Skip to main content
SpringerLink
Log in

A neural architecture for visual information processing

  • Published:
International Journal of Computer Vision Aims and scope Submit manuscript

Abstract

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.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Aloimonos, J., Weiss, I., and Bandyopadhyay, A. 1987. Active Vision.International Journal of Computer Vision, pp. 333–356.

  • Ancona, N. 1992. A Fast Obstacle Detection Method based on Optimal Flow. In2nd ECCV, Genua, Springer-Verlag, pp. 267–271.

  • Arbib, M.A. 1981. Perceptual structures and distributed motor control. In V.B. Brooks (ed.),Handbook of physiology, Sect. 1: The nervous system. Vol. II Motor Control. Part 2, American Physiological Society, Bethesda, Maryland, pp. 1449–1480.

    Google Scholar 

  • Arkin, R.C. 1990. Integrating behavioral, perceptual, and world knowledge in reactive navigation.Robotics and autonomous control, 6:105–122.

    Google Scholar 

  • Bajcsy, R. 1988. Active Perception.Proceedings of the IEEE, 76(8):996–1005.

    Google Scholar 

  • Ballard, D.H. 1991. Animate Vision.Artificial Intelligence, Elsevier, 48(l):57–86.

    Google Scholar 

  • Blasdel, G.G. and Salama, G. 1986. Voltage-sensitive dyes reveal a modular organization in monkey striate cortex.Nature, 321; 579–585.

    Google Scholar 

  • Bohrer, S. 1993.Visual Obstacle Avoidance Using Optic Flow and the Inverse Perspective Mapping. Dissertation, Ruhr-Universität Bochum (in German), Bochum.

    Google Scholar 

  • Bohrer, S., Bülthoff, H.H., and Mallot, H.A. 1990. Adaptation of a Parallel Correlation-based Optical Flow Scheme. InINNC-90, Paris, IEEE.

  • Bohrer, S., Lütgendorf, A., and Mempel, M. 1991. Using Inverse Perspective Mapping as a Basis for two Concurrent Obstacle Avoidance Schemes. InICANN-91, Helsinki, Elsevier, North Holland.

  • Brooks, R.A. 1991. New approaches to robotics.Science, 253: 1227–1232.

    Google Scholar 

  • Brown, CM. 1988.The Rochester Robot. Technical Report 257. University of Rochester, Computer Science Department.

  • Bülthoff, H.H., Little, J.J., and Poggio, T. 1989. A Parallel Algorithm for Real-Time Computation of Optical Flow.Nature, 337(9): 549–553.

    Google Scholar 

  • Carlsson, S. and Eklundh, J.O. 1990. Object detection using Model based Prediction and Motion Parallax. In 1stECCV, Antibes, Spring-Verlag, pp. 297–306.

  • Christensen, H.I. 1992. The AUC Robot Camera Head. InSPIE Vol. 1708 Applications of Artificial Intelligence X: Machine Vision and Robotics, Washington, International Society for Optical Engineering.

  • Clark, J.J. and Ferrier, N.J. 1988. Model Control of an Attentive Vision System. In 2nd ICCV, Tampa Florida, IEEE, pp. 514–23.

  • Collewijn, H. 1985.Adaptive Mechanisms in Gaze Control, chapter Integration of adaptive changes of the optokinetic reflex, pusuit and vestibular-ocular reflex. Elsevier Science Publishers, 1985.

  • Collewijn, H. and Erkelens, C.J. 1990. Binocular eye movements and the perception of depth. In E. Kolwer (ed.),Eye Movements and Their Role in Visual and Cognitive Processes. Elsevier Science Publishers B.V., Amsterdam, pp. 213–261.

    Google Scholar 

  • Connolly, C.I., Burns, J.B., and Weiss, R. 1990. Path planning using Laplace's equation.IEEE Robotics and Automation, pp.2102–2106.

  • Crowley, J.L., Bobet, P., and Mesrabi, M. 1992. Gaze Control for a Binocular Camera Head. In2nd ECCV, Santa Margherita Ligure, Springer-Verlag, pp. 588–62.

