Hierarchical Self-Organizing Maps System for Action Classification

Zahra Gharaee, Peter Gärdenfors, Magnus Johnsson

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceedingResearchpeer-review

5 Citations (SciVal)

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.
Original languageEnglish
Title of host publicationProceedings of the 9th International Conference on Agents and Artificial Intelligence (ICAART 2017)
PublisherSciTePress
Pages583-590
Number of pages8
ISBN (Electronic)978-989-758-220-2
DOIs
Publication statusPublished - 2017
EventICAART 2017-International Conference on Agents and Artificial Intelligence - Holiday Inn Porto Gaia, Porto, Portugal
Duration: 2017 Feb 242017 Feb 26

Conference

ConferenceICAART 2017-International Conference on Agents and Artificial Intelligence
Country/TerritoryPortugal
CityPorto
Period2017/02/242017/02/26

Subject classification (UKÄ)

  • Robotics
  • Computer Systems

Fingerprint

Dive into the research topics of 'Hierarchical Self-Organizing Maps System for Action Classification'. Together they form a unique fingerprint.

Cite this