Online Recognition of Actions Involving Objects

Forskningsoutput: TidskriftsbidragArtikel i vetenskaplig tidskrift

Abstract

We present an online system for real time recognition of actions involving objects working in online mode. The system merges two streams of information pro- cessing running in parallel. One is carried out by a hierarchical self-organizing map (SOM) system that recognizes the performed actions by analysing the spa- tial trajectories of the agent’s movements. It consists of two layers of SOMs and a custom made supervised neural network. The activation sequences in the first layer SOM represent the sequences of significant postures of the agent during the performance of actions. These activation sequences are subsequently recoded and clustered in the second layer SOM, and then labeled by the ac- tivity in the third layer custom made supervised neural network. The second information processing stream is carried out by a second system that determines which object among several in the agent’s vicinity the action is applied to. This is achieved by applying a proximity measure. The presented method combines the two information processing streams to determine what action the agent per- formed and on what object. The action recognition system has been tested with excellent performance.

Detaljer

Författare
Enheter & grupper
Externa organisationer
  • University of Technology Sydney
  • National Research Nuclear University MEPhI
Forskningsområden

Ämnesklassifikation (UKÄ) – OBLIGATORISK

  • Data- och informationsvetenskap

Nyckelord

Originalspråkengelska
Sidor (från-till)10-19
TidskriftBiologically Inspired Cognitive Architectures
Volym22
Tidigt onlinedatum2017 okt 10
StatusPublished - 2017
Peer review utfördJa

Related projects

Visa alla (3)