  • Daugman, J.G. 1985. Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters.J. Opt. Soc. Am. A, 2:1160–1169. 1985.

    Google Scholar 

  • Diao, Y., Jia, W., and Swindale, N.V. et al. 1990. Functional organization of the cortical 17/18 border region in the cat.Experimental Brain Research, 79:271–282.

    Google Scholar 

  • Donath, M. and Anderson, T.L. 1990. Animal behavior as a paradigm for developing robot autonomy.Robotics and Autonomous Systems, 6:145–168.

    Google Scholar 

  • Dose, M. 1992. Einführung in die Sprache VACCL.Internal Technical Report, Institut für Neuroinformatik, Ruhr-Universität Bochum.

  • Dose, M., Fuhrmann, S., Schulze-Krüger, E., and Theimer, W. 1994. An Autonomous Mobile Robot—A Development Tool for Operation in a Natural Environment. Technical report, Ruhr-Universität Bochum, Institut für Neuroinformatik.

  • Duncan, J. and Humphreys, G. 1989. Visual search and stimulus similarity.Psychological Review, 96:433–458.

    Google Scholar 

  • Durbin, R. and Mitchison, G. 1990. A dimension reduction framework for understanding cortical maps.Nature, 343:644–647.

    Google Scholar 

  • Enkelmann, W. 1991. Obstacle Detection by Evaluation of Optical Flow Fields from Image Sequences.Image and Vision Computing, Butterworth-Heinemann, 9(3): 160–168.

    Google Scholar 

  • Fermüller, C. and Aloimonos, Y. 1992. Tracking facilitates 3-D Motion Estimation.Biological Cybernetics, Spring Verlag, 67: 259–268.

    Google Scholar 

  • Fleet, D.J., Jepson, A.D., and Jenkin, M.R.M. 1991. Phase-Based Disparity Measurement.CVGIP: Image Understanding, 53: 198–210.

    Google Scholar 

  • Hata, Y., Tsumoto, T., and Sato, H. 1988. Inhibition contributes to orientation selectivity in visual cortex of cat.Nature, 335: 815–817.

    Google Scholar 

  • Hubel, D.H. and Wiesel, T.N. 1977. Functional architecture of macaqe monkey visual cortex.Proceedings of The Royal Society (London) B, 198:1–59.

    Google Scholar 

  • Janßen, H., Giefing, G., and Mallot, H.A. 1991. A saccadic camera movement system for object recognition. InArtificial Neural Networks. Elsevier North-Holland, pp. I-63–8.

  • Janßen, H. and Kopecz, J. 1991. Image recognition in hypercolumnar scale space by sarely coded associative memory. In T. Kohonen, K. Mäkisara, O. Simula, and J. Kangas (eds.),Artificial Neural Networks. ICANN91, Elseviler Science Publishers, pp. 1203–1206.

  • Janßen, H., Kopecz, J., and Mallot, H. 1990. Erkennung natürlicher Bilder mit Hilfe diskreter parametrischer Repräsentationen und Assoziativspecichern. In R.E. Groβkopf (ed.),Mustererkennung 1990, 12. DAGM-Symposium, Volume 254 ofInformatik-Fachberichte. DAGM, Springer Verlag.

  • Kohonen, T. 1982. Self-organized formation of topologically correct feature maps.Biological Cybernetics, 43:59–69.

    Google Scholar 

  • Kopecz, J. 1992. Modellierung lokaler Wechselwirkungen in diskreten cortikalen strukturen mittels nichtlinearer Dynamik, Dissertation.

  • Kopecz, J. 1993. A Cortical Structure for Real World Image Processing. InInternational Conference on Neural Networks ICNN, San Francisco, IEEE, pp. 138–143.

  • Kopecz, J., Janβen, H., Engels, C, and Schöner, G. 1993. Flexibility in neural architecture for visual orientation in a natural environement, submitted.

