Steps toward making robots see

  • Michael Brady
Conference paper
Part of the NATO ASI Series book series (volume 43)

Abstract

This paper reports on recent progress in Computer Vision by the Oxford Robotics Research Group. We discuss in particular: edge and corner finding; shape from contour; parallel algorithms for computing shape representations; parallel architectures for computer vision; and the application of truth maintenance systems to recognise variable geometry objects in cluttered images. Model-based vision and data-directed vision are discussed as extreme cases of architectures for vision systems.

Keywords

Computer Vision Edge Detection Parallel Algorithm Human Visual System Parallel Architecture 
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. T. O. Binford, 1981. Inferring surfaces from images. Artificial Intelligence, 17:205–245.CrossRefGoogle Scholar
  2. A. Blake and A. Zisserman, 1987. Visual Reconstruction. MIT Press, Cambridge, Mass.Google Scholar
  3. H. Blum, 1973. Biological shape and visual science (part 1). Journal of Theoretical Biology, 38:205–287.CrossRefGoogle Scholar
  4. R. A. Boie, I. J. Cox, and P. Rehak, 1986. On optimum edge recognition using matched filters. In Proc. Conf Pattern Recognition Image Processing, pages 100-108, Miami Beach, FL.Google Scholar
  5. R.C. Bolles and R.A. Cain, 1982. Recognising and locating partially visible objects. International Journal of Robotics Research, 1(3):57–82.CrossRefGoogle Scholar
  6. R.C. Bolles and P. Horaud, 1986. 3DPO: A three-dimensional part orientation system. International Journal of Robotics Research, 5(3):3–26.CrossRefGoogle Scholar
  7. J. B. Bowen and J. E. W. May hew, 1986. Consistency maintenance in the REV graph. Sheffield University AIVRU 020.Google Scholar
  8. J. M. Brady, 1981 (). Dangerous behaviour. In Proc. AISB Conf., Amsterdam, Netherlands.Google Scholar
  9. Michael Brady, 1982. Computational approaches to image understanding. Computing Surveys, 14(l):3–63.CrossRefGoogle Scholar
  10. Michael Brady, 1985 (). Criteria for representations of shape. In Human and Machine Vision (Beck, Hope, and Rosenfeld eds.), page, Academic Press, NY.Google Scholar
  11. J.M. Brady, 1987. Seeds of Perception. In Proc. Alvey Vis. Conf, page, Cambridge, UK.Google Scholar
  12. M. Brady and H. Asada, 1984. Smooth local symmetries and their implementation. International Journal of Robotics Research, 3(3).Google Scholar
  13. Michael Brady and G. L. Scott, 1987 (). Parallel algorithms for shape representation. In Parallel Architectures and Computer Vision (I. Page editor), page, Oxford University.Google Scholar
  14. J.M. Brady and B.J. Wielinga, 1978. Reading the writing on the wall. In Computer Vision Systems (Hanson and Riseman eds.), pages 283–302, Academic Press, New York.Google Scholar
  15. Michael Brady and A. Yuille, 1984. An extremum principle for shape from contour. IEEE Trans. Pattern Anal. Machine Intell., PAMI-6:288–310.MATHCrossRefGoogle Scholar
  16. Michael Brady, S. A. Cameron, and et. al., 1987. Progress towards a system that can acquire pallets and clean warehouses. In Proc. Fourth Int. Symp. Rob. Research (Bolles, R. and Roth, B. eds.), page, MIT Press.Google Scholar
  17. M. Brady, J. Ponce, A. Yuille, and H. Asada, 1985. Describing surfaces. Comput. Graphics Image Processing, 32:1–28.MATHCrossRefGoogle Scholar
  18. J.F. Canny, 1983. Finding Edges and Lines. Technical Report Tech.Rep. 720, Massachusetts Inst. Technol.Google Scholar
  19. J. Canny, 1986. A computational approach to edge detection. IEEE Trans. Pattern Anal. Machine Intell., PAMI-8:679–698.CrossRefGoogle Scholar
  20. J.H. Connell and J.M. Brady, 1985 (). Learning shape descriptions. In Int. J. Conf. Artif. Intell., Los Angeles, Ca.Google Scholar
  21. J.L. Crowley and A.C. Parker, 1984. A representation for shape based on peaks and ridges in the difference of low-pass transform. IEEE Trans. Pattern Anal. Machine Intell., PAMI-6:156–169.CrossRefGoogle Scholar
  22. S. W. Draper, 1981. The use of gradient and dual space in line-drawing interpretation. Artificial Intelligence, 17:461–508.Google Scholar
  23. Meng Chiau Er, 1986. Computer interpretation of engineering drawings. PhD thesis, Essex University.Google Scholar
  24. O.D. Faugeras and M. Hebert, 1986. The representation, recognition, and locating of 3-d objects. International Journal of Robotics Research, 5:27–52.CrossRefGoogle Scholar
  25. Margaret M. Fleck, 1987 (). The phantom edge finder. In Proceedings of the Alvey Vision Conference, Cambridge, England.Google Scholar
  26. David J. Foster, 1987. The role of pipelining in machine vision. PhD thesis, Oxford University.Google Scholar
