Del Vecchio, D. and Murray, R. M. and Perona, Pietro (2003) Segmentation of human motion into dynamics based primitives with application to drawing tasks. In: Proceedings of the 2003 American Control Conference. IEEE , Piscataway, NJ, pp. 1816-1823. ISBN 0780378962 http://resolver.caltech.edu/CaltechAUTHORS:20111018-134102626
Full text is not posted in this repository. Consult Related URLs below.
Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20111018-134102626
Using tools from dynamical systems and systems identification we develop a framework for the study of decomposition of human motion. The objective is understanding human motion by decomposing it into a sequence of elementary building blocks, which we refer to as movemes, which belong to a known alphabet of dynamical systems: We develop classification and segmentation algorithms with error analysis and we test them on human drawing data.
|Item Type:||Book Section|
|Additional Information:||© 2003 IEEE. Issue Date: June 4-6, 2003. Date of Current Version: 27 October 2003. This project has been funded in part by the NSF Engineering Research Center for Neuromorphic Systems Engineering (CNSE) at Caltech (NSF9402726). The authors would like to acknowledge the reviewers for providing information about related work.|
|Official Citation:||Del Vecchio, D.; Murray, R.M.; Perona, P.; , "Segmentation of human motion into dynamics based primitives with application to drawing tasks," American Control Conference, 2003. Proceedings of the 2003 , vol.2, no., pp. 1816- 1823, June 4-6, 2003 doi: 10.1109/ACC.2003.1239860 URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1239860&isnumber=27786|
|Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||Tony Diaz|
|Deposited On:||25 Oct 2011 15:19|
|Last Modified:||25 Oct 2011 15:19|
Repository Staff Only: item control page