Abstract
This paper proposes a standalone system for real-time processing of video streams using CNNs. The computing platform is easily expandable and customizable for any application. This is achieved by using a modular approach both for the CNN architecture itself and for its hardware implementation. Several FPGA-based processing modules can be cascaded together with a video acquisition stage and an output interface to a framegrabber for video output storage, all sharing a common communication interface. The pre-verified CNN components, the modular architecture, and the expandable hardware platform provide an excellent workbench for fast and confident developing of CNN applications.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Harrer, H., Nossek, J., Stelzl, R.: An analog implementation of discrete-time cellular neural networks. IEEE Transactions on Neural Networks 3, 466–476 (1992)
Harrer, H., Nossek, J., Roska, T., Chua, L.: A current-mode DTCNN universal chip. In: IEEE International Symposium on Circuits and Systems, vol. 4, pp. 135–138 (1993)
Paasio, A., Dawidziuk, A., Porra, V.: A QCIF Resolution Binary I/O CNN-UM Chip. J. VLSI Signal Processing Systems 23, 281–290 (1999)
Malki, S., Spaanenburg, L.: CNN Image Processing on a Xilinx Virtex-II 6000. In: Proceedings ECCTD 2003, Krakow, pp. 261–264 (2003)
Rodriguez-Vazquez, A., Linan-Cembrano, G., Carranza, L., Roca-Moreno, E., Carmona-Galan, R., Jimenez-Garrido, F., Dominguez-Castro, R., EMeana, S.: ACE16k: the third generation of mixed-signal SIMD-CNN ACE chips toward VSoCs. IEEE Transactions on Circuits and Systems I 51(5), 851–863 (2004)
AnaFocus Ltd. (2004), http://www.anafocus.com eye-RIS v1.0/v2.0 Datasheet
Martínez, J.J., Garrigós, F.J., Toledo, F.J., Ferrández, J.M.: High performance implementation of an FPGA-based sequential DT-CNN. In: Mira, J., Álvarez, J.R. (eds.) IWINAC 2007. LNCS, vol. 4528, pp. 1–9. Springer, Heidelberg (2007)
Voroshazi, Z., Kiss, A., Nagy, Z., Szolgay, P.: Implementation of embedded emulated-digital CNN-UM global analogic programming unit on FPGA and its application. International Journal of Circuit Theory and Applications 36, 589–603 (2008)
Nagy, Z., Szolgay, P.: Configurable multilayer CNN-UM emulator on FPGA. IEEE Trans. on Circuits and Systems I 50(6), 774–778 (2003)
Laiho, M., Poikonen, J., Virta, P., Paasio, A.: A 64x64 cell mixed-mode array processor prototyping system. In: International Workshop on Cellular Neural Networks and Their Applications, CNNA 2008, pp. 14–16 (2008)
Fujita, T., Okamura, T., Nakanishi, M., Ogura, T.: CAM2-universal machine: A DTCNN implementation for real-time image processing. In: International Workshop on Cellular Neural Networks and Their Applications, CNNA 2008, pp. 219–223 (2008)
Martínez, J.J., Toledo, F.J., Fernández, E., Ferrández, J.M.: A retinomorphic architecture based on discrete-time cellular neural networks using reconfigurable computing. Neurocomputing 71(4-6), 766–775 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Martínez-Álvarez, J.J., Garrigós-Guerrero, F.J., Toledo-Moreo, F.J., Ferrández-Vicente, J.M. (2011). An Expandable Hardware Platform for Implementation of CNN-Based Applications. In: Ferrández, J.M., Álvarez Sánchez, J.R., de la Paz, F., Toledo, F.J. (eds) New Challenges on Bioinspired Applications. IWINAC 2011. Lecture Notes in Computer Science, vol 6687. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21326-7_22
Download citation
DOI: https://doi.org/10.1007/978-3-642-21326-7_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21325-0
Online ISBN: 978-3-642-21326-7
eBook Packages: Computer ScienceComputer Science (R0)