  27. E. C. Freuder, 1975. A computer vision system for visual recognition using active knowledge. PhD thesis, MIT Artificial Intelligence Laboratory.Google Scholar
  28. A. Gennert, Michael, 1986 (). Detecting half-edges and vertices in images. In Proc. CVPR, pages 552-557, Miami, Fla.Google Scholar
  29. W. E. L. Grimson, 1981. From Images to Surfaces. MIT Press, Cambridge, Mass.Google Scholar
  30. W. Eric L. Grimson and Tomas Lozano-Perez, 1986 (). Search and sensing strategies for recognition and localization of two-and three- dimensional objects. In Third Symp. Robotics Research, pages 73-82, Gouvieux, France.Google Scholar
  31. A. Guzman, 1971 (). Analysis of curved line drawings using context and global information. In Machine Intelligence 6 (Meltzer and Michie eds.), pages 325-375, Ellis Horwood.Google Scholar
  32. R.M. Haralick, 1980. Edge and Region Analysis for Digital Image Data. Comput. Graphics Image Processing, 12:60–73.CrossRefGoogle Scholar
  33. R.M. Haralick, 1984. Digital Step Edges from Zero-crossings of Second Directional Derivatives. IEEE Trans. Pattern Anal. Machine Intell., PAMI-6(l):58–68.CrossRefGoogle Scholar
  34. R.M. Haralick, 1985. Second Directional Derivative Zero-crossing Detector using the Cubic Facet Model. In Proc. Conf. Pattern Recognition Image Processing, pages 672-677.Google Scholar
  35. M. J. Hawken and A. J. Parker, 1986. Spatial properties of neurons in the monkey striate cortex. Proc. Roy. Soc. London, B 231:(in press).Google Scholar
  36. G. Healey and T. O. Binford, 1987 (). Local shape from specularity. In Proceedings of the First International Conf Comp. Vision., pages 151-160, London, England.Google Scholar
  37. Martin Herman and Takeo Kanade, 1987. Incremental reconstruction of 3-d scenes from multiple complex images. Artificial Intelligence, 31:.Google Scholar
  38. A. Heurtas and G. Medioni, 1986. Detection of Intensity Changes with subpixel accuracy using Laplacian-Gaussian Masks. IEEE Trans. Pattern Anal. Machine Intell., PAMI-8(4) :651–664.CrossRefGoogle Scholar
  39. W. Daniel Hillis, 1985. The Connection Machine. MIT Press, Cambridge, Ma.Google Scholar
  40. G. H. Hinton, 1976. Relaxation and its role in computer vision. PhD thesis, Edinburgh University.Google Scholar
  41. C. A. R. Hoare, 1979. Communicating sequential processes. Comm. A. C. M.Google Scholar
  42. Radu Horaud and Michael Brady, 1987 (June). On the geometric interpretation of image contours. In Proceedings of the First International Conf Comp. Vision., pages 374-382, London, England.Google Scholar
  43. B. K. P. Horn, 1986. Robot Vision. MIT Press, Cambridge, Ma.Google Scholar
  44. D. A. Huffman, 1971. Impossible objects as nonsense sentences. Machine Intelligence 6, 295–323.Google Scholar
  45. Geraint Jones, 1987. Programming in Occam. Prentice Hall, Englewood Cliffs, NJ.MATHGoogle Scholar
  46. J. J. Koenderinck and A. J. van Doom, 1987. Dynamic shape. Biol. Cyb.Google Scholar
  47. J. Malik, 1987. Interpreting line drawings of curved objects. International Journal of Computer Vision, 1:73–103.CrossRefGoogle Scholar
  48. D.C. Marr, 1976. Early Processing of Visual Information. Phil. Trans. Roy. Soc. London B, 275:483–524.CrossRefGoogle Scholar
  49. D. Marr, 1982. Vision. Freeman, San Francisco.Google Scholar
  50. D. Marr and E.C. Hildreth, 1980. Theory of edge detection. Proc. Roy. Soc. London, B207:187–217.CrossRefGoogle Scholar
  51. J.W. Mayhew and J.P. Frisby, 1981. Psychophysical and computational studies toward a theory of human stereopsis. Artificial Intelligence, 17:349–387.CrossRefGoogle Scholar
  52. D. W. Murray, D. A. Castelow, and B. F. Buxton, 1987. From an image sequence to a recognised polyhedral object. In Proc. Alvey Vis. Conf., Cambridge, UK.Google Scholar
  53. W.M. Newman and R.F. Sproull, 1973. Principles of Interactive Computer Graphics. McGraw-Hill, New York.MATHGoogle Scholar
  54. J.A. Noble, 1987a. Finding corners. In Proc. Alvey Vis. Conf., Cambridge, UK.Google Scholar
  55. J.A. Noble, 1987b. The Geometric Structure of Images. M.Sc. report. Ian Page, 1987a. Parallel Algorithms and Computer Vision. Oxford University Press, Oxford.Google Scholar
  56. Ian Page, 1987b. The DisPuter. In Parallel Architectures for Computer Vision (Page, Ian ed.), page, Oxford University Press.Google Scholar
  57. S. B. Pollard, 1985. Identifying correspondences in binocular stereo. PhD thesis, Sheffield University.Google Scholar
  58. Stephen B. Pollard, John Porrill, John E. W. Mayhew, and John P. Frisby, 1985 (). Disparity gradient, lipschitz continuity, and computing binocular correspondences. In The Third International Symposium on Robotics Research, pages 19-26, Gouvieux, France.Google Scholar
  59. J. