Implementation of a Modular Growing When Required Neural Gas Architecture for Recognition of Falls

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F16%3A00306982" target="_blank" >RIV/68407700:21230/16:00306982 - isvavai.cz</a>

Výsledek na webu

<a href="http://link.springer.com/chapter/10.1007%2F978-3-319-46687-3_58" target="_blank" >http://link.springer.com/chapter/10.1007%2F978-3-319-46687-3_58</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-46687-3_58" target="_blank" >10.1007/978-3-319-46687-3_58</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Implementation of a Modular Growing When Required Neural Gas Architecture for Recognition of Falls

Popis výsledku v původním jazyce

In this paper we aim for the replication of a state of the art architecture for recognition of human actions using skeleton poses obtained from a depth sensor. We review the usefulness of accurate human action recognition in the field of robotic elderly care, focusing on fall detection. We attempt fall recognition using a chained Growing When Required neural gas classifier that is fed only skeleton joints data. We test this architecture against Recurrent SOMs (RSOMs) to classify the TST Fall detection database ver. 2, a specialised dataset for fall sequences. We also introduce a simplified mathematical model of falls for easier and faster bench-testing of classification algorithms for fall detection. The outcome of classifying falls from our mathematical model was successful with an accuracy of 97.12±1.65% and from the TST Fall detection database ver. 2 with an accuracy of 90.2±2.68% when a filter was added.

Název v anglickém jazyce

Implementation of a Modular Growing When Required Neural Gas Architecture for Recognition of Falls

Popis výsledku anglicky

In this paper we aim for the replication of a state of the art architecture for recognition of human actions using skeleton poses obtained from a depth sensor. We review the usefulness of accurate human action recognition in the field of robotic elderly care, focusing on fall detection. We attempt fall recognition using a chained Growing When Required neural gas classifier that is fed only skeleton joints data. We test this architecture against Recurrent SOMs (RSOMs) to classify the TST Fall detection database ver. 2, a specialised dataset for fall sequences. We also introduce a simplified mathematical model of falls for easier and faster bench-testing of classification algorithms for fall detection. The outcome of classifying falls from our mathematical model was successful with an accuracy of 97.12±1.65% and from the TST Fall detection database ver. 2 with an accuracy of 90.2±2.68% when a filter was added.

Druh

D - Stať ve sborníku

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2016

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

23rd International Conference, ICONIP 2016, Kyoto, Japan, October 16–21, 2016, Proceedings, Part I

ISBN

978-3-319-46686-6

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

9

Strana od-do

526-534

Název nakladatele

Springer International Publishing

Místo vydání

Cham

Místo konání akce

Kyoto

Datum konání akce

16. 10. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000389805900058