Action Recognition Online with Hierarchical Self-Organizing Maps

Zahra Gharaee; Peter Gardenfors; Magnus Johnsson

doi:10.1109/SITIS.2016.91

Action Recognition Online with Hierarchical Self-Organizing Maps

Zahra Gharaee, Peter Gardenfors, Magnus Johnsson

Forskningsoutput: Konferensbidrag › Arbetsdokument (paper) › Peer review

10 Citeringar (Scopus)

Sammanfattning

We present a hierarchical self-organizing map based system for online recognition of human actions. We have made a first evaluation of our system by training it on two different sets of recorded human actions, one set containing manner actions and one set containing result actions, and then tested it by letting a human performer carry out the actions online in real time in front of the system's 3D-camera. The system successfully recognized more than 94% of the manner actions and most of the result actions carried out by the human performer.

Originalspråk	Engelska
Sidor	538-544
Antal sidor	7
DOI	https://doi.org/10.1109/SITIS.2016.91
Status	Publicerad - 2017-apr.-21
Externt publicerad	Ja
Evenemang	12th International Conference on Signal Image Technology and Internet-Based Systems, SITIS 2016 - Naples, Italien Varaktighet: 2016-nov.-28 → 2016-dec.-01

Konferens

Konferens	12th International Conference on Signal Image Technology and Internet-Based Systems, SITIS 2016
Land/Territorium	Italien
Ort	Naples
Period	16-11-28 → 16-12-01

Nationell ämneskategori

Elektroteknik och elektronik (202)

Åtkomst av dokument

10.1109/SITIS.2016.91

Citera det här

@conference{c51f74a1b09542228e4c61c3ece1237a,

title = "Action Recognition Online with Hierarchical Self-Organizing Maps",

abstract = "We present a hierarchical self-organizing map based system for online recognition of human actions. We have made a first evaluation of our system by training it on two different sets of recorded human actions, one set containing manner actions and one set containing result actions, and then tested it by letting a human performer carry out the actions online in real time in front of the system's 3D-camera. The system successfully recognized more than 94% of the manner actions and most of the result actions carried out by the human performer.",

keywords = "Action Recognition, Conceptual Space, Hierarchical Model, Manner Action, Neural Network, Result Action, Self-Organizing Map",

author = "Zahra Gharaee and Peter Gardenfors and Magnus Johnsson",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 12th International Conference on Signal Image Technology and Internet-Based Systems, SITIS 2016 ; Conference date: 28-11-2016 Through 01-12-2016",

year = "2017",

month = apr,

day = "21",

doi = "10.1109/SITIS.2016.91",

language = "English",

pages = "538--544",

}

TY - CONF

T1 - Action Recognition Online with Hierarchical Self-Organizing Maps

AU - Gharaee, Zahra

AU - Gardenfors, Peter

AU - Johnsson, Magnus

PY - 2017/4/21

Y1 - 2017/4/21

N2 - We present a hierarchical self-organizing map based system for online recognition of human actions. We have made a first evaluation of our system by training it on two different sets of recorded human actions, one set containing manner actions and one set containing result actions, and then tested it by letting a human performer carry out the actions online in real time in front of the system's 3D-camera. The system successfully recognized more than 94% of the manner actions and most of the result actions carried out by the human performer.

AB - We present a hierarchical self-organizing map based system for online recognition of human actions. We have made a first evaluation of our system by training it on two different sets of recorded human actions, one set containing manner actions and one set containing result actions, and then tested it by letting a human performer carry out the actions online in real time in front of the system's 3D-camera. The system successfully recognized more than 94% of the manner actions and most of the result actions carried out by the human performer.

KW - Action Recognition

KW - Conceptual Space

KW - Hierarchical Model

KW - Manner Action

KW - Neural Network

KW - Result Action

KW - Self-Organizing Map

U2 - 10.1109/SITIS.2016.91

DO - 10.1109/SITIS.2016.91

M3 - Paper

AN - SCOPUS:85019192205

SP - 538

EP - 544

T2 - 12th International Conference on Signal Image Technology and Internet-Based Systems, SITIS 2016

Y2 - 28 November 2016 through 1 December 2016

ER -

Action Recognition Online with Hierarchical Self-Organizing Maps

Sammanfattning

Konferens

Nationell ämneskategori

Åtkomst av dokument

Fingeravtryck

Citera det här