  • Krone, G., Mallot, H., Palm, G., and Schütz, A. 1986. Spatio-temporal receptive fields: a dynamical model derived from cortical architectonics.Proc. Roy. Soc. (London) B, 226:421–444.

    Google Scholar 

  • Krotkov, E., Fuma, F., and Summers, J. 1988. An Agile Stereo Camera System for Flexible Image Acquisition.Journal of Robotics and Automation, IEEE, 4(l):108–113.

    Google Scholar 

  • Mallot, H.A., Arndt, P.A. 1992. Disparity-evoked vergence is directed towards average depth. InInvest. Ophth. and Vis. Sc. Suppl 33. Association for Research in Vision and Ophlthalmology.

  • Mallot, H.A. and Brittinger, R. 1989. Towards a network theory of cortical areas. In R. Cotteril (ed.),Models of Brain Function, Cambridge Univ. Press, pp. 175–189.

  • Mallot, H.A., Bülthoff, H. H., Little, J.J., and Bohrer, S. 1991. Inverse Perspective Mapping Simplifies Optical Flow Computation and Obstacle Detection.Biological Cybernetics, Springer-Verlag, 64:177–185.

    Google Scholar 

  • Mallot, H.A. and Giefing, G. 1990. Retinal sampling grids and space-variant image processing. InParallel Processing in Neural Systems and Computers. DGK, North-Holland, pp. 125–128.

  • Mallot, H.A., Schulze, E., and Storjohann, K. 1988. Neural Network Strategies for Robot Navigation. InProc. of nEuro'88, Paris, pp. 560–569

  • Mallot, H.A., von Seelen, W., and Giannakopoulos, F. 1990. Neural Mapping and Space-Variant Image Processing.Neural Networks, 3:245–263.

    Google Scholar 

  • Marr, D. 1982.Vision. W. H. Freeman, San Francisco.

    Google Scholar 

  • Nelson, R.C. and Yiannis, J. Aloimonos 1988. Using Flow Field Divergence for Obstacle Avoidance: Towards Qualitative Vision. In2nd ICCV, Tampa Florida, IEEE, pp. 188–196.

  • Palm, G. 1980. On associative memory.Biological Cybernetics, 36:19–31.

    Google Scholar 

  • Pahlavan, K. and Eklundh, J.O. 1992. A Head-Eye System-Analysis and Design.CVGIP-IU, Academic Press, 56(l):41–56.

    Google Scholar 

  • Rimey, R.D. and Brown, CM. 1990. Selective attention as sequential behavior: Modeling eye movements with an augmented hidden markov model. Technical Report TR327, Computer Science Department, University of Rochester.

  • Rimon, E. and Koditschek, D.E. 1990. Exact robot navigation in geometrically complicated but topologically simple space.IEEE Robotics and Automation, pp. 1937–1942.

  • Ritter, H., Martinetz, T., and Schulten, K. 1989. Topology-Conserving Maps for learning Visuo-Motor-Coordination.Neural Networks, 2:159–168.

    Google Scholar 

  • Sandini, G. and Tistarelli, M. 1991. Robust Obstacle Detection Using Optical Flow. InWorkshop on Robust Computer Vision, Seattle, IEEE.

  • Sanger, T.D. 1988. Stereo Disparity Computation Using Gabor Filters.Biol. Cybern., 59:405–18.

    Google Scholar 

  • Schöner, G. and Dose, M. 1992. A dynamical systems approach to task-level system integration used to plan and control autonomous vehicle motion.Robotics and Autonomous Systems, 10:253–267.

    Google Scholar 

  • Schulze, E.R., Bohrer, S., Dose, M., and Fuhrmann, S. 1990. An Active Vision System for Task-Specific Information Processing. InMustererkennung 1990, 12. DAGM-Symossium, Oberkochen-Aalen, Springer-Verlag.

  • Theimer, W.M. and Mallot, H.A. 1993. Vergence Guided Depth Reconstruction Using a Phase Method. In Karl Goser and Jeanny Wérault (eds.),Neural Networks and their Industrial and Cognitive Applications: Neuro-Nimes 93. EC2, EC2 Publishing, pp. 299–308.

