Reliable disparity estimation through selective integration

A network model of disparity estimation was developed based on disparity-selective neurons, such as those found in the early stages of processing in the visual cortex. The model accurately estimated multiple disparities in regions, which may be caused by transparency or occlusion. The selective integration of reliable local estimates enabled the network to generate accurate disparity estimates on normal and transparent random-dot stereograms. The model was consistent with human psychophysical results on the effects of spatial-frequency filtering on disparity sensitivity. The responses of neurons in macaque area V2 to random-dot stereograms are consistent with the prediction of the model that a subset of neurons responsible for disparity selection should be sensitive to disparity gradients.

[1]  G. J. Mitchison,et al.  Interpolation in stereoscopic matching , 1985, Nature.

[2]  H. Wilson,et al.  Neural models of stereoscopic vision , 1991, Trends in Neurosciences.

[3]  L. Cormack,et al.  Interocular correlation, luminance contrast and cyclopean processing , 1991, Vision Research.

[4]  J. Mayhew,et al.  Vergence Eye Movements Made in Response to Spatial-Frequency-Filtered Random-Dot Stereograms , 1981, Perception.

[5]  John Scott Bridle,et al.  Probabilistic Interpretation of Feedforward Classification Network Outputs, with Relationships to Statistical Pattern Recognition , 1989, NATO Neurocomputing.

[6]  Ning Qian,et al.  Binocular Receptive Field Models, Disparity Tuning, and Characteristic Disparity , 1996, Neural Computation.

[7]  Haluk Derin,et al.  Modeling and Segmentation of Noisy and Textured Images Using Gibbs Random Fields , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  A. Norcia,et al.  Temporal frequency limits for stereoscopic apparent motion processes , 1984, Vision Research.

[9]  Peter Földiák,et al.  Sparse coding in the primate cortex , 1998 .

[10]  David J. Fleet,et al.  Neural encoding of binocular disparity: Energy models, position shifts and phase shifts , 1996, Vision Research.

[11]  I. Ohzawa,et al.  Encoding of binocular disparity by complex cells in the cat's visual cortex. , 1996, Journal of neurophysiology.

[12]  K Nakayama,et al.  Experiencing and perceiving visual surfaces. , 1992, Science.

[13]  Dennis Gabor,et al.  Theory of communication , 1946 .

[14]  I. Ohzawa,et al.  Encoding of binocular disparity by simple cells in the cat's visual cortex. , 1996, Journal of neurophysiology.

[15]  A. B. Bonds.  Temporal dynamics of contrast gain in single cells of the cat striate cortex , 1991, Visual Neuroscience.

[16]  Jitendra Malik,et al.  Review of computational models of stereopsis , 1995 .

[17]  J. Daugman.  Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[18]  D. M. Green,et al.  Signal detection theory and psychophysics , 1966 .

[19]  Heinrich H. Bülthoff,et al.  Stereo Integration, Mean Field Theory and Psychophysics , 1990, ECCV.

[20]  I. Ohzawa,et al.  The neural coding of stereoscopic depth. , 1997, Neuroreport.

[21]  Lawrence K. Cormack,et al.  Depth attraction and repulsion in random dot stereograms , 1991, Vision Research.

[22]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[23]  A. Parker,et al.  Spatial properties of disparity pooling in human stereo vision , 1989, Vision Research.

[24]  S. Lehky,et al.  Neural model of stereoacuity and depth interpolation based on a distributed representation of stereo disparity [published erratum appears in J Neurosci 1991 Mar;11(3):following Table of Contents] , 1990, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[25]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[26]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[27]  S. McKee,et al.  Temporal coherence theory for the detection and measurement of visual motion , 1995, Vision Research.

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

[29]  S. McKee,et al.  Stereoscopic acuity with defocused and spatially filtered retinal images , 1980 .

[30]  H. Smallman.  Fine-to-coarse scale disambiguation in stereopsis , 1995, Vision Research.

[31]  Julie M. Harris,et al.  Is stereopsis effective in breaking camouflage for moving targets? , 1997, Vision Research.

[32]  B. Julesz.  Foundations of Cyclopean Perception , 1971 .

[33]  Terrence J. Sejnowski,et al.  Filter selection model for motion segmentation and velocity integration , 1994 .

[34]  T. Sejnowski,et al.  A selection model for motion processing in area MT of primates , 1995, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[35]  Alexandre Pouget,et al.  Statistically Efficient Estimations Using Cortical Lateral Connections , 1996, NIPS.

[36]  D Marr,et al.  Cooperative computation of stereo disparity. , 1976, Science.

[37]  G. Westheimer.  Spatial interaction in the domain of disparity signals in human stereoscopic vision. , 1986, The Journal of physiology.

[38]  D Marr,et al.  A computational theory of human stereo vision. , 1979, Proceedings of the Royal Society of London. Series B, Biological sciences.

[39]  E H Adelson,et al.  Spatiotemporal energy models for the perception of motion. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[40]  G Mitchison,et al.  The Neural Representation of Stereoscopic Depth Contrast , 1993, Perception.