Camera-based fall detection using a particle filter

More than thirty percent of persons over 65 years fall at least once a year and are often not able to get up again. The lack of timely aid after such a fall incident can lead to severe complications. This timely aid can however be assured by a camera-based fall detection system triggering an alarm w...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) Jg. 2015; S. 6947 - 6950
Hauptverfasser: Debard, Glen, Baldewijns, Greet, Goedeme, Toon, Tuytelaars, Tinne, Vanrumste, Bart
Format: Tagungsbericht Journal Article
Sprache:Englisch
Veröffentlicht: United States IEEE 01.01.2015
Schlagworte:
ISSN:1094-687X, 1557-170X, 2694-0604, 2694-0604
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract More than thirty percent of persons over 65 years fall at least once a year and are often not able to get up again. The lack of timely aid after such a fall incident can lead to severe complications. This timely aid can however be assured by a camera-based fall detection system triggering an alarm when a fall occurs. Most algorithms described in literature use the biggest object detected using background subtraction to extract the fall features. In this paper we compare the performance of our state-of-the-art fall detection algorithm when using only background subtraction, when using a particle filter to track the person and a hybrid method in which the particle filter is only used to enhance the background subtraction and not for the feature extraction. We tested this using our simulation data set containing reenactments of real-life falls. This comparison shows that this hybrid method significantly increases the sensitivity and robustness of the fall detection algorithm resulting in a sensitivity of 76.1% and a PPV of 41.2%.
AbstractList More than thirty percent of persons over 65 years fall at least once a year and are often not able to get up again. The lack of timely aid after such a fall incident can lead to severe complications. This timely aid can however be assured by a camera-based fall detection system triggering an alarm when a fall occurs. Most algorithms described in literature use the biggest object detected using background subtraction to extract the fall features. In this paper we compare the performance of our state-of-the-art fall detection algorithm when using only background subtraction, when using a particle filter to track the person and a hybrid method in which the particle filter is only used to enhance the background subtraction and not for the feature extraction. We tested this using our simulation data set containing reenactments of real-life falls. This comparison shows that this hybrid method significantly increases the sensitivity and robustness of the fall detection algorithm resulting in a sensitivity of 76.1% and a PPV of 41.2%.
More than thirty percent of persons over 65 years fall at least once a year and are often not able to get up again. The lack of timely aid after such a fall incident can lead to severe complications. This timely aid can however be assured by a camera-based fall detection system triggering an alarm when a fall occurs. Most algorithms described in literature use the biggest object detected using background subtraction to extract the fall features. In this paper we compare the performance of our state-of-the-art fall detection algorithm when using only background subtraction, when using a particle filter to track the person and a hybrid method in which the particle filter is only used to enhance the background subtraction and not for the feature extraction. We tested this using our simulation data set containing reenactments of real-life falls. This comparison shows that this hybrid method significantly increases the sensitivity and robustness of the fall detection algorithm resulting in a sensitivity of 76.1% and a PPV of 41.2%.More than thirty percent of persons over 65 years fall at least once a year and are often not able to get up again. The lack of timely aid after such a fall incident can lead to severe complications. This timely aid can however be assured by a camera-based fall detection system triggering an alarm when a fall occurs. Most algorithms described in literature use the biggest object detected using background subtraction to extract the fall features. In this paper we compare the performance of our state-of-the-art fall detection algorithm when using only background subtraction, when using a particle filter to track the person and a hybrid method in which the particle filter is only used to enhance the background subtraction and not for the feature extraction. We tested this using our simulation data set containing reenactments of real-life falls. This comparison shows that this hybrid method significantly increases the sensitivity and robustness of the fall detection algorithm resulting in a sensitivity of 76.1% and a PPV of 41.2%.
