Hierarchical Self-Organizing Maps System for Action Classification

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKonferenspaper i proceeding

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.

Detaljer

Författare
Enheter & grupper
Forskningsområden

Ämnesklassifikation (UKÄ) – OBLIGATORISK

  • Robotteknik och automation
  • Datorsystem
Originalspråkengelska
Titel på värdpublikationProceedings of the 9th International Conference on Agents and Artificial Intelligence (ICAART 2017)
FörlagSciTePress
Sidor583-590
Antal sidor8
ISBN (elektroniskt)978-989-758-220-2
StatusPublished - 2017
PublikationskategoriForskning
Peer review utfördJa
EvenemangICAART 2017-International Conference on Agents and Artificial Intelligence - Holiday Inn Porto Gaia, Porto, Portugal
Varaktighet: 2017 feb 242017 feb 26

Konferens

KonferensICAART 2017-International Conference on Agents and Artificial Intelligence
LandPortugal
OrtPorto
Period2017/02/242017/02/26

Relaterad forskningsoutput

Gharaee, Z., 2018 mar 15, Lund: Lund University Cognitive Science. 166 s.

Forskningsoutput: AvhandlingDoktorsavhandling (sammanläggning)

Visa alla (1)

Related projects

Birger Johansson, Christian Balkenius, Magnus Johnsson, Rasmus Bååth, Stefan Winberg, Zahra Gharaee & Trond Arild Tjøstheim

2001/01/012021/12/31

Projekt: Forskning

Visa alla (2)