Computer Vision Requirements in Blind Mobility Aids

  • Michael F. Deering
Chapter
Part of the NATO ASI Series book series (NSSE, volume 99)

Abstract

There are many different approaches to blind mobility aids. All have in common the transformation of raw environmental data into a form suitable for non-visual perception by the blind user. However, when this transformation involves no direct “understanding” or complex interpretation of the data by the transforming device, the blind user is still faced with the formidable task of perceiving the data in some “analog” (iconic) form, and must extract the complex structure of the external world from low level cues. Examples of such systems in the past include tactile systems such as Collins (2) and Collins & Madey (3). While these systems have met with some success indoors (4), the outdoor environment has proven too complex for direct mapping of image data to the skin. Alternate imaging techniques such as ultrasonic systems (e.g. 1) reduce some of the information but have their own limitations. Others have gone in the direction of preprocessing the visual image before presentation to the blind (12), though the output still is a form of image.

Keywords

Computer Vision Ground Plane Vision Algorithm Blind Subject Computer Vision System 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Brabyn, J., Collins, C. C., & Kay, L. (1981). A wide band- width CTFM scanning sonar with tactile and acoustic display for persons with impaired vision (blind, drivers, etc.). Proceedings of the Ultransonic International 81, Brighton, U.K.Google Scholar
  2. 2.
    Collins, C. C. (1970). Tactile television: Mechanical and electrical image projection. IEEE Transactions on Man- Machine System, 11, 65–71.CrossRefGoogle Scholar
  3. 3.
    Collins, C. C. & Madey, J. (1974). Tactile sensory replace- ment. Proceedings of the San Diego Biomedical Symposium, 13, 15–26.Google Scholar
  4. 4.
    Collins, C. C., Scadden, L. A., & Alden, A. B. (1977). Mo- bility studies with a tactile imaging device. Proceedings of the Conference on Systems and Devices for the Disabled, Seattle, 170–174.Google Scholar
  5. 5.
    DARPA (1983). STRATEGIC COMPUTING New-Generation Computing Technology: A Strategic Plan for its Development and Application to Critical Problems in Defense. Defense Advanced Research Projects Agency.Google Scholar
  6. 6.
    Deering, M. (1982). Real-Time Natural Scene Analysis for a Blind Prosthesis. Ph.D. Thesis, University of California at Berkeley, November 1981. Available as Fairchild Technical Report No. 622, August.Google Scholar
  7. 7.
    Deering, M. (1984). Hardware and software architectures for efficient AI. Proceedings of AAAI-84, Austin, Texas, August.Google Scholar
  8. 8.
    Deering, M. & Collins, C. (1981). Real-Time natural scene analysis for a blind prosthesis. In Proceedings of IJCAI81, Vancouver, B.C., Canada, 704–709.Google Scholar
  9. 9.
    Gibson, J. (1950). The Perception of the Visual World. Boston: Houghton-Mifflin.Google Scholar
  10. 10.
    Kurokawa, H., Matsumoto, K., Iwashita, M., & Nukiyama, T. (1983). The architecture and performance of Image Pipeline Processor. In Proceedings of VLSI ‘83, Trondheim, Norway, August, 275–284.Google Scholar
  11. 11.
    Perkins, W. (1978) A model based vision system for indus-trial parts. IEEE Transactions in Computing, Vol. C-27, 126–143.Google Scholar
  12. 12.
    Pun, T. & de Coulon, F. (1981). Image processing for visual prosthesis. Proceedings of the IEEE Conference on Pattern Recognition and Image Processing, 120–126, Dallas, Texas. Computer Vision Papers with Application to Mobility Aids Google Scholar
  13. 13.
    Gennery, D. (1977). A stereo vision system for an autonomous vehicle. Proceedings of IJCAI-77, Cambridge, Massachusetts, August, 576–582.Google Scholar
  14. 14.
    Gennery, D. (1980). Modeling the Environment of an Exploring Vehicle by Means of Stereo Vision. Ph.D. Dissertation, Stanford Artificial Intelligence Laboratory Memo AIM-339, Stanford University, June.Google Scholar
  15. 15.
    Gennery, D (1982). Tracking known three-dimensional objects. Proceedings of AAAI-82, Pittsburgh, Pennsylvania, August, 13–17.Google Scholar
  16. 16.
    Lavin, M. (1979). Analysis of scenes from a moving viewpoint. In P. Winston & R. Brown, (Eds.), Artificial Intelligence: An MIT Perspective. Cambridge, MA: MIT Press.Google Scholar
  17. 17.
    Moravec, H. (1977). Towards automatic visual obstacle avoidance. Proceedings of IJCAI-77, Cambridge, Massachusetts, August, 576–582.Google Scholar
  18. 18.
    Moravec, H. (1982). The CMU rover. Proceedings of AAAI-82, Pittsburgh, Pennsylvania, August, 377–380.Google Scholar
  19. 19.
    Nevatia, R. (1976). Depth measurement by motion stereo. Computer Graphics & Image Processing, 5, 203–214.CrossRefGoogle Scholar
  20. 20.
    Roach, J. & Aggarwal, J. (1980). Determining the Three-Dimensional Motion and Model of Objects from a Sequence of Images. University of Texas at Austin Laboratory for Image and Signal Analysis research report TR-80–2, June.Google Scholar
  21. 21.
    Tsuji, S., Osada, M., & Yachida, M. (1980). Tracking and segmentation of moving objects in dynamic line images. IEEE Transactions in Pattern Analysis and Machine Intelligence, Vol. PAMI-2 6, 516–522.Google Scholar
  22. 22.
    Williams, T. (1980). Depth from camera motion in a real world scene. IEEE Transactions in Pattern Analysis and Machine Intelligence, Vol. PAMI-2, 6, 511–516.Google Scholar
  23. 23.
    Witkin, A. (1980). A statistical technique for recovering surface orientation from texture in natural imagery. The First Annual National Conference on Artificial Intelligence, 1 3.Google Scholar
  24. 24.
    The November, 1980 issue of IEEE Transactions on Pattern Matching and Machine Intelligence, Vol. 2, No. 6, is a special issue on motion and time-varying imagery. These computer vision papers describe systems containing vision algorithms relevant to blind mobility aids.Google Scholar

The following two books contain a good description of practical vision algorithms

  1. 25.
    Ballard, D. & Brown, C. (1982). Computer Vision. New Jersey: Prentice Hall.Google Scholar
  2. 26.
    Pavlidis, Theo (1982). Algorithms for Graphics and Image Processing. Computer Science Press.Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 1985

Authors and Affiliations

  • Michael F. Deering
    • 1
  1. 1.Schlumberger ResearchPalo AltoUSA

Personalised recommendations