Spiking Cooperative Stereo-Matching at 2 ms Latency with Neuromorphic Hardware

  • Georgi Dikov
  • Mohsen Firouzi
  • Florian Röhrbein
  • Jörg Conradt
  • Christoph RichterEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10384)


We demonstrate a spiking neural network that extracts spatial depth information from a stereoscopic visual input stream. The system makes use of a scalable neuromorphic computing platform, SpiNNaker, and neuromorphic vision sensors, so called silicon retinas, to solve the stereo matching (correspondence) problem in real-time. It dynamically fuses two retinal event streams into a depth-resolved event stream with a fixed latency of 2 ms, even at input rates as high as several 100,000 events per second. The network design is simple and portable so it can run on many types of neuromorphic computing platforms including FPGAs and dedicated silicon.


Correspondence problem Dynamic vision sensor (DVS) Event-based vision Event-based computation Neuromorphic computing PyNN Spiking neural networks Stereopsis 



We thank S. Temple and the SpiNNaker Manchester team for their invaluable hardware, software and support. We also acknowledge I. Krawczuk and L. Everding for fruitful discussions, technical assistance with benchmarks and power measurements as well as for help in obtaining good stereo-DVS datasets. The research leading to these results has received funding from the European Union Seventh Framework Programme (FP7/2007–2013) under grant agreement no. 720270 (Human Brain Project) and the Bundesministerium für Bildung und Forschung via grant no. 01GQ0440 (Bernstein Center for Computational Neuroscience Munich).


  1. 1.
    Benjamin, B.V., Gao, P., McQuinn, E., Choudhary, S., Chandrasekaran, A.R., Bussat, J.M., Alvarez-Icaza, R., Arthur, J.V., Merolla, P.A., Boahen, K.: Neurogrid: a mixed-analog-digital multichip system for large-scale neural simulations. Proc. IEEE 102(5), 699–716 (2014)CrossRefGoogle Scholar
  2. 2.
    Cheung, K., Schultz, S.R., Luk, W.: NeuroFlow: a general purpose spiking neural network simulation platform using customizable processors. Front. Neurosci. 9(516), 1–15 (2016)Google Scholar
  3. 3.
    Davies, E.: 3D vision and motion. In: Machine Vision. Signal Processing and its Applications, 3 edn., p. 443. Morgan Kaufmann, Burlington (2005)Google Scholar
  4. 4.
    Davison, A., Brüderle, D., Eppler, J., Kremkow, J., Muller, E., Pecevski, D., Perrinet, L., Yger, P.: PyNN: a common interface for neuronal network simulators. Front. Neuroinform. 2, 11 (2009). Google Scholar
  5. 5.
    Delbruck, T., Linares-Barranco, B., Culurciello, E., Posch, C.: Activity-driven, event-based vision sensors. In: Proceedings of 2010 IEEE International Symposium on Circuits and Systems, pp. 2426–2429, May 2010Google Scholar
  6. 6.
    Denk, C., Llobet-Blandino, F., Galluppi, F., Plana, L.A., Furber, S., Conradt, J.: Real-time interface board for closed-loop robotic tasks on the SpiNNaker neural computing system. In: International Conference on Artificial Neural Networks (ICANN), Sofia, Bulgaria, pp. 467–474, September 2013.
  7. 7.
    Diamond, A., Nowotny, T., Schmuker, M.: Comparing neuromorphic solutions in action: Implementing a bio-inspired solution to a benchmark classification task on three parallel-computing platforms. Front. Neurosci. 9, 491 (2016). CrossRefGoogle Scholar
  8. 8.
    Domínguez-Morales, M., Jimenez-Fernandez, A., Paz, R., López-Torres, M.R., Cerezuela-Escudero, E., Linares-Barranco, A., Jimenez-Moreno, G., Morgado, A.: An approach to distance estimation with stereo vision using address-event-representation. In: Lu, B.-L., Zhang, L., Kwok, J. (eds.) ICONIP 2011. LNCS, vol. 7062, pp. 190–198. Springer, Heidelberg (2011). doi: 10.1007/978-3-642-24955-6_23 CrossRefGoogle Scholar
  9. 9.