Author Debard, Glen
Tuytelaars, Tinne
Goedeme, Toon
Vanrumste, Bart
Baldewijns, Greet
Author_xml – sequence: 1
  givenname: Glen
  surname: Debard
  fullname: Debard, Glen
  email: glen.debard@thomasmore.be
  organization: MOBILAB, Thomas More Kempen, Geel, Belgium
– sequence: 2
  givenname: Greet
  surname: Baldewijns
  fullname: Baldewijns, Greet
  organization: Technol. Campus Geel, KU Leuven, Geel, Belgium
– sequence: 3
  givenname: Toon
  surname: Goedeme
  fullname: Goedeme, Toon
  organization: ESAT, KU Leuven, Leuven, Belgium
– sequence: 4
  givenname: Tinne
  surname: Tuytelaars
  fullname: Tuytelaars, Tinne
  organization: ESAT, KU Leuven, Leuven, Belgium
– sequence: 5
  givenname: Bart
  surname: Vanrumste
  fullname: Vanrumste, Bart
  organization: Technol. Campus Geel, KU Leuven, Geel, Belgium
BackLink https://www.ncbi.nlm.nih.gov/pubmed/26737890$$D View this record in MEDLINE/PubMed
BookMark eNo9kDlPw0AUhBcURELID0BIyCWNw9vDe5RghUMKoklBZ63Xb9EiH8FrF_z7WEqgmmK-GWnmiszarkVCbiisKQXzsHl_ytcMaLZWnBpj4IysjNJUMCEMU1SfkwWTRqQgQczIYsqIVGr1OSerGL8BgCopmcguyZxJxZU2sCA8tw32Ni1txCrxtq6TCgd0Q-jaZIyh_Upssrf9EFyNiQ_1gP01uZjAiKuTLsnuebPLX9Ptx8tb_rhNA5NiSJ12WhlhnbdaZpo7L52xwB1oK6SvEEs0XKLx0jDPMig5U5NazzOuHV-S-2Ptvu9-RoxD0YTosK5ti90Yi2kO6CnK6YTendCxbLAq9n1obP9b_O2cgNsjEBDx3z4dyQ_OumJT
ContentType Conference Proceeding
Journal Article
DBID 6IE
6IH
CBEJK
RIE
RIO
CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1109/EMBC.2015.7319990
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Xplore
IEEE Proceedings Order Plans (POP) 1998-present
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE

MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9781424492718
1424492718
EISSN 2694-0604
EndPage 6950
ExternalDocumentID 26737890
7319990
Genre orig-research
Research Support, Non-U.S. Gov't
Journal Article
GroupedDBID 6IE
6IF
6IH
AAJGR
ACGFS
AFFNX
ALMA_UNASSIGNED_HOLDINGS
CBEJK
M43
RIE
RIO
RNS
29F
29G
6IK
6IM
CGR
CUY
CVF
ECM
EIF
IPLJI
NPM
7X8
ID FETCH-LOGICAL-i264t-c8c8794acfa86583cf6c9a03c08a46fdeebe936e9f692f250b327f25af3538c3
IEDL.DBID RIE
ISICitedReferencesCount 15
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000371717207055&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1094-687X
1557-170X
2694-0604
IngestDate Sun Nov 09 13:19:32 EST 2025
Thu Jan 02 22:17:20 EST 2025
Wed Aug 27 02:49:46 EDT 2025
IsPeerReviewed true
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i264t-c8c8794acfa86583cf6c9a03c08a46fdeebe936e9f692f250b327f25af3538c3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 26737890
PQID 1760869231
PQPubID 23479
PageCount 4
ParticipantIDs proquest_miscellaneous_1760869231
pubmed_primary_26737890
ieee_primary_7319990
PublicationCentury 2000
PublicationDate 2015-01-01
PublicationDateYYYYMMDD 2015-01-01
PublicationDate_xml – month: 01
  year: 2015
  text: 2015-01-01
  day: 01
PublicationDecade 2010
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
PublicationTitleAbbrev EMBC
PublicationTitleAlternate Conf Proc IEEE Eng Med Biol Soc
PublicationYear 2015
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0001766245
ssj0020051
ssj0061641
ssib061542107
ssib053545923
ssib042469959
Score 2.1608963
Snippet More than thirty percent of persons over 65 years fall at least once a year and are often not able to get up again. The lack of timely aid after such a fall...
