A neural architecture for visual information processing

We report on the work done at the Institut für Neuroinformatik in Bochum concerning the development of a neural architecture for the information processing of autonomous visually guided systems acting in a natural environment. Since biological systems like our brain are superior to artificial systems in solving such a task, we use findings from neurophysiology and -anatomy as well as psychophysics for defining processing principles and modules that have been implemented on our mobile platform MARVIN. MARVIN is equipped with an active stereo camera system. Our final objective is to define a neural instruction set for early information processing in the sense of a perception for action approach. From the biological paradigm we use principles like active vision, foveation, two-dimensional cortical layers, mapping, and discrete parametric representations in a task-oriented way to solve problems like obstacle avoidance, path planning, scene recognition, tracking, and 3D perception. This paper has the character of an overview of the work done in this field at our institute. Most of the modules presented here were published either in conference proceedings or in journals which will be referenced for a more thorough discussion of each issue.

[1]  Randal C. Nelson,et al.  Using Flow Field Divergence For Obstacle Avoidance: Towards Qualitative Vision , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[2]  Ronald C. Arkin,et al.  Integrating behavioral, perceptual, and world knowledge in reactive navigation , 1990, Robotics Auton. Syst..

[3]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[4]  Leslie G. Ungerleider.  Two cortical visual systems , 1982 .

[5]  A. Verri,et al.  A computational approach to motion perception , 1988, Biological Cybernetics.

[6]  J. Kopecz,et al.  Flexibility through a neural architecture for visual orientation in a natural environment , 1994 .

[7]  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.

[8]  Eric Krotkov,et al.  An agile stereo camera system for flexible image acquisition , 1988, IEEE J. Robotics Autom..

[9]  J. Kopecz.  A cortical structure for real world image processing , 1993, IEEE International Conference on Neural Networks.

[10]  H Collewijn,et al.  Integration of adaptive changes of the optokinetic reflex, pursuit and the vestibulo-ocular reflex. , 1985, Reviews of oculomotor research.

[11]  Yiannis Aloimonos,et al.  Tracking facilitates 3-D motion estimation , 1992, Biological Cybernetics.

[12]  Alan L. Yuille,et al.  Stereo and controlled movement , 1990, International Journal of Computer Vision.

[13]  Hanspeter A. Mallot,et al.  Erkennung natürlicher Bilder mit Hilfe diskreter parametrischer Repräsentationen und Assoziativspeichern , 1990, DAGM-Symposium.

[14]  Hanspeter A. Mallot,et al.  Neural mapping and space-variant image processing , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[15]  A. Treisman.  Preattentive processing in vision , 1985, Comput. Vis. Graph. Image Process..

[16]  James J. Clark,et al.  Modal Control Of An Attentive Vision System , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[17]  T. Poggio,et al.  A parallel algorithm for real-time computation of optical flow , 1989, Nature.

[18]  T. Sanger,et al.  Stereo disparity computation using Gabor filters , 1988, Biological Cybernetics.

[19]  G. Blasdel,et al.  Voltage-sensitive dyes reveal a modular organization in monkey striate cortex , 1986, Nature.

[20]  Richard Durbin,et al.  A dimension reduction framework for understanding cortical maps , 1990, Nature.

[21]  T. Kohonen.  Self-Organized Formation of Correct Feature Maps , 1982 .

[22]  R A Brooks,et al.  New Approaches to Robotics , 1991, Science.

[23]  Hans Knutsson,et al.  Hierarchical Phase Based Disparity Estimation , 1992 .

[24]  D. Hubel,et al.  Ferrier lecture - Functional architecture of macaque monkey visual cortex , 1977, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[25]  Christopher M. Brown,et al.  Selective Attention as Sequential Behavior: Modeling Eye Movements with an Augmented Hidden Markov Model , 1990 .

[26]  Wilfried Enkelmann,et al.  Obstacle detection by evaluation of optical flow fields from image sequences , 1990, Image Vis. Comput..

[27]  M. Cynader,et al.  Functional organization of the cortical 17/18 border region in the cat , 2004, Experimental Brain Research.

[28]  Heinrich H. Bülthoff,et al.  Adaptation of a parallel correlation-based optical flow scheme , 1990 .

