Sciweavers

ICVGIP
2004

Multi-Cue Exemplar-Based Nonparametric Model for Gesture Recognition

13 years 5 months ago
Multi-Cue Exemplar-Based Nonparametric Model for Gesture Recognition
This paper presents an approach for a multi-cue, viewbased recognition of gestures. We describe an exemplarbased technique that combines two different forms of exemplars - shape exemplars and motion exemplars - in a unified probabilistic framework. Each gesture is represented as a sequence of learned body poses as well as a sequence of learned motion parameters. The shape exemplars are comprised of pose contours, and the motion exemplars are represented as affine motion parameters extracted using a robust estimation approach. The probabilistic framework learns by employing a nonparametric estimation technique to model the exemplar distributions. It imposes temporal constraints between different exemplars through a learned Hidden Markov Model (HMM) for each gesture. We use the proposed multi-cue approach to recognize a set of fourteen gestures and contrast it against a shape only, singlecue based system.
Vinay D. Shet, V. Shiv Naga Prasad, Ahmed M. Elgam
Added 31 Oct 2010
Updated 31 Oct 2010
Type Conference
Year 2004
Where ICVGIP
Authors Vinay D. Shet, V. Shiv Naga Prasad, Ahmed M. Elgammal, Yaser Yacoob, Larry S. Davis
Comments (0)