Synthetic aperture radar processing by a multiple scale neural system for boundary and surface representation

Abstract A neural network model of boundary segmentation and surface representation is developed to process images containing range data gathered by a synthetic aperture radar (SAR) sensor. The boundary and surface processing are accomplished by an improved Boundary Countour System (BCS) and Feature Countour System (FCS), respectively, that have been derived from analyses of perceptual and neurobiological data. BCS/FCS processing makes structures such as motor vehicles, roads, and buildings more salient and interpretable to human observers than they are in the original imagery. Early processing by ON cells and OFF cells embedded in shunting center-surround network models preprocessing by lateral geniculate nucleus (LGN). Such preprocessing compensates for illumination gradients, normalizes input dynamic range, and extracts local ratio contrasts. ON cell and OFF cell outputs are combined in the BCS to define oriental filters that model corticla simple cells. Pooling ON and OFF outputs at simple cells overcomes complementary processing deficiencies of each cell type along concave and convex contours, and enhances simpl;e cell sensitivity to image edges. Oriented filter outputs are rectified and outputs sensitive to opposite contrast polarities are pooled to define complex cells. The complex cells output to stages of short-range spatial competition (or endstopping) and orientational competition among hypercomplex cells. Hypercomplex cells activate long-range cooperative bipole cells that begin to group image boundaries. Nonlinear feedback between bipole cells and hypercomplex cell segments image regions by cooperatively completing and regularizing the most favored boundaries while suppressing image noise and weaker boundary groupings. Boundary segmentation is performed by three copies of the BCS at small, medium, and large filter scales, whose subsequent interaction distances covary with the size of the filter. Filling-in of multiple surface representations occurs within the FCS at each scale via a boundary-gated diffusion process. Diffusion is activated by the normalized LGN ON and OFF outputs within ON and OFFfilling-in domains. Diffusion is restricted to the regions defined by gating signals from the corresponding BCS boundary segmentation. The filled-in opponent ON and OFFsignals are subtracted to form double opponent surface representations. These surface representations are shown by any of three methods to be sensitive to both image ratio contrasts and background luminance. The three scales of surface representation are then added to yield a final multiple-scale output. The BCS and FCS are shown to perform favorably in comparison to several other techniques for speckle removal.

[1]  D. Ferster.  Spatially opponent excitation and inhibition in simple cells of the cat visual cortex , 1988, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[2]  D. Munson,et al.  A tomographic formulation of spotlight-mode synthetic aperture radar , 1983, Proceedings of the IEEE.

[3]  Stephen Grossberg,et al.  Invariant recognition of cluttered scenes by a self-organizing ART architecture: CORT-X boundary segmentation , 1989, Neural Networks.

[4]  Stephen Grossberg,et al.  Neural dynamics of surface perception: Boundary webs, illuminants, and shape-from-shading , 1987, Comput. Vis. Graph. Image Process..

[5]  Stephen Grossberg,et al.  Contour Enhancement, Short Term Memory, and Constancies in Reverberating Neural Networks , 1973 .

[6]  Stephen Grossberg,et al.  GROUND SEPARATION BY VISUAL CORTEX , 1996 .

[7]  S. Grossberg,et al.  A neural network architecture for preattentive vision , 1989, IEEE Transactions on Biomedical Engineering.

[8]  K. Nakayama,et al.  Brithtness perception and filing-in , 1991 .

[9]  Stephen Grossberg,et al.  A neural network architecture for figure-ground separation of connected scenic figures , 1991, Neural Networks.

[10]  K. Arrington.  The temporal dynamics of brightness filling-in , 1994, Vision Research.

[11]  K. Miller.  Development of orientation columns via competition between ON- and OFF-center inputs. , 1992, Neuroreport.

[12]  Stephen Grossberg,et al.  Invariant recognition of cluttered scenes by a self-organizing ART architecture: figure-ground separation , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[13]  Leo Maurice Hurvich,et al.  Color vision , 1981 .

[14]  Stephen Grossberg,et al.  Neural dynamics of brightness perception: Features, boundaries, diffusion, and resonance , 1984 .

[15]  D. Pollen,et al.  Interneuronal interaction between members of quadrature phase and anti-phase pairs in the cat's visual cortex , 1992, Vision Research.

[16]  Jong-Sen Lee,et al.  A simple speckle smoothing algorithm for synthetic aperture radar images , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[17]  Stephen Grossberg,et al.  Neural dynamics of form perception: boundary completion , 1985 .

[18]  R. D. Chaney,et al.  Optimal Processing of Polarimetric Synthetic-Aperture Radar Imagery , 1990 .

[19]  E. Degreef,et al.  Trends in mathematical psychology , 1984 .

[20]  Heiko Neumann,et al.  A Contrast- and Luminance-driven Multiscale Network Model of Brightness Perception , 1995, Vision Research.

[21]  R. von der Heydt,et al.  Illusory contours and cortical neuron responses. , 1984, Science.

[22]  T R Crimmins,et al.  Geometric filter for speckle reduction. , 1985, Applied optics.

[23]  J. Mollon.  Color vision. , 1982, Annual review of psychology.

[24]  David C. Munson,et al.  A signal processing view of strip-mapping synthetic aperture radar , 1989, IEEE Trans. Acoust. Speech Signal Process..

[25]  Ken Nakayama,et al.  Brightness perception and filling-in , 1991, Vision Research.

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

[27]  S. Grossberg.  Outline of A Theory of Brightness, Color, and form Perception , 1984 .

[28]  S Grossberg,et al.  Cortical dynamics of three-dimensional form, color, and brightness perception: II. Binocular theory , 1988, Perception & psychophysics.

[29]  S. Grossberg.  Contour Enhancement , Short Term Memory , and Constancies in Reverberating Neural Networks , 1973 .

[30]  S. Grossberg,et al.  Neural dynamics of 1-D and 2-D brightness perception: A unified model of classical and recent phenomena , 1988, Perception & psychophysics.

[31]  S Grossberg,et al.  Neural dynamics of brightness perception: Features, boundaries, diffusion, and resonance , 1984, Perception & Psychophysics.

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

[33]  Ennio Mingolla,et al.  Neural dynamics of perceptual grouping: Textures, boundaries, and emergent segmentations , 1985 .

[34]  Stephen Grossberg,et al.  Processing of synthetic aperture radar images by the boundary contour system and feature contour system , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[35]  Thomas S. Huang,et al.  Image enhancement using the median and the interquartile distance , 1984, Comput. Vis. Graph. Image Process..