[29]  G. Krone,et al.  Spatiotemporal receptive fields: a dynamical model derived from cortical architectonics , 1986, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[30]  Dana H. Ballard,et al.  The Rochester Robot , 1988 .

[31]  Tracy L. Anderson,et al.  Animal behavior as a paradigm for developing robot autonomy , 1990, Robotics Auton. Syst..

[32]  Roman Bek,et al.  Discourse on one way in which a quantum-mechanics language on the classical logical base can be built up , 1978, Kybernetika.

[33]  Gregor Schöner,et al.  A dynamical systems approach to task-level system integration used to plan and control autonomous vehicle motion , 1992, Robotics Auton. Syst..

[34]  Klaus Schulten,et al.  Topology-conserving maps for learning visuo-motor-coordination , 1989, Neural Networks.

[35]  J. Brian Burns,et al.  Path planning using Laplace's equation , 1990, Proceedings., IEEE International Conference on Robotics and Automation.

[36]  Daniel E. Koditschek,et al.  Exact robot navigation in geometrically complicated but topologically simple spaces , 1990, Proceedings., IEEE International Conference on Robotics and Automation.

[37]  H. Tamura,et al.  Inhibition contributes to orientation selectivity in visual cortex of cat , 1988, Nature.

[38]  R. Bajcsy.  Active perception , 1988 .

[39]  Dana H. Ballard,et al.  Animate Vision , 1991, Artif. Intell..

[40]  Henrik I. Christensen,et al.  AUC robot camera head , 1992, Defense, Security, and Sensing.

[41]  Sebastian Toelg,et al.  Phase method for binocular vergence control and depth reconstruction , 1992, Other Conferences.

[42]  James L. Crowley,et al.  Gaze Control for a Binocular Camera Head , 1992, ECCV.

[43]  C. Malsburg.  Self-organization of orientation sensitive cells in the striate cortex , 2004, Kybernetik.

[44]  Sebastian Toelg.  Gaze control for an active camera system by modeling human pursuit eye movements , 1992, Other Conferences.

[45]  Michael Dose,et al.  An Active Visison System for Task-Specific Information Processing , 1990, DAGM-Symposium.

[46]  Stefan Bohrer,et al.  Using Inverse Perspective Mapping as a Basis for two Concurrent Obstacle Avoidance Schemes , 1991 .

[47]  Hanspeter A. Mallot,et al.  Disparity-evoked vergence is directed towards average depth , 1995 .

[48]  J. Austin.  Associative memory , 1987 .

[49]  Nicola Ancona.  A Fast Obstacle Detection Method based on Optical Flow , 1992, ECCV.

[50]  Y. Dube,et al.  An Autonomous Mobile Robot , 1992, Singapore International Conference on Intelligent Control and Instrumentation [Proceedings 1992].

[51]  W. Seelen,et al.  Intensity and edge-based symmetry detection with an application to car-following , 1993 .

[52]  J. Little,et al.  Inverse perspective mapping simplifies optical flow computation and obstacle detection , 2004, Biological Cybernetics.

[53]  H Collewijn,et al.  Binocular eye movements and the perception of depth. , 1990, Reviews of oculomotor research.

[54]  Jan-Olof Eklundh,et al.  A head-eye system - Analysis and design , 1992, CVGIP Image Underst..

[55]  Refractor.  Vision , 2000, The Lancet.

[56]  Jan-Olof Eklundh,et al.  Object detection using model based prediction and motion parallax , 1990, ECCV.

[57]  A. Verri,et al.  Differential techniques for optical flow , 1990 .

[58]  J. Kopecz,et al.  IMAGE RECOGNITION IN HYPERCOLUMNAR SCALE SPACE BY SPARSELY CODED ASSOCIATIVE MEMORY , 1991 .

[59]  David J. Fleet,et al.  Phase-based disparity measurement , 1991, CVGIP Image Underst..

[60]  T. Wiesel,et al.  Functional architecture of macaque monkey visual cortex , 1977 .

[61]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[62]  J. Mayhew,et al.  SWITCHER: a stereo algorithm for ground plane obstacle detection , 1990, Image Vis. Comput..

[63]  Michael A. Arbib,et al.  Perceptual Structures and Distributed Motor Control , 1981 .

[64]  J. Duncan,et al.  Visual search and stimulus similarity. , 1989, Psychological review.