Recognition of manual actions using vector quantization and dynamic time warping

Martin M, Maycock J, Schmidt F, Krämer O (2010)
In: Proc. 5th Conf. Hybrid Artificial Intelligence Systems. Graña Romay M, Corchado E, Garcia Sebastian MT (Eds);6067. Springer: 221-228.

Conference Paper | Published | English

No fulltext has been uploaded

Author
; ; ;
Editor
Graña Romay, Manuel ; Corchado, Emilio ; Garcia Sebastian, M. Teresa
Abstract
The recognition of manual actions, i.e., hand movements, hand postures and gestures, plays an important role in human-computer interaction, while belonging to a category of particularly difficult tasks. Using a Vicon system to capture 3D spatial data, we investigate the recognition of manual actions in tasks such as pouring a cup of milk and writing into a book. We propose recognizing sequences in multidimensional time-series by first learning a smooth quantization of the data, and then using a variant of dynamic time warping to recognize short sequences of prototypical motions in a long unknown sequence. An experimental analysis validates our approach. Short manual actions are successfully recognized and the approach is shown to be spatially invariant. We also show that the approach speeds up processing while not decreasing recognition performance.
Publishing Year
Conference
Hybrid Artificial Intelligence Systems
Location
HAIS 2010
Conference Date
2010-06-23
PUB-ID

Cite this

Martin M, Maycock J, Schmidt F, Krämer O. Recognition of manual actions using vector quantization and dynamic time warping. In: Graña Romay M, Corchado E, Garcia Sebastian MT, eds. Proc. 5th Conf. Hybrid Artificial Intelligence Systems. Vol 6067. Springer; 2010: 221-228.
Martin, M., Maycock, J., Schmidt, F., & Krämer, O. (2010). Recognition of manual actions using vector quantization and dynamic time warping. In M. Graña Romay, E. Corchado, & M. T. Garcia Sebastian (Eds.), Proc. 5th Conf. Hybrid Artificial Intelligence Systems (Vol. 6067, pp. 221-228). Springer.
Martin, M., Maycock, J., Schmidt, F., and Krämer, O. (2010). “Recognition of manual actions using vector quantization and dynamic time warping” in Proc. 5th Conf. Hybrid Artificial Intelligence Systems, ed. M. Graña Romay, E. Corchado, and M. T. Garcia Sebastian, vol. 6067, (Springer), 221-228.
Martin, M., et al., 2010. Recognition of manual actions using vector quantization and dynamic time warping. In M. Graña Romay, E. Corchado, & M. T. Garcia Sebastian, eds. Proc. 5th Conf. Hybrid Artificial Intelligence Systems. no.6067 Springer, pp. 221-228.
M. Martin, et al., “Recognition of manual actions using vector quantization and dynamic time warping”, Proc. 5th Conf. Hybrid Artificial Intelligence Systems, M. Graña Romay, E. Corchado, and M.T. Garcia Sebastian, eds., vol. 6067, Springer, 2010, pp.221-228.
Martin, M., Maycock, J., Schmidt, F., Krämer, O.: Recognition of manual actions using vector quantization and dynamic time warping. In: Graña Romay, M., Corchado, E., and Garcia Sebastian, M.T. (eds.) Proc. 5th Conf. Hybrid Artificial Intelligence Systems. 6067, p. 221-228. Springer (2010).
Martin, Marcel, Maycock, Jonathan, Schmidt, Florian, and Krämer, Oliver. “Recognition of manual actions using vector quantization and dynamic time warping”. Proc. 5th Conf. Hybrid Artificial Intelligence Systems. Ed. Manuel Graña Romay, Emilio Corchado, and M. Teresa Garcia Sebastian. Springer, 2010.Vol. 6067. 221-228.
This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Search this title in

Google Scholar