Head-Centric Disparity and Epipolar Geometry Estimation from a Population of Binocular Energy Neurons

We present a hybrid neural network architecture that supports the estimation of binocular disparity in a cyclopean, head-centric coordinate system without explicitly establishing retinal correspondences. Instead the responses of binocular energy neurons are gain-modulated by oculomotor signals. The network can handle the full six degrees of freedom of binocular gaze and operates directly on image pairs of possibly varying contrast. Furthermore, we show that in the absence of an oculomotor signal the same architecture is capable of estimating the epipolar geometry directly from the population response. The increased complexity of the scenarios considered in this work provides an important step towards the application of computational models centered on gain modulation mechanisms in real-world robotic applications. The proposed network is shown to outperform a standard computer vision technique on a disparity estimation task involving real-world stereo images.

[1]  Manuela Chessa,et al.  A cortical model for binocular vergence control without explicit calculation of disparity , 2010, Neurocomputing.

[2]  Erkki Oja,et al.  Neural Networks, Principal Components, and Subspaces , 1989, Int. J. Neural Syst..

[3]  S. R. Lehky,et al.  Neural models of binocular depth perception. , 1990, Cold Spring Harbor symposia on quantitative biology.

[4]  Kazuyuki Murase,et al.  Faster Training Using Fusion of Activation Functions for Feed Forward Neural Networks , 2009, Int. J. Neural Syst..

[5]  María José Castro Bleda,et al.  Cursive Word Recognition Based on Interactive Activation and Early Visual Processing Models , 2008, Int. J. Neural Syst..

[6]  Juan Miguel Ortiz-de-Lazcano-Lobato,et al.  Dynamic Competitive Probabilistic Principal Components Analysis , 2009, Int. J. Neural Syst..

[7]  Manuela Chessa,et al.  A Fast Joint Bioinspired Algorithm for Optic Flow and Two-Dimensional Disparity Estimation , 2009, ICVS.

[8]  Agostino Gibaldi,et al.  Learning Eye Vergence Control from a Distributed Disparity Representation , 2010, Int. J. Neural Syst..

[9]  T. Sejnowski,et al.  A neural model of the cortical representation of egocentric distance. , 1994, Cerebral cortex.

[10]  S. Celebrini,et al.  Gaze direction controls response gain in primary visual-cortex neurons , 1999, Nature.

[11]  I. Ohzawa,et al.  Stereoscopic depth discrimination in the visual cortex: neurons ideally suited as disparity detectors. , 1990, Science.

[12]  E. L. Schwartz,et al.  Spatial mapping in the primate sensory projection: Analytic structure and relevance to perception , 1977, Biological Cybernetics.

[13]  Ning Qian,et al.  A Coarse-to-Fine Disparity Energy Model with Both Phase-Shift and Position-Shift Receptive Field Mechanisms , 2004, Neural Computation.

[14]  Martin Fodslette Møller,et al.  A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[15]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[16]  G C DeAngelis,et al.  The physiology of stereopsis. , 2001, Annual review of neuroscience.

[17]  BENOÎT DECOUX,et al.  Self-Supervised Learning in Cooperative Stereo Vision Correspondence , 1997, Int. J. Neural Syst..

[18]  D. Calvetti,et al.  AN IMPLICITLY RESTARTED LANCZOS METHOD FOR LARGE SYMMETRIC EIGENVALUE PROBLEMS , 1994 .

[19]  Hojjat Adeli,et al.  Principal Component Analysis-Enhanced Cosine Radial Basis Function Neural Network for Robust Epilepsy and Seizure Detection , 2008, IEEE Transactions on Biomedical Engineering.

[20]  Qingquan Wu,et al.  View invariant head recognition by Hybrid PCA based reconstruction , 2008 .

[21]  Casper J. Erkelens,et al.  A computational model of depth perception based on headcentric disparity , 1998, Vision Research.

[22]  Clifton M. Schor,et al.  Perisaccadic Stereo Depth with Zero Retinal Disparity , 2010, Current Biology.

[23]  Florentin Wörgötter,et al.  An Asic-Chip for Stereoscopic Depth Analysis in Video-Real-Time Based on Visual Cortical Cell Behavior , 1999, Int. J. Neural Syst..

[24]  Martin Fodslette Meiller.  A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning , 1993 .

[25]  H. Opower.  Multiple view geometry in computer vision , 2002 .

[26]  Richard A. Andersen,et al.  A back-propagation programmed network that simulates response properties of a subset of posterior parietal neurons , 1988, Nature.

[27]  Qingquan Wu,et al.  View invariant head recognition by Hybrid PCA based reconstruction , 2008, Integr. Comput. Aided Eng..

[28]  Noel Lopes,et al.  An Evaluation of Multiple Feed-Forward Networks on GPUs , 2011, Int. J. Neural Syst..

[29]  Philippe Bekaert,et al.  Extrinsic Recalibration in Camera Networks , 2007, Fourth Canadian Conference on Computer and Robot Vision (CRV '07).

[30]  Heiko Wersing,et al.  Online Learning of Objects in a Biologically Motivated Visual Architecture , 2007, Int. J. Neural Syst..

[31]  T. Sejnowski,et al.  Spatial Transformations in the Parietal Cortex Using Basis Functions , 1997, Journal of Cognitive Neuroscience.

[32]  Ning Qian,et al.  Computing Stereo Disparity and Motion with Known Binocular Cell Properties , 1994, Neural Computation.

[33]  MARKO JANKOVIC,et al.  A New Modulated Hebbian Learning Rule - Biologically Plausible Method for Local Computation of a Principal Subspace , 2003, Int. J. Neural Syst..

[34]  Fabio Solari,et al.  A compact harmonic code for early vision based on anisotropic frequency channels , 2010, Comput. Vis. Image Underst..