An Expandable Hardware Platform for Implementation of CNN-Based Applications

  • J. Javier Martínez-Álvarez
  • F. Javier Garrigós-Guerrero
  • F. Javier Toledo-Moreo
  • J. Manuel Ferrández-Vicente
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6687)


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.


Video Stream Output Port Input Port Cellular Neural Network Register Bank 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Harrer, H., Nossek, J., Stelzl, R.: An analog implementation of discrete-time cellular neural networks. IEEE Transactions on Neural Networks 3, 466–476 (1992)CrossRefGoogle Scholar
  2. 2.
    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)Google Scholar
  3. 3.
    Paasio, A., Dawidziuk, A., Porra, V.: A QCIF Resolution Binary I/O CNN-UM Chip. J. VLSI Signal Processing Systems 23, 281–290 (1999)CrossRefGoogle Scholar
  4. 4.
    Malki, S., Spaanenburg, L.: CNN Image Processing on a Xilinx Virtex-II 6000. In: Proceedings ECCTD 2003, Krakow, pp. 261–264 (2003)Google Scholar
  5. 5.
    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)CrossRefGoogle Scholar
  6. 6.
    AnaFocus Ltd. (2004), eye-RIS v1.0/v2.0 Datasheet
  7. 7.
    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)CrossRefGoogle Scholar
  8. 8.
    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)CrossRefGoogle Scholar
  9. 9.
    Nagy, Z., Szolgay, P.: Configurable multilayer CNN-UM emulator on FPGA. IEEE Trans. on Circuits and Systems I 50(6), 774–778 (2003)CrossRefGoogle Scholar
  10. 10.
    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)Google Scholar
  11. 11.
    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)Google Scholar
  12. 12.
    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)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • J. Javier Martínez-Álvarez
    • 1
  • F. Javier Garrigós-Guerrero
    • 1
  • F. Javier Toledo-Moreo
    • 1
  • J. Manuel Ferrández-Vicente
    • 1
  1. 1.Dpto. Electrónica, Tecnología de Computadoras y ProyectosUniversidad Politécnica de CartagenaCartagenaSpain

Personalised recommendations