    Eibensteiner, F., Kogler, J., Scharinger, J.: A high-performance hardware architecture for a frameless stereo vision algorithm implemented on a FPGA platform. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 623–630 (2014)Google Scholar
  10. 10.
    Everding, L., Walger, L., Ghaderi, V.S., Conradt, J.: A mobility device for the blind with improved vertical resolution using dynamic vision sensors. In: IEEE HealthCom 2016, Munich, Germany, September 2016Google Scholar
  11. 11.
    Firouzi, M., Conradt, J.: Asynchronous event-based cooperative stereo matching using neuromorphic silicon retinas. Neural Process. Lett. 43(2), 311–326 (2016)CrossRefGoogle Scholar
  12. 12.
    Furber, S.B., Galluppi, F., Temple, S., Plana, L.A.: The SpiNNaker project. Proc. IEEE 102(5), 652–665 (2014)CrossRefGoogle Scholar
  13. 13.
    Furber, S.B., Lester, D.R., Plana, L.A., Garside, J.D., Painkras, E., Temple, S., Brown, A.D.: Overview of the spinnaker system architecture. IEEE Trans. Comput. 62(12), 2454–2467 (2013)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Georgieva, S., Peeters, R., Kolster, H., Todd, J.T., Orban, G.A.: The processing of three-dimensional shape from disparity in the human brain. J. Neurosci. 29(3), 727–742 (2009)CrossRefGoogle Scholar
  15. 15.
    Ghaderi, V.S., Mulas, M., Santos Pereira, V., Everding, L., Weikersdorfer, D., Conradt, J.: A wearable mobility device for the blind using retina-inspired dynamic vision sensors. In: 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 3371–3374, August 2015Google Scholar
  16. 16.
    Grossberg, S., Howe, P.D.: A laminar cortical model of stereopsis and three-dimensional surface perception. Vis. Res. 43(7), 801–829 (2003)CrossRefGoogle Scholar
  17. 17.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2003)zbMATHGoogle Scholar
  18. 18.
    Jany, R., Richter, C., Woltmann, C., Pfanzelt, G., Förg, B., Rommel, M., Reindl, T., Waizmann, U., Weis, J., Mundy, J.A., et al.: Monolithically integrated circuits from functional oxides. Adv. Mater. Interfaces 1(1) (2014)Google Scholar
  19. 19.
    Kogler, J., Humenberger, M., Sulzbachner, C.: Event-based stereo matching approaches for frameless address event stereo data. In: Bebis, G., et al. (eds.) ISVC 2011. LNCS, vol. 6938, pp. 674–685. Springer, Heidelberg (2011). doi: 10.1007/978-3-642-24028-7_62 CrossRefGoogle Scholar
  20. 20.
    Layher, G., Brosch, T., Neumann, H.: Real-time biologically inspired action recognition from key poses using a neuromorphic architecture. Front. Neurorobot. 11 (2017).
  21. 21.
    Li, C., Brandli, C., Berner, R., Liu, H., Yang, M., Liu, S.C., Delbruck, T.: Design of an RGBW color VGA rolling and global shutter dynamic and active-pixel vision sensor. In: 2015 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 718–721. IEEE (2015)Google Scholar
  22. 22.
    Lichtsteiner, P., Posch, C., Delbruck, T.: A \(128 \, \times \, 128\) \(120 \, \text{ db } \; 15 \, {\upmu }\)s latency asynchronous temporal contrast vision sensor. IEEE J. Solid State Circ. 43(2), 566–576 (2008)CrossRefGoogle Scholar
  23. 23.
    Liu, Q., Pineda-Garca, G., Stromatias, E., Serrano-Gotarredona, T., Furber, S.B.: Benchmarking spike-based visual recognition: a dataset and evaluation. Front. Neurosci. 10, 496 (2016). Google Scholar
  24. 24.
