Neural Mechanisms for Form and Motion Detection and Integration: Biology Meets Machine Vision

  • Heiko Neumann
  • Florian Raudies
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7583)


General-purpose vision systems, either biological or technical, rely on the robust processing of visual data from the sensor array. Such systems need to adapt their processing capabilities to varying conditions, have to deal with noise, and also need to learn task-relevant representations. Here, we describe models of early and mid-level vision. These models are motivated by the layered and hierarchical processing of form and motion information in primate cortex. Core cortical processing principles are: (i) bottom-up processing to build representations of increasing feature specificity and spatial scale, (ii) selective amplification of bottom-up signals by feedback that utilizes spatial, temporal, or task-related context information, and (iii) automatic gain control via center-surround competitive interaction and activity normalization. We use these principles as a framework to design and develop bio-inspired models for form and motion processing. Our models replicate experimental findings and, furthermore, provide a functional explanation for psychophysical and physiological data. In addition, our models successfully process natural images or videos. We show mechanism that group items into boundary representations or estimate visual motions from opaque or transparent surfaces. Our framework suggests a basis for designing bio-inspired models that solve typical computer vision problems and enable the development of neural technology for vision.


Motion Detection Motion Perception Automatic Gain Control Feed Forward Signal Feed Forward 
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.


  1. 1.
    Bayerl, P., Neumann, H.: Disambiguating visual motion through contextual feedback modulation. Neural Computation 16, 2041–2066 (2004)zbMATHCrossRefGoogle Scholar
  2. 2.
    Bayerl, P., Neumann, H.: Disambiguating visual motion by form-motion interactional computational model. Int’l J. of Comp. Vis. 72(1), 27–45 (2007)CrossRefGoogle Scholar
  3. 3.
    Black, M.J., Anandan, P.: The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields. Comp. Visi. and Image Understanding 63(1), 75–104 (1996)CrossRefGoogle Scholar
  4. 4.
    Felleman, D.J., van Essen, D.C.: Distributed hierarchical processing in the primate cerebral cortex. Cerebral Cortex 1, 1–47 (1991)CrossRefGoogle Scholar
  5. 5.
    Grossberg, S., Mingolla, E.: Neural dynamics of perceptual grouping: textures, boundaries, and emergent segmentation. Percept. & Psychophys. 38, 141–171 (1985)CrossRefGoogle Scholar
  6. 6.
    Hansen, T., Neumann, H.: Neural mechanisms for the robust representation of junctions. Neural Computation 16, 1013–1037 (2004)zbMATHCrossRefGoogle Scholar
  7. 7.
    Hansen, T., Neumann, H.: A recurrent model of contour integration in primary visual cortex. J. of Vision 8(8), 1–25 (2008)CrossRefGoogle Scholar
  8. 8.
    Hirsch, J.A., Gilbert, C.D.: Synaptic physiology of horizontal connections in the cats visual cortex. J. of Neuroscience 11, 1800–1809 (1991)Google Scholar
  9. 9.
    Kapadia, K.M., Ito, M., Gilbert, C.D., Westheimer, G.: Improvement in visual sensitivity by changes in local context: Parallel studies in human observers and in V1 of alert monkeys. Neuron. 15, 843–856 (1995)CrossRefGoogle Scholar
  10. 10.
    Layher, G., Giese, M.A., Neumann, H.: Learning Representations for Animated Motion Sequence and Implied Motion Recognition. In: Villa, A.E.P., Duch, W., Érdi, P., Masulli, F., Palm, G. (eds.) ICANN 2012, Part I. LNCS, vol. 7552, pp. 288–295. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  11. 11.
    Neumann, H., Yazdanbakhsh, A., Mingolla, E.: Seeing surfaces: The brain’s vision of the world. Physics of Life Reviews 4, 189–222 (2007)CrossRefGoogle Scholar
  12. 12.
    Orban, G.: Higher order visual processing in macaque extrastriate cortex. Physiol. Rev. 88, 69–89 (2008)CrossRefGoogle Scholar
  13. 13.
    Raudies, F., Neumann, H.: A neural model of the temporal dynamics of figure-ground segregation in motion perception. Neural Networks 23, 160–176 (2010)CrossRefGoogle Scholar
  14. 14.
    Raudies, F., Neumann, H.: A model of neural mechanisms in monocular transparent motion perception. J. of Physiology 104, 71–83 (2010)Google Scholar
  15. 15.
    Raudies, F., Mingolla, E., Neumann, H.: A model of motion transparency processing with local center-surround interactions and feedback. Neural Computation 23, 2868–2914 (2011)CrossRefGoogle Scholar
  16. 16.
    Weidenbacher, U., Neumann, H.: Extraction of surface-related features in a recurrent model of V1-V2 interactions. PLoS One 4(6), e5909 (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Heiko Neumann
    • 1
  • Florian Raudies
    • 2
  1. 1.Institute for Neural Information ProcessingUlm Univ.Germany
  2. 2.Center for Computational Neuroscience and Neural TechnologyBoston Univ.USA

Personalised recommendations