    Google Scholar 

  • Theimer, W.M., Mallot, H.A., and Tölg, S. 1992. Phase method for binocular vergence control and depth reconstruction. In David P.Casasent (ed.),Intelligent Robots and Computer Vision XI: Biololgical, Neural Net, and 3-D Methods, Volume 1826, Boston, MA, Society of Photo-Optical Instrumentation Engineers, pp. 76–87.

    Google Scholar 

  • Tölg, S. 1992a. Gaze control for an active camera system by modeling human pursuit eye movements. In David P. Casasent (ed.),Intelligent Robots and Computer Vision XI, Volume 1825. SPIE—The International Society for Optical Engineering.

  • Tölg, S. 1992b.Strukturuntersuchungen zur Informationsverarbeitung in neuronaler Architek tur am Beispiel der Modellierung von Augenbewegungen für aktives Sehen, volume 197 ofFortschritt-Berichte VDI, Reihe 10: Informatik/Kommunikationstechnik. VDI Verlag, Düsseldorf, ISBN 3-18-149710-X.

  • Treisman, A. 1985. Preattentive processing in vision.Computer Graphics and Image Processing, 31:156–177.

    Google Scholar 

  • Uras, S., Girosi, F., Verri, A., and Torre, V. 1988. A computational approach to motion perception.Biol. Cybern., 60:79–87.

    Google Scholar 

  • Ungerleider, L.G. and Mishkin, M. 1982. Two cortical visual systems. In D.J. Ingle, M.A. Goodale, and R.J.W. Mansfield (eds.),The Analysis of Visual Behavior, The MIT Press, Cambridge, MA. pp. 549–586. '

    Google Scholar 

  • von der Malsburg, 1973. Self-Organization of Orientation Sensitive Cells in the Striate Cortex.Kybernetik, 14:85–100.

    Google Scholar 

  • Verri, A., Giros F., and Torre, V. 1990. Differential Techniques for Optical Flow.Journal of the Optical Society of America A, 7(5):912–922.

    Google Scholar 

  • Vivani, P. 1990 Eye movements in visual search: cognitive, perceptual and motor control aspects. In E. Kowler (ed.),Eye movements and their role in visual and cognitive processes. Elsevier Science Publishers BV.

  • Wiklund, J., Westelius, C, and Knutsson, H. 1992. Hierarchical Phase Based Disparity Estimation. Technical Report LiTH-ISY-I-1327, Department of Electical Engineering, Linköping University.

  • Yuille, A. and Geiger, D. 1990. Stero and controlled movement.Intl. J. Computer Vision, 4:141–152.

    Google Scholar 

  • Zielke, T., Brauckmann, M., and von Seelen, W. 1993. Intensity and Edge-Based Symmetry Detection with an Application to Car-Following.CVG1P: Image Understanding, 58(1).

  • Zheng, Y., Jones, D.G., Billings, S.A., Mayhew, J.E.W., and Frisby, J.P. 1990. SWITCHER: a Stereo Algorithm for Ground Plane Obstacle Detection.Image and Vision Computing. Butterworth-Heinemann, 8(l):57–62.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institut für Neuroinformatik, Ruhr-Universitätsstr. Bochum, Universitätsstr. 150, ND 04/584, D-44780, Bochum, Germany

    Werner Von Seelen & Wolfgang M. Theimer

  2. C-VIS Computer Vision und Automation GmbH, Universitätsstr. 142, D-44799, Bochum, Germany

    Stefan Bohrer

  3. Zentrum für Neuroinformatik, Universitätsstr. 142, D-44799, Bochum, Germany

    Jörg Kopecz

Authors
  1. Werner Von Seelen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Stefan Bohrer
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jörg Kopecz
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Wolfgang M. Theimer
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Von Seelen, W., Bohrer, S., Kopecz, J. et al. A neural architecture for visual information processing. Int J Comput Vision 16, 229–260 (1995). https://doi.org/10.1007/BF01539628

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01539628

Keywords

Search

Navigation