Decomposition of human motion into dynamic based primitives with application to drawing tasks

Decomposition of human motion into dynamic based primitives with application to drawing tasks (2002)

Cached

Download Links

[www.cds.caltech.edu]

by D. Del Vecchio , R. M. Murray , P. Perona

Citations:

5 - 1 self

Versions

Version History

Metadata Version 0

Datum	Value	Source
TITLE	Decomposition of Human Motion into Dynamics Based Primitives with Application to Drawing Tasks	SVM HeaderParse 0.2
AUTHOR NAME	D. Del Vecchio	SVM HeaderParse 0.2
AUTHOR AFFIL	Division of Engineering and Applied Science; 1200 E. California Boulevard mail stop 107-81; California Institute of Technology	SVM HeaderParse 0.2
AUTHOR ADDR	Pasadena, CA 91125	SVM HeaderParse 0.2
AUTHOR NAME	R. M. Murray	SVM HeaderParse 0.2
AUTHOR AFFIL	Division of Engineering and Applied Science; 1200 E. California Boulevard mail stop 107-81; California Institute of Technology	SVM HeaderParse 0.2
AUTHOR ADDR	Pasadena, CA 91125	SVM HeaderParse 0.2
AUTHOR NAME	P. Perona	SVM HeaderParse 0.2
AUTHOR AFFIL	Division of Engineering and Applied Science; 1200 E. California Boulevard mail stop 107-81; California Institute of Technology	SVM HeaderParse 0.2
AUTHOR ADDR	Pasadena, CA 91125	SVM HeaderParse 0.2
ABSTRACT	Using tools from dynamical systems and systems identification we develop a framework for the study of primitives for human motion, which we refer to as movemes. The objective is understanding human motion by decomposing it into a sequence of elementary building blocks that belong to a known alphabet of dynamical systems. In this work we define conditions under which a class of dynamical models is able to represent a given collection of trajectories as different movemes, and we refer to these conditions as well-posedness. Based on the assumption of well-posedness, we develop segmentation and classification algorithms in order to reduce a complex activity into the sequence of movemes that have generated it. Using examples we show that the definition of well-posedness can be applied in practice and show analytically that the proposed algorithms are robust with respect to noise and model uncertainty. We test our ideas on data sampled from five human subjects who were drawing figures using a computer mouse. Our experiments show that we are able to distinguish between movemes and recognize them even when they take place in activities containing more than one moveme at a time.	SVM HeaderParse 0.2
CITATIONS	24 found	ParsCit 1.0