Abstract
This paper proposes a novel approach based on spiking neural networks to recognize human actions in videos. In our method, a star skeleton detector is designed to extract spatial features of input videos, and a classifier using evolving ReSuMe algorithm is proposed, with scale and shift invariance, to recognize input patterns. In learning algorithm, the remote supervised learning method(ReSuMe) is improved by the particle swarm optimization(PSO) algorithm. Experimental results on KTH and Weizmann dataset prove that our method achieves a significant improvement in performance compared with traditional ReSuMe and other method based on neural networks.
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
Petridis, V., Deb, B., et al.: Detection and Identification of Human Actions Using Predictive Modular Neural Networks. In: 17th Mediterranean Conference on Control & Automation, pp. 406–411. IEEE Press, Thessaloniki (2009)
Meng, Y., Jin, Y., et al.: Modeling Activity-Dependent Plasticity in BCM Spiking Neural Networks with Application to Human Behavior Recognition. IEEE Transactions on Neural Networks 22, 1952–1966 (2011)
Escobar, M.-J., Masson, G.S., et al.: Action Recognition Using a Bio-Inspired Feedforward Spiking Network. International Journal of Computer Vision 82, 284–301 (2009)
Chen, H.S., Chen, H.T., et al.: Human Action Recognition using star skeleton. In: 4th ACM International Workshop on Video Surveillance and Sensor Networks, pp. 171–178. ACM Press, Santa Barbara (2006)
Gerstner, W., Kistler, W.M.: Spiking Nerual Models: Single Neurons, Populations, Plasticity. Cambridge University Press, Cambridge (2002)
Ponulak, F., Kasiński, A.: Supervised Learning in Spiking Nerual Networks with ReSuMe: Sequence Learning, Classification, and Spike Shifting. Neural Computation 22, 467–510 (2010)
Poli, R.: Analysis of the Publications on the Applications of Particle Swarm Optimisation. Journal of Artificial Evolution and Applications 2008, 1–10 (2008)
Han, J., Kamber, M.: Data Mining: Concepts and Techniques. Morgan Kaufmann, San Francisco (2011)
Schüldt, C., Laptev, I., et al.: Recognizing Human Actions: A Local SVM Approach. In: 17th International Conference on Pattern Recognition, pp. 32–36. IEEE Press, Cambridge (2004)
Viola, P., Jones, M.J., et al.: Detecting pedestrians using patterns of motion and appearance. In: 9th IEEE International Conference in Computer Vision, pp. 734–741. IEEE Press, Cambridge (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Xie, X., Qu, H., Liu, G., Liu, L. (2014). Recognizing Human Actions by Using the Evolving Remote Supervised Method of Spiking Neural Networks. In: Loo, C.K., Yap, K.S., Wong, K.W., Teoh, A., Huang, K. (eds) Neural Information Processing. ICONIP 2014. Lecture Notes in Computer Science, vol 8834. Springer, Cham. https://doi.org/10.1007/978-3-319-12637-1_46
Download citation
DOI: https://doi.org/10.1007/978-3-319-12637-1_46
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-12636-4
Online ISBN: 978-3-319-12637-1
eBook Packages: Computer ScienceComputer Science (R0)