Object Discrimination Based on Depth-from-Occlusion

We present a model of how objects can be visually discriminated based on the extraction of depth-from-occlusion. Object discrimination requires consideration of both the binding problem and the problem of segmentation. We propose that the visual system binds contours and surfaces by identifying proto-objectscompact regions bounded by contours. Proto-objects can then be linked into larger structures. The model is simulated by a system of interconnected neural networks. The networks have biologically motivated architectures and utilize a distributed representation of depth. We present simulations that demonstrate three robust psychophysical properties of the system. The networks are able to stratify multiple occluding objects in a complex scene into separate depth planes. They bind the contours and surfaces of occluded objects (for example, if a tree branch partially occludes the moon, the two "half-moons" are bound into a single object). Finally, the model accounts for human perceptions of illusory contour stimuli.

[1]  L. Finkel,et al.  Integration of distributed cortical systems by reentry: a computer simulation of interactive functionally segregated visual areas , 1989, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[2]  David Marr,et al.  VISION A Computational Investigation into the Human Representation and Processing of Visual Information , 2009 .

[3]  D. Hubel,et al.  Segregation of form, color, movement, and depth: anatomy, physiology, and perception. , 1988, Science.

[4]  G. Poggio,et al.  Stereoscopic mechanisms in monkey visual cortex: binocular correlation and disparity selectivity , 1988, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[5]  V. S. Ramachandran,et al.  Visual Perception of Surfaces: A Biological Theory , 1987 .

[6]  F. Attneave.  Some informational aspects of visual perception. , 1954, Psychological review.

[7]  T. Wiesel,et al.  Receptive field dynamics in adult primary visual cortex , 1992, Nature.

[8]  E. Spelke,et al.  Perceptual completion of surfaces in infancy. , 1987, Journal of experimental psychology. Human perception and performance.

[9]  S. Ullman.  Aligning pictorial descriptions: An approach to object recognition , 1989, Cognition.

[10]  E. Rosch,et al.  Cognition and Categorization , 1980 .

[11]  T. Wiesel,et al.  Columnar specificity of intrinsic horizontal and corticocortical connections in cat visual cortex , 1989, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[12]  Leif H. Finkel,et al.  Object segmentation and binding within a biologically-based neural network model of depth-from-occlusion , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  V S Ramachandran,et al.  Capture of stereopsis and apparent motion by illusory contours , 1986, Perception & psychophysics.

[14]  W. Singer,et al.  Stimulus-specific neuronal oscillations in orientation columns of cat visual cortex. , 1989, Proceedings of the National Academy of Sciences of the United States of America.

[15]  K. Koffka.  Principles Of Gestalt Psychology , 1936 .

[16]  Antonio R. Damasio,et al.  The Brain Binds Entities and Events by Multiregional Activation from Convergence Zones , 1989, Neural Computation.

[17]  S. Grossberg,et al.  Neural dynamics of form perception: boundary completion, illusory figures, and neon color spreading. , 1985, Psychological review.

[18]  Azriel Rosenfeld,et al.  Computer Vision , 1988, Adv. Comput..

[19]  H. L. Resnikoff.  The illusion of reality , 1988 .

[20]  C. Koch,et al.  Towards a neurobiological theory of consciousness , 1990 .

[21]  H. Barlow.  Critical limiting factors in the design of the eye and visual cortex , 1981 .

[22]  R. von der Heydt,et al.  Mechanisms of contour perception in monkey visual cortex. I. Lines of pattern discontinuity , 1989, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[23]  Heinrich H. Bülthoff,et al.  Integration of Visual Modules , 1992 .

[24]  Leif H. Finkel,et al.  NEXUS: A simulation environment for large-scale neural systems , 1992, Simul..

[25]  James Gordon,et al.  The existence of interpolated illusory contours depends on contrast and spatial separation , 1987 .

[26]  R. Gregory,et al.  Cognitive Contours , 1972, Nature.

[27]  S. Grossberg.  Cortical dynamics of three-dimensional form, color, and brightness perception: I. Monocular theory , 1987, Perception & psychophysics.

[28]  S. Zucker,et al.  Endstopped neurons in the visual cortex as a substrate for calculating curvature , 1987, Nature.

[29]  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.

[30]  T Poggio,et al.  Parallel integration of vision modules. , 1988, Science.

[31]  R. von der Heydt,et al.  Mechanisms of contour perception in monkey visual cortex. II. Contours bridging gaps , 1989, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[32]  P. Cavanagh,et al.  Subjective contours capture stereopsis , 1985, Nature.

[33]  J. Lund,et al.  Widespread periodic intrinsic connections in the tree shrew visual cortex. , 1982, Science.

[34]  Terrence J. Sejnowski,et al.  Separating figure from ground with a Boltzmann machine , 1990 .

[35]  G. Mitchison,et al.  Long axons within the striate cortex: their distribution, orientation, and patterns of connection. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[36]  K Nakayama,et al.  Toward a neural understanding of visual surface representation. , 1990, Cold Spring Harbor symposia on quantitative biology.

[37]  I. Biederman.  Recognition-by-components: a theory of human image understanding. , 1987, Psychological review.

[38]  Adolfo Guzman,et al.  Decomposition of a visual scene into three-dimensional bodies , 1968 .

[39]  Peter König,et al.  Stimulus-Dependent Assembly Formation of Oscillatory Responses: I. Synchronization , 1991, Neural Computation.

[40]  Leif H. Finkel,et al.  A neural network model of object segmentation and feature binding in visual cortex , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[41]  Peter König,et al.  Stimulus-Dependent Assembly Formation of Oscillatory Responses: III. Learning , 1992, Neural Computation.