    Lorenz, M., Rao, M.S.R., Venkatesan, T., Fortunato, E., Barquinha, P., Branquinho, R., Salgueiro, D., Martins, R., Carlos, E., Liu, A., Shan, F.K., Grundmann, M., Boschker, H., Mukherjee, J., Priyadarshini, M., DasGupta, N., Rogers, D.J., Teherani, F.H., Sandana, E.V., Bove, P., Rietwyk, K., Zaban, A., Veziridis, A., Weidenkaff, A., Muralidhar, M., Murakami, M., Abel, S., Fompeyrine, J., Zuniga-Perez, J., Ramesh, R., Spaldin, N.A., Ostanin, S., Borisov, V., Mertig, I., Lazenka, V., Srinivasan, G., Prellier, W., Uchida, M., Kawasaki, M., Pentcheva, R., Gegenwart, P., Granozio, F.M., Fontcuberta, J., Pryds, N.: The 2016 oxide electronic materials and oxide interfaces roadmap. J. Phys. D Appl. Phys. 49(43), 433001 (2016). CrossRefGoogle Scholar
  25. 25.
    Mahowald, M.A., Delbrück, T.: Cooperative Stereo Matching Using Static and Dynamic Image Features, pp. 213–238. Springer, Boston (1989). doi: 10.1007/978-1-4613-1639-8_9 Google Scholar
  26. 26.
    Marr, D., Poggio, T.: Cooperative computation of stereo disparity. Science 194(4262), 283–287 (1976)CrossRefGoogle Scholar
  27. 27.
    Merolla, P.A., Arthur, J.V., Alvarez-Icaza, R., Cassidy, A.S., Sawada, J., Akopyan, F., Jackson, B.L., Imam, N., Guo, C., Nakamura, Y., et al.: A million spiking-neuron integrated circuit with a scalable communication network and interface. Science 345(6197), 668–673 (2014)CrossRefGoogle Scholar
  28. 28.
    Müller, G.R., Conradt, J.: A miniature low-power sensor system for real time 2D visual tracking of led markers. In: 2011 IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 2429–2434, December 2011Google Scholar
  29. 29.
    Ohzawa, I., DeAngelis, G.C., Freeman, R.D., et al.: Stereoscopic depth discrimination in the visual cortex: neurons ideally suited as disparity detectors. Science 249(4972), 1037–1041 (1990)CrossRefGoogle Scholar
  30. 30.
    Piatkowska, E., Belbachir, A.N., Gelautz, M.: Cooperative and asynchronous stereo vision for dynamic vision sensors. Meas. Sci. Technol. 25(5), 1–8 (2014)CrossRefGoogle Scholar
  31. 31.
    Posch, C., Matolin, D., Wohlgenannt, R.: A QVGA \(143\,\text{ dB }\) dynamic range frame-free PWM image sensor with lossless pixel-level video compression and time-domain CDS. IEEE J. Solid State Circ. 46(1), 259–275 (2011)CrossRefGoogle Scholar
  32. 32.
    Qiao, N., Mostafa, H., Corradi, F., Osswald, M., Stefanini, F., Sumislawska, D., Indiveri, G.: A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128k synapses. Front. Neurosci. 9 (2015).
  33. 33.
    Rast, A.D., et al.: Transport-independent protocols for universal AER communications. In: Arik, S., Huang, T., Lai, W.K., Liu, Q. (eds.) ICONIP 2015. LNCS, vol. 9492, pp. 675–684. Springer, Cham (2015). doi: 10.1007/978-3-319-26561-2_79 CrossRefGoogle Scholar
  34. 34.
    Read, J.: Early computational processing in binocular vision and depth perception. Prog. Biophys. Mol. Biol. 87(1), 77–108 (2005)CrossRefGoogle Scholar
  35. 35.
    Richter, C., Jentzsch, S., Hostettler, R., Garrido, J.A., Ros, E., Knoll, A.C., Röhrbein, F., van der Smagt, P., Conradt, J.: Musculoskeletal robots: scalability in neural control. IEEE Robot. Autom. Mag. 23(4), 128–137 (2016). doi: 10.1109/MRA.2016.2535081 CrossRefGoogle Scholar
  36. 36.
