Advertisement

Spiking Hough for Shape Recognition

  • Pablo Negri
  • Teresa Serrano-Gotarredona
  • Bernabe Linares-Barranco
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10657)

Abstract

The paper implements a spiking neural model methodology inspired on the Hough Transform. On-line event-driven spikes from Dynamic Vision Sensors are evaluated to characterize and recognize the shape of Poker signs. The multi-class system, referred as Spiking Hough, shows the good performance on the public POKER-DVS dataset.

Notes

Acknowledgements

This work was funded by PID Nro. P16T01 (UADE, Argentine), EU H2020 grants 644096 “ECOMODE” and 687299 “NEURAM3”, and by Spanish grant from the Ministry of Economy and Competitivity TEC2015-63884-C2-1-P (COGNET) (with support from the European Regional Development Fund).

References

  1. 1.
    Anderson, J.: An Indroduction to Neural Networks. MIT Press, Cambridge (1995)Google Scholar
  2. 2.
    Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. IST 2(3) (2011). http://www.csie.ntu.edu.tw/~cjlin/libsvm
  3. 3.
    Clady, X., et al.: A motion-based feature for event-based pattern recognition. Front. Neurosci. 10, 594 (2017)CrossRefGoogle Scholar
  4. 4.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, vol. 1, pp. 886–893 (2005)Google Scholar
  5. 5.
    Lagorce, X., et al.: HOTS: a hierarchy of event-based time-surfaces for pattern recognition. PAMI 39(7), 1346–1359 (2017)CrossRefGoogle Scholar
  6. 6.
    Li, X., et al.: Lane detection based on spiking neural network and hough transform. In: CISP, pp. 626–630 (2015)Google Scholar
  7. 7.
    Lichtsteiner, P., Posch, C., Delbruck, T.: A 128*128 120dB 15us latency asynchronous temporal contrast vision sensor. JSSC 43(2), 566–576 (2008)Google Scholar
  8. 8.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)CrossRefGoogle Scholar
  9. 9.
    Negri, P.: Pedestrian detection using multi-objective optimization. In: Pardo, A., Kittler, J. (eds.) CIARP 2015. LNCS, vol. 9423, pp. 776–784. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-25751-8_93 CrossRefGoogle Scholar
  10. 10.
    Negri, P.: Extended LBP operator to characterize event-address representation connectivity. In: Beltrán-Castañón, C., Nyström, I., Famili, F. (eds.) CIARP 2016. LNCS, vol. 10125, pp. 241–248. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-52277-7_30 CrossRefGoogle Scholar
  11. 11.
    Pérez-Carrasco, J., et al.: Mapping from frame-driven to frame-free event-driven vision systems by low-rate rate coding and coincidence processing-application to feedforward convnets. PAMI 35(11), 2706–2719 (2013)CrossRefGoogle Scholar
  12. 12.
    Seifozzakerini, S., et al.: Event-based hough transform in a spiking neural network for multiple line detection and tracking using a dynamic vision sensor, pp. 94.1–94.12, September 2016Google Scholar
  13. 13.
    Serrano-Gotarredona, T., Linares-Barranco, B.: 2015 poker-DVS dataset (2015). http://www2.imse-cnm.csic.es/caviar/POKERDVS.html. Accessed 8 June 2017
  14. 14.
    Stromatias, E., Soto, M., Serrano-Gotarredona, T., Linares-Barranco, B.: An event-driven classifier for spiking neural networks fed with synthetic or dynamic vision sensor data. Front. Neurosci. 11, 350 (2017)CrossRefGoogle Scholar
  15. 15.
    Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995).  https://doi.org/10.1007/978-1-4757-3264-1. ISBN 9780387987804CrossRefzbMATHGoogle Scholar
  16. 16.
    Wu, T.F., Lin, C.J., Weng, R.: Probability estimates for multi-class classification by pairwise coupling. J. Mach. Learn. Res. 5, 975–1005 (2004)MathSciNetzbMATHGoogle Scholar
  17. 17.
    Zhao, B., et al.: Event-driven simulation of the tempotron spiking neuron. In: BioCAS, pp. 667–670, October 2014Google Scholar
  18. 18.
    Zhao, B., et al.: Feedforward categorization on AER motion events using cortex-like features in a spiking neural network. Neural Netw. Learn. Syst. 26(9), 1963–1978 (2015)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.CONICETBuenos AiresArgentina
  2. 2.Universidad Argentina de la Empresa (UADE)Buenos AiresArgentina
  3. 3.CSIC, Instituto de Microelectronica Sevilla (IMSE-CNM)SevillaSpain

Personalised recommendations