Live participant´s action recognition for virtual reality interactions

Author

Emering, Luc ; Boulic, Ronan ; Thalmann, Daniel

Author_Institution

Comput. Graphics Lab., Fed. Inst. of Technol., Lausanne, Switzerland

fYear

1997

fDate

13-16 Oct 1997

Firstpage

15

Lastpage

21

Abstract

The recognition of daily human activities is a decisive interface component for more intuitive virtual reality (VR) interactions. In this paper, we describe a hierarchical model of body actions based on fine-grained action primitives. The associated recognition algorithm allows on-the-fly identification of simultaneous actions. Measurements highlight robustness to participants´ variability and high detection rates when using the full potential of the action model. An example illustrates an interaction with a virtual character driven by the participant´s action recognition

Keywords

interactive devices; pattern recognition; pattern recognition equipment; virtual reality; action recognition; body actions identification; daily human activities; detection rates; fine-grained action primitives; hierarchical model; interface component; live participant; recognition algorithm; virtual character; virtual reality interactions; Biological system modeling; Character recognition; Computer graphics; Handicapped aids; Humans; Magnetic sensors; Particle measurements; Robustness; Surges; Virtual reality;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Graphics and Applications, 1997. Proceedings., The Fifth Pacific Conference on

Conference_Location

Seoul

Print_ISBN

0-8186-8028-8

Type

conf

DOI

10.1109/PCCGA.1997.626167

Filename

626167