Learning Eye Vergence Control from a Distributed Disparity Representation

We present two neural models for vergence angle control of a robotic head, a simplified and a more complex one. Both models work in a closed-loop manner and do not rely on explicitly computed disparity, but extract the desired vergence angle from the post-processed response of a population of disparity tuned complex cells, the actual gaze direction and the actual vergence angle. The first model assumes that the gaze direction of the robotic head is orthogonal to its baseline and the stimulus is a frontoparallel plane orthogonal to the gaze direction. The second model goes beyond these assumptions, and operates reliably in the general case where all restrictions on the orientation of the gaze, as well as the stimulus position, type and orientation, are dropped.

[1]  G. Westheimer,et al.  Disjunctive eye movements , 1961, The Journal of physiology.

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

[3]  Hanspeter A. Mallot,et al.  Phase-based binocular vergence control and depth reconstruction using active vision , 1994 .

[4]  Casper J. Erkelens,et al.  The relationship between absolute disparity and ocular vergence , 2004, Biological Cybernetics.

[5]  Michael Hansen,et al.  Active depth estimation with gaze and vergence control using Gabor filters , 1996, Proceedings of 13th International Conference on Pattern Recognition.

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

[7]  Klaus-Robert Müller,et al.  Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.

[8]  Patrice Y. Simard,et al.  Best practices for convolutional neural networks applied to visual document analysis , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[9]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

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

[11]  B. G. Cumming,et al.  Responses of primary visual cortical neurons to binocular disparity without depth perception , 1997, Nature.

[12]  H. Mallot,et al.  Disparity-evoked Vergence is Driven by Interocular Correlation , 1996, Vision Research.

[13]  W. Richards,et al.  Anomalous stereoscopic depth perception. , 1971, Journal of the Optical Society of America.

[14]  Clifton M. Schor,et al.  The relationship between fusional vergence eye movements and fixation disparity , 1979, Vision Research.

[15]  George K. Hung,et al.  A Dual-Mode Dynamic Model of the Vergence Eye Movement System , 1986, IEEE Transactions on Biomedical Engineering.

[16]  G WESTHEIMER,et al.  Eye movement responses to convergence stimuli. , 1956, A.M.A. archives of ophthalmology.

[17]  J. Semmlow,et al.  Initial component control in disparity vergence: a model-based study , 1998, IEEE Transactions on Biomedical Engineering.

[18]  Hanspeter A. Mallot,et al.  Vergence Control and Disparity Estimation with Energy Neurons: Theory and Implementation , 2002, ICANN.

[19]  Radu Horaud,et al.  Cyclopean Geometry of Binocular Vision , 2008, Journal of the Optical Society of America. A, Optics, image science, and vision.

[20]  H. Ogmen,et al.  Neural network model of short-term horizontal disparity vergence dynamics. , 1997, Vision research.

[21]  V. V. Krishnan,et al.  A Heuristic Model for the Human Vergence Eye Movement System , 1977, IEEE Transactions on Biomedical Engineering.

[22]  Manuela Chessa,et al.  A neural model for binocular vergence control without explicit calculation of disparity , 2009, ESANN.

[23]  Cristina Urdiales,et al.  Automatic vergence control based on hierarchical segmentation of stereo pairs , 2003, Int. J. Imaging Syst. Technol..

[24]  Y. LeCun,et al.  Learning methods for generic object recognition with invariance to pose and lighting , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

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