Feature Representations for the Recognition of 3D Emblematic Gestures

J. Richarz and G. A. Fink
Proc. Int. Workshop on Human Behavior Understanding, in conjunction with 20th Int. Conf. on Pattern Recognition, 2010.

BibTeX PDF

Abstract

In human-machine interaction, gestures play an important role as input modality for natural and intuitive interfaces. The class of gestures often called ``emblems'' is of special interest since they convey a well-defined meaning in an intuitive way. We present an approach for the visual recognition of 3D dynamic emblematic gestures in a smart room scenario using a HMM-based recognition framework. In particular, we assess the suitability of several feature representations calculated from a gesture trajectory in a detailed experimental evaluation on realistic data.