Summary

Proceedings of the 2013 International Symposium on Nonlinear Theory and its Applications

2013

Session Number:C1L-D

Session:

Number:378

Detection of Spatial-Temporal Events with Delayed CNN Templates

András Horváth,  Tamás Roska,  

pp.378-381

Publication Date:

Online ISSN:2188-5079

DOI:10.15248/proc.2.378

PDF download (1.4MB)

Spatial-temporal event detection is a crucial task in machine-vision and it is usually difficult to be handled efficiently with current algorithms and devices. The human vision system can solve extremely difficult task with simplicity and low power consumption, like looming or detection of moving objects with given speed and direction. In this article we show how cellular neural networks with delayed type templates are capable of detecting certain spatial-temporal events. The detection is done by using continuous dynamics without cutting the input flow into frames. We can observe similar structures, the analogy of delayed type templates in the retina as well, which performs well and efficiently in image processing tasks. Delayed type templates can provide us with even more flexibilities and possibilities in new applications including frameless detection of motion features.

[1] RJ Schalkoff, “Digital image processing and computer vision” John Wiley & Sons, Inc. Publishers - New York, 1989

[2] T. Fulop; A. Zarandy , “Bio-inspired looming direction detection method” IEEE 13th International Workshop on Cellular Nanoscale Networks and their Applications, pg. 1-6, August 2012, Turin, Italy

[3] Frank Werblin, Tamas Roska, Leon O. Chua , “The analogic cellular neural network as a bionic eye” International Journal of Circuit Theory and Applications, Volume 23, Issue 6, pages 541-569, November-December 1995

[4] Chua L.O., Roska T., “Cellular Neural Networks and Visual Computing: Foundations and Applications” University Press, Cambridge, 2002

[5] T. Roska, “Cellular neural networks with nonlinear and delay-type template elements” Proceedings of IEEE International Workshop on Cellular Neural Networks and their Applications, pages 12-25, 1990

[6] Cao J. , “A Set of Stability Criteria for Delayed CNNs” IEEE Transactions on Circuits and Systems I: Regular Papers, Volume 48, pages 494-498, 2001

[7] Athanasios I. Margaris, “On the global stability of time delayed CNNs” Central European Journal of Computer Science, Volume 1, Issue 1, pp 67-100, March 2011

[8] Rodriguez-Vazquez, A, Espejo, S. ; Dominguez-Castron, R. ; Huertas, J.L. ; Sanchez-Sinencio, E. “Current-mode techniques for the implementation of continuous- and discrete-time cellular neural networks” IEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, Volume 40, Issue 3, pp 132-146, March 1993

[9] T. Asai, Y. Kanazawa, T. Hirose, Y. Amemiya “Analog Reaction-Diffusion Chip Imitating Belousov-Zhabotinsky Reaction with Hardware Oregonator Model” Int. Journal of Unconventional Computing, Vol. 1, pp. 123?147, 2005

[10] Gyorgy Csaba, Matt Pufall, Dmitri Nikonov, George Bourianoff, Andras Horvath, Tamas Roska, Wolfgang Porod “Spin Torque Oscillator Models for Applications in Associative Memories” 13th IEEE international workshop on cellular nanoscale networks and applications, Turin, Italy, 2012