    Rogister, P., Benosman, R., Ieng, S.H., Lichtsteiner, P., Delbruck, T.: Asynchronous event-based binocular stereo matching. IEEE Trans. Neural Netw. Learn. Syst. 23(2), 347–353 (2012)CrossRefGoogle Scholar
  37. 37.
    Rowley, A.G.D., Stokes, A.B., Knight, J., Lester, D.R., Hopkins, M., Davies, S., Rast, A., Bogdan, P., Davidson, S.: PyNN on SpiNNaker software 2015.004, July 2015.
  38. 38.
    Schemmel, J., Brüderle, D., Grübl, A., Hock, M., Meier, K., Millner, S.: A wafer-scale neuromorphic hardware system for large-scale neural modeling. In: Proceedings of 2010 IEEE International Symposium on Circuits and systems (ISCAS), pp. 1947–1950. IEEE (2010)Google Scholar
  39. 39.
    Schraml, S., Schön, P., Milosevic, N.: Smartcam for real-time stereo vision-address-event based embedded system. In: VISApp (2), pp. 466–471 (2007)Google Scholar
  40. 40.
    Serrano-Gotarredona, T., Linares-Barranco, B., Galluppi, F., Plana, L., Furber, S.: ConvNets experiments on SpiNNaker. In: 2015 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 2405–2408, May 2015Google Scholar
  41. 41.
    Shi, B.E., Tsang, E.K.: A neuromorphic multi-chip model of a disparity selective complex cell. In: Thrun, S., Saul, L.K., Schölkopf, P.B. (eds.) Advances in Neural Information Processing Systems, vol. 16, pp. 1051–1058. MIT Press, Cambridge (2004)Google Scholar
  42. 42.
    Shimonomura, K., Kushima, T., Yagi, T.: Binocular robot vision emulating disparity computation in the primary visual cortex. Neural Netw. 21(23), 331–340 (2008). Advances in Neural Networks Research: International Joint Conference on Neural Networks, IJCNN 2007, July 2007. CrossRefGoogle Scholar
  43. 43.
    Stewart, T.C., Kleinhans, A., Mundy, A., Conradt, J.: Serendipitous offline learning in a neuromorphic robot. Front. Neurorobot. 10, 1–11 (2016)CrossRefGoogle Scholar
  44. 44.
    Sugiarto, I., Liu, G., Davidson, S., Plana, L.A., Furber, S.B.: High performance computing on SpiNNaker neuromorphic platform: a case study for energy efficient image processing. In: 2016 IEEE 35th International Performance Computing and Communications Conference (IPCCC), pp. 1–8, December 2016Google Scholar
  45. 45.
    Walter, F., Röhrbein, F., Knoll, A.: Neuromorphic implementations of neurobiological learning algorithms for spiking neural networks. Neural Netw. 72(C), 152–167 (2015)CrossRefGoogle Scholar
  46. 46.
    Yang, M., Liu, S.C., Delbruck, T.: A dynamic vision sensor with 1% temporal contrast sensitivity and in-pixel asynchronous delta modulator for event encoding. IEEE J. Solid State Circ. 50(9), 2149–2160 (2015)CrossRefGoogle Scholar
  47. 47.
    Zitnick, C.L., Kanade, T.: A cooperative algorithm for stereo matching and occlusion detection. IEEE Trans. Pattern Analy. Mach. Intell. 22(7), 675–684 (2000)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Georgi Dikov
    • 1
    • 2
  • Mohsen Firouzi
    • 1
    • 3
  • Florian Röhrbein
    • 2
    • 3
  • Jörg Conradt
    • 1
    • 3
  • Christoph Richter
    • 1
    • 3
    Email author
  1. 1.Neuroscientific System Theory, Department of Electical and Computer EngineeringTechnical University of MunichMunichGermany
  2. 2.Robotics and Embedded Systems, Department of InformaticsTechnical University of MunichGarchingGermany
  3. 3.Bernstein Center for Computational Neuroscience MunichMunichGermany

Personalised recommendations