SourceID proquest
pubmed
ieee
SourceType Aggregation Database
Index Database
Publisher
StartPage 6947
SubjectTerms Accidental Falls
Aged
Algorithms
Atmospheric measurements
Detection algorithms
Feature extraction
Filtration - instrumentation
Histograms
Humans
Image color analysis
Photography - instrumentation
Sensitivity
Tracking
Title Camera-based fall detection using a particle filter
URI https://ieeexplore.ieee.org/document/7319990
https://www.ncbi.nlm.nih.gov/pubmed/26737890
https://www.proquest.com/docview/1760869231
Volume 2015
WOSCitedRecordID wos000371717207055&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07b8IwELZo1aFd-oC29IFcqWMNNA5-rEWgLkUMDNkix7ErJBQQhP7-3jkBOrRDpziDndh39n2-JyHPXoNUUUIz7nXG4oHSzOTaMiuc9j6zIKN8KDYhJxOVJHraIC_7WBjnXHA-c11sBlt-vrRbVJX1JMegebigH0kpqlitgz5FChHFhzx7yG3B0qljJpRMaosmvPdGH29DdOoadOsBMSMw1mtR4WTG7_6NN4PcGZ__748vSOsQwEene9F0SRquuCJnP3IPNgkfGtRHMRRjOfVmsaC5K4NjVkHRG_6TGrqqGYv6OVrVW2Q2Hs2G76yuoMDmAHRKZpVVsOGM9UYB1ODWC6tNn9u-MrHwuQMSao5kETrygIYyHkl4Gs_hILT8mhwXy8LdEpojbsx07K0xcRQbI6WV8hXQRV-72ERt0sTZp6sqR0ZaT7xNnnbrmALfojHCFG653aRAL7hNIbxsk5tqgfedd8S4-33Qe3KK1KsUIQ_kuFxv3SM5sV_lfLPuAHMkqhOY4xsnoLNg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NT8IwFH8haKJe_AAVP2vi0QKuox9XCQQjEA4cuC1d1xoSMggM_377xgAPevC07tBu7Xvt-_V9Ajw75aWK5Ioyp2IatqSiOlGGGm6Vc7HxMsrlxSbEcCgnEzUqwcsuFsZamzuf2To2c1t-MjdrVJU1BMOgeX9BP8DKWUW01l6jIjgPwn2mPeS33NapQsqlmBQ2Tf_e6Aze2ujW1aoXQ2JOYKzYIvOzGb_8N-LMJU_39H__fAbVfQgfGe2E0zmUbHoBJz-yD1aAtTVqpCgKsoQ4PZuRxGa5a1ZK0B_-k2iyKFiLuCna1asw7nbG7R4taijQqYc6GTXSSL_ltHFaerDBjONG6SYzTalD7hLriagYEoarwHk8FLNA-Kd2zB-Fhl1COZ2n9hpIgsgxVqEzWodBqLUQRohXjy-ayoY6qEEFZx8tNlkyomLiNXjarmPkORfNETq18_Uq8vTy9ykEmDW42izwrvOWGDe_D_oIR73xoB_134cft3CMlNyoRe6gnC3X9h4OzVc2XS0fchb5BnbItcE
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2015+37th+Annual+International+Conference+of+the+IEEE+Engineering+in+Medicine+and+Biology+Society+%28EMBC%29&rft.atitle=Camera-based+fall+detection+using+a+particle+filter&rft.au=Debard%2C+Glen&rft.au=Baldewijns%2C+Greet&rft.au=Goedeme%2C+Toon&rft.au=Tuytelaars%2C+Tinne&rft.date=2015-01-01&rft.pub=IEEE&rft.issn=1094-687X&rft.spage=6947&rft.epage=6950&rft_id=info:doi/10.1109%2FEMBC.2015.7319990&rft_id=info%3Apmid%2F26737890&rft.externalDocID=7319990
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1094-687X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1094-687X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1094-687X&client=summon