Advanced

Hierarchical Self-Organizing Maps System for Action Classification

Gharaee, Zahra LU ; Gärdenfors, Peter LU and Johnsson, Magnus LU (2016) ICAART 2017-International Conference on Agents and Artificial Intelligence p.1-8
Abstract
We present a novel action recognition system that is able to learn how to recognize and classify actions. Our system employs a three-layered hierarchy of Self-Organizing Maps together with a supervised neural network for labelling the actions. We have evaluated our system in an experiments consisting of ten different actions from a publicly available data set. The results are encouraging with 83% correctly classified actions based on the actor’s spatial trajectory.
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to conference
publication status
in press
subject
pages
8 pages
conference name
ICAART 2017-International Conference on Agents and Artificial Intelligence
language
English
LU publication?
yes
id
98c8370a-8170-4acb-918e-37cb31933e8b
date added to LUP
2016-12-04 17:31:13
date last changed
2016-12-06 12:07:07
@misc{98c8370a-8170-4acb-918e-37cb31933e8b,
  abstract     = {We present a novel action recognition system that is able to learn how to recognize and classify actions. Our system employs a three-layered hierarchy of Self-Organizing Maps together with a supervised neural network for labelling the actions. We have evaluated our system in an experiments consisting of ten different actions from a publicly available data set. The results are encouraging with 83% correctly classified actions based on the actor’s spatial trajectory.},
  author       = {Gharaee, Zahra and Gärdenfors, Peter and Johnsson, Magnus},
  language     = {eng},
  pages        = {1--8},
  title        = {Hierarchical Self-Organizing Maps System for Action Classification},
  year         = {2016},
}