Parametric Primitives for Hand Gesture Recognition

Sanmohan Baby, Volker Krüger

Research output: Contribution to journalJournal articlepeer-review

Abstract

Imitation learning is considered to be an effective way of teaching humanoid robots and action recognition is the key step to imitation learning. In this paper  an online algorithm to recognize parametric actions with object context is presented. Objects are key instruments in understanding an action when there is uncertainty. Ambiguities arising in similar actions can be resolved with object context. We classify actions according to the changes they make to the object space. Actions that produce the same state change in the object movement space are classified to belong to the same class. This allow us to define several classes of actions where members of each class are connected with a semantic interpretation.
Original languageEnglish
JournalWorld Academy of Science, Engineering and Technology. Proceedings
Volume58
Pages (from-to)97-101
Number of pages4
ISSN2070-3740
Publication statusPublished - 2009
EventInternational Conference on Intelligent Control, Robotics, and Automation - Venice, Italy
Duration: 28 Oct 200930 Oct 2009

Conference

ConferenceInternational Conference on Intelligent Control, Robotics, and Automation
Country/TerritoryItaly
CityVenice
Period28/10/200930/10/2009

Keywords

  • Parametric actions, Action primitives, Hand gesture recognition, Imitation learning.

Fingerprint

Dive into the research topics of 'Parametric Primitives for Hand Gesture Recognition'. Together they form a unique fingerprint.

Cite this