A Fast Joint Bioinspired Algorithm for Optic Flow and Two-Dimensional Disparity Estimation

  • Manuela Chessa
  • Silvio P. Sabatini
  • Fabio Solari
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5815)


The faithful detection of the motion and of the distance of the objects in the visual scene is a desirable feature of any artificial vision system designed to operate in unknown environments characterized by conditions variable in time in an often unpredictable way. Here, we propose a distributed neuromorphic architecture, that, by sharing the computational resources to solve the stereo and the motion problems, produces fast and reliable estimates of optic flow and 2D disparity. The specific joint design approach allows us to obtain high performance at an affordable computational cost. The approach is validated with respect to the state-of-the-art algorithms and in real-world situations.


Optic Flow Stereo Camera Binocular Disparity Population Code Vertical Disparity 
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.
    Baker, S., Scharstein, D., Lewis, J., Roth, S., Black, M., Szeliski, R.: A database and evaluation methodology for optical flow. In: ICCV (2007)Google Scholar
  2. 2.
    Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. of Computer Vision 47, 7–42 (2002)zbMATHCrossRefGoogle Scholar
  3. 3.
    Tombari, F., Mattoccia, S., Di Stefano, L., Addimanda, E.: Classification and evaluation of cost aggregation methods for stereo correspondence. In: CVPR (2008)Google Scholar
  4. 4.
    Milner, A.D., Goodale, M.: The visual brain in action. Oxford Univ. Press, Oxford (1995)Google Scholar
  5. 5.
    Heeger, D.: Model for the extraction of image flow. JOSA 4(8), 1455–1471 (1987)CrossRefGoogle Scholar
  6. 6.
    Grzywacz, N., Yuille, A.: A model for the estimate of local image velocity by cells in the visual cortex. Proc. R. Soc. Lond. B 239, 129–161 (1990)CrossRefGoogle Scholar
  7. 7.
    Chen, Y., Qian, N.: A coarse-to-fine disparity energy model with both phase-shift and position-shift receptive field mechanisms. Neural Computation 16, 1545–1577 (2004)zbMATHCrossRefGoogle Scholar
  8. 8.
    Fleet, D., Wagner, H., Heeger, D.: Neural encoding of binocular disparity: Energy models, position shifts and phase shifts. Vision Res. 36(12), 1839–1857 (1996)CrossRefGoogle Scholar
  9. 9.
    Bayerl, P., Neumann, H.: A fast biologically inspired algorithm for recurrent motion estimation. IEEE Trans. Pattern Anal. Mach. Intell. 29(2), 246–260 (2007)CrossRefGoogle Scholar
  10. 10.
    Shimonomura, K., Kushima, T., Yagi, T.: Binocular robot vision emulating disparity computation in the primary visual cortex. Neural Networks 21(2-3), 331–340 (2008)CrossRefGoogle Scholar
  11. 11.
    Higgins, C., Shams, S.: A neuromorphic vision processor for spatial integration of optical flow. In: ICCNS 2001 (2001)Google Scholar
  12. 12.
    Dale, J., Johnston, A.: A real-time implementation of a neuromorphic optic-flow algorithm. Perception 31, 136 (2002)Google Scholar
  13. 13.
    Pouget, A., Dayan, P., Zemel, R.S.: Inference and computation with population codes. Ann. Rev Neurosci 26, 381–410 (2003)CrossRefGoogle Scholar
  14. 14.
    Adelson, E., Bergen, J.: The plenoptic and the elements of early vision. In: Landy, M., Movshon, J. (eds.) Computational Models of Visual Processing, pp. 3–20. MIT Press, Cambridge (1991)Google Scholar
  15. 15.
    Adelson, E., Bergen, J.: Spatiotemporal energy models for the perception of motion. JOSA 2, 284–321 (1985)CrossRefGoogle Scholar
  16. 16.
    Ohzawa, I., De Angelis, G., Freeman, R.: Stereoscopic depth discrimination in the visual cortex: neurons ideally suited as disparity detectors. Science 249, 1037–1041 (1990)CrossRefGoogle Scholar
  17. 17.
    Morgan, M.J., Castet, E.: The aperture problem in stereopsis. Vision Res. 37(19), 2737–2744 (1997)CrossRefGoogle Scholar
  18. 18.
    Serrano-Pedraza, I., Read, J.C.A.: Stereo vision requires an explicit encoding of vertical disparity. J.Vision 9(4), 1–12 (2009)CrossRefGoogle Scholar
  19. 19.
    Daugman, J.: Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. JOSA A/2, 1160–1169 (1985)Google Scholar
  20. 20.
    Nestares, O., Navarro, R., Portilla, J., Tabernero, A.: Efficient spatial-domain implementation of a multiscale image representation based on Gabor functions. J. of Electronic Imaging 7(1), 166–173 (1998)CrossRefGoogle Scholar
  21. 21.
    Pauwels, K., Hulle, M.V.: Optic flow from unstable sequences containing unconstrained scenes through local velocity constancy maximization. BMVC 1, 397–406 (2006)Google Scholar
  22. 22.
    Theimer, W., Mallot, H.: Phase-based binocular vergence control and depth reconstruction using active vision. CVGIP: Image Understanding 60(3), 343–358 (1994)CrossRefGoogle Scholar
  23. 23.
    Chessa, M., Solari, F., Sabatini, S.: A virtual reality simulator for active stereo vision systems. In: VISAPP (2009)Google Scholar
  24. 24.
    Barron, J., Fleet, D., Beauchemin, S.: Performance of optical flow techniques. Int. J. of Computer Vision 12, 43–77 (1994)CrossRefGoogle Scholar
  25. 25.
    Jenkin, M., Tsotsos, J.: Applying temporal constraints to the dynamic stereo problem. In: CVGIP, vol. 33, pp. 16–32 (1986)Google Scholar
  26. 26.
    Sabatini, S., Solari, F., Cavalleri, P., Bisio, G.: Phase-based binocular perception of motion in depth: Cortical-like operators and analog VLSI architectures. EURASIP Journal on Applied Signal Processing 7, 690–702 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Manuela Chessa
    • 1
  • Silvio P. Sabatini
    • 1
  • Fabio Solari
    • 1
  1. 1.Department of Biophysical and Electronic EngineeringUniversity of GenoaGenovaItaly

Personalised recommendations