Abstract
Multiple timescale recurrent neural network (MTRNN) model is a useful tool to model a continuous signal for a dynamic task such as human action recognition. Different setting of initial states in the MTRNN brings us convenience to predict multiple signals using the same network model. On the contrary, optimal switching for suitable initial states in the slow context unit of the MTRNN becomes critical condition to achieve desired multiple dynamic tasks. In this paper, we propose a hybrid neural network model combining the MTRNN with a deep learning neural network (DN), which is to overcome the problem related to the initial state setting in the MTRNN. The DN together with MTRNN generates a suitable initial state for the slow context units in the MTRNN according to automatically detected situation change. We apply our approach to 20 motion skeleton units, which is obtained by KINECT, to construct three kinds of human motion sequences. The results show that the proposed method is able to recognize various motions using proper initial state information in a real-time procedure.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Cruz, L., Djalma, L., Luiz, V.: Kinect and RGBD Images: Challenges and Applications. In: 2012 25th SIBGRAPI Conference on Graphics, Patterns and Images Tutorials, pp. 22–25 (2012)
Laptev, I., Lindeberg, T.: Tracking of Multi-state Hand Models Using Particle Filtering and a Hierarchy of Multi-scale Image Features. In: Kerckhove, M. (ed.) Scale-Space 2001. LNCS, vol. 2106, pp. 63–74. Springer, Heidelberg (2001)
Li, P., Bouzerdoum, A., Phung, S.L.: Adaptive Autoregressive Logarithmic Search for 3D Human Tracking. In: 2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance (AVSS), pp. 18–21 (2012)
Poppe, R.: A survey on vision-based human action recognition. Image and Vision Computing 28(6), 976–990 (2010)
Wei, W., Yunxiao, A.: Vision-based human motion recognition: A Survey. In: 2009 Second International Conference on Intelligent Networks and Intelligent Systems, Tianjin, China, pp. 1–3 (2009)
Kendon, A.: Conducting Interaction: Patterns of behavior in focused encounters. Cambridge University Press, Cambridge (1990)
Joslin, C., El-Sawah, A., Chen, Q., Georganas, N.: Dynamic Gesture Recognition. In: Instrumentation and Measurement Technology Conference 2005, Ottawa, Canada, pp. 17–19 (2005)
Fukushima, K.: Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological Cybernetics 36(4), 93–202 (1980)
Hinton, G.E., Osindero, S., Teh, Y.: A fast learning algorithm for deep belief nets. Neural Computation 18(7), 1527–1554 (2006)
Behnke, S.: Hierarchical Neural Networks for Image Interpretation (2003)
Yamashita, Y., Tani, J.: Emergence of functional hierarchy in a multiple timescale neural network model: a humanoid robot experiment. PLoS Computational Biology 4(11) (2008)
Cleeremans, A., Servan-Schreiber, D., McClelland, J.L.: Finite state automata and simple recurrent networks. Neural Computation 1(3), 372–381 (1989)
Hinoshita, W., Arie, H., Tani, J., Okuno, H.G., Ogata, T.: Emergence of hierarchical structure mirroring linguistic composition in a recurrent neural network. Neural Networks 24(4), 311–320 (2011)
Kohonen, T.: Self-Organized Formation of Topologically Correct Feature Maps. Biological Cybernetics 43(1), 59–69 (1982)
Doya, K., Yoshizawa, S.: Adaptive neural oscillator using continuous-time back-propagation learning. Neural Networks 2, 375–386 (1989)
Zhang, Y., Ogata, T., Takahashi, T., Okuno, H.G.: Dynamic Recognition of Environmental Sounds with Recurrent Neural Network. In: The 28th Annual Conference of the Robotics Society of Japan, Nagoya, Japan (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yu, Z., Lee, M. (2013). Continuous Motion Recognition Using Multiple Time Constant Recurrent Neural Network with a Deep Network Model. In: Yin, H., et al. Intelligent Data Engineering and Automated Learning – IDEAL 2013. IDEAL 2013. Lecture Notes in Computer Science, vol 8206. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41278-3_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-41278-3_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41277-6
Online ISBN: 978-3-642-41278-3
eBook Packages: Computer ScienceComputer Science (R0)