using biological inspired feedforward network that can detect sudden abnormalities in the event. We test the algorithm on real dataset and found that our approach is able to distinguish the transition state between walk and fall.

Original languageEnglish
Title of host publicationProceedings - 2012 IEEE 8th International Colloquium on Signal Processing and Its Applications, CSPA 2012
Pages519-524
Number of pages6
DOIs
Publication statusPublished - 2012
Event2012 IEEE 8th International Colloquium on Signal Processing and Its Applications, CSPA 2012 - Melaka
Duration: 23 Mar 201225 Mar 2012

Other

Other2012 IEEE 8th International Colloquium on Signal Processing and Its Applications, CSPA 2012
CityMelaka
Period23/3/1225/3/12

Fingerprint

Monitoring

Keywords

  • Biological Inspired Network
  • Motion geometric distribution (MGD)
  • Motion history histogram (MHH)
  • Sudden fall detection

ASJC Scopus subject areas

  • Signal Processing

Cite this

Suriani, N. S., & Hussain, A. (2012). Sudden fall classification using motion features. In Proceedings - 2012 IEEE 8th International Colloquium on Signal Processing and Its Applications, CSPA 2012 (pp. 519-524). [6194784] https://doi.org/10.1109/CSPA.2012.6194784

Sudden fall classification using motion features. / Suriani, Nor Surayahani; Hussain, Aini.

Proceedings - 2012 IEEE 8th International Colloquium on Signal Processing and Its Applications, CSPA 2012. 2012. p. 519-524 6194784.

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

Suriani, NS & Hussain, A 2012, Sudden fall classification using motion features. in Proceedings - 2012 IEEE 8th International Colloquium on Signal Processing and Its Applications, CSPA 2012., 6194784, pp. 519-524, 2012 IEEE 8th International Colloquium on Signal Processing and Its Applications, CSPA 2012, Melaka, 23/3/12. https://doi.org/10.1109/CSPA.2012.6194784
Suriani NS, Hussain A. Sudden fall classification using motion features. In Proceedings - 2012 IEEE 8th International Colloquium on Signal Processing and Its Applications, CSPA 2012. 2012. p. 519-524. 6194784 https://doi.org/10.1109/CSPA.2012.6194784
Suriani, Nor Surayahani ; Hussain, Aini. / Sudden fall classification using motion features. Proceedings - 2012 IEEE 8th International Colloquium on Signal Processing and Its Applications, CSPA 2012. 2012. pp. 519-524
@inproceedings{4e03ac045a1049cc8bf18ec256e8cb74,
title = "Sudden fall classification using motion features",
abstract = "Monitoring of abnormal activities under video surveillance research area is important due to providing comfort and safety living for the society. The popular scenario is to learn pattern of normal activity, and subsequently detect abnormal events in the scene. Instead of detecting abnormal event, we propose to model the sudden change in the event specifically fall event that deviates from the normal activities. We learn the motion features namely, motion history histogram (MHH) and motion geometric distribution (MGD) across image in the frame sequence. Then, we propose a classification strategy using biological inspired feedforward network that can detect sudden abnormalities in the event. We test the algorithm on real dataset and found that our approach is able to distinguish the transition state between walk and fall.",
keywords = "Biological Inspired Network, Motion geometric distribution (MGD), Motion history histogram (MHH), Sudden fall detection",
author = "Suriani, {Nor Surayahani} and Aini Hussain",
year = "2012",
doi = "10.1109/CSPA.2012.6194784",
language = "English",
isbn = "9781467309615",
pages = "519--524",
booktitle = "Proceedings - 2012 IEEE 8th International Colloquium on Signal Processing and Its Applications, CSPA 2012",

}

TY - GEN

T1 - Sudden fall classification using motion features

AU - Suriani, Nor Surayahani

AU - Hussain, Aini

PY - 2012

Y1 - 2012

N2 - Monitoring of abnormal activities under video surveillance research area is important due to providing comfort and safety living for the society. The popular scenario is to learn pattern of normal activity, and subsequently detect abnormal events in the scene. Instead of detecting abnormal event, we propose to model the sudden change in the event specifically fall event that deviates from the normal activities. We learn the motion features namely, motion history histogram (MHH) and motion geometric distribution (MGD) across image in the frame sequence. Then, we propose a classification strategy using biological inspired feedforward network that can detect sudden abnormalities in the event. We test the algorithm on real dataset and found that our approach is able to distinguish the transition state between walk and fall.

AB - Monitoring of abnormal activities under video surveillance research area is important due to providing comfort and safety living for the society. The popular scenario is to learn pattern of normal activity, and subsequently detect abnormal events in the scene. Instead of detecting abnormal event, we propose to model the sudden change in the event specifically fall event that deviates from the normal activities. We learn the motion features namely, motion history histogram (MHH) and motion geometric distribution (MGD) across image in the frame sequence. Then, we propose a classification strategy using biological inspired feedforward network that can detect sudden abnormalities in the event. We test the algorithm on real dataset and found that our approach is able to distinguish the transition state between walk and fall.

KW - Biological Inspired Network

KW - Motion geometric distribution (MGD)

KW - Motion history histogram (MHH)

KW - Sudden fall detection

UR - http://www.scopus.com/inward/record.url?scp=84861551064&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84861551064&partnerID=8YFLogxK

U2 - 10.1109/CSPA.2012.6194784

DO - 10.1109/CSPA.2012.6194784

M3 - Conference contribution

SN - 9781467309615

SP - 519

EP - 524

BT - Proceedings - 2012 IEEE 8th International Colloquium on Signal Processing and Its Applications, CSPA 2012

ER -