Abstract
We applied a method for self-organizing network to gesture motion images. We extract both so-called common parts and singular parts of gesture by analysis of the network topology. We call these parts to elemental motion units. In this paper, we propose a method to extract elemental motion units from gesture motion images and a gesture recognition method of a large vocabulary on the basis of recognition of elemental motion units. When recognizing gestures in time-varying motion images, the usual adopted method has been to distinguish different kind of gestures from a series of movie or images. However when a gesture targeted for recognition has an extensive vocabulary, the recognition of that gesture with an extended version of the usual method is difficult. So we use elemental motion unit to recognize gestures with large vocabulary. We have already proposed the incremental path method that is one of self-organizing network method. This method is constructing an incremental network structure given an input sequence. We applied this method to gesture motion images, so that we extract common parts in some gestures and singular parts. We show detail of incremental path method in section 11.5 and Automated extraction method in section 11.6. At last we describe new gesture recognition method using this elemental motion units and conclusion.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
T.Endo,H.Takahashi,J.Toyoura and R.Oka.: “Video image modeling based on a self-organizing network and visualization of dynamic features.” Technical report of IEICE-PRMU, 97 (78): 49–54, July 1997.
J.Toyoura and R.Oka. “Self-organizing network for transforming text into knowledge base.” Technical report of IEICE-NLC, 59 (96), March 1997.
R.Oka, Y.Ito, J.Kiyama and J.X.Zhang. “Concept spotting by image automaton.” Proc. of The Acoustical Society of Japan, pages 67–68, March,1995.
J.Yamato,J.Ohya and K.Ishii. “Recognizing human action in time-sequential images using hidden markov model.” Proc. CVPR, pages 379385, 1992.
S.Nagaya, S.Seki and R.Oka. “A proposal of gesture trajectory feature for gesture spotting recognition.” Technical report of IEICE-PRU, 95 (142): 45–50, October 1995.
Y.Ito, J.Kiyama, H.Kojima, S.Seki and R.Oka. “Reference interval-free continuous dynamic programming(rifcdp) for spotting speech waves by arbitrary parts of a reference pattern.” Technical report of IEICE-SP, 95 (34): 73–80, June 1995.
M.Nakazawa,T.Endo,K.Furukawa,J.Toyoura and R.Oka. “A study on speech summary using demi-phoneme symbols generated from speech waves.” Technical report of IPSJ-SLP, 97 (15): 119–124, 1997.
T.J.Darell and A.P.Pentland. “Space-time gestures.” Proc. of IJCAI ‘83 Looking at People Workshop, 1993.
H.Ishii, k.Mochizuki and F.Kishino“A Motion Recognition Method from Stereo Images for Human Image Synthesis.” The Trans. of the EIC, vol. J 76-D-II, no.8, p p 1805–1812,1993.
K.Takahashi, S,Seki, H.Kojima and R.Oka. “Spotting Recognition of Human Gesture from Time-varying motion images.” Trans. of IEICE(DII), J77-D-II,No. 8,pp 1552–1561, 1994
S.Seki, H.Kojima, S.Nagaya and R.Oka.“Efficient gesture recognition algorithm based of Continuous Dynamic Programming. ” Proc. of RWC Symposium Technical Report,pp 47–48, 1995
Sakaguchi, Ohya and Kishino. “Facial Expression Recognition from Image Sequence Using Hidden Markov Model.” The Journal of the institute of Television Engineers of Japan, 49–8,pp 1060–1067, 1995
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Physica-Verlag Heidelberg
About this chapter
Cite this chapter
Mukai, T., Nishimura, T., Endo, T., Oka, R. (2001). A Symbol Grounding Problem of Gesture Motion through a Self-organizing Network of Time-varying Motion Images. In: Furuhashi, T., Tano, S., Jacobsen, HA. (eds) Deep Fusion of Computational and Symbolic Processing. Studies in Fuzziness and Soft Computing, vol 59. Physica, Heidelberg. https://doi.org/10.1007/978-3-7908-1837-6_11
Download citation
DOI: https://doi.org/10.1007/978-3-7908-1837-6_11
Publisher Name: Physica, Heidelberg
Print ISBN: 978-3-662-00373-2
Online ISBN: 978-3-7908-1837-6
eBook Packages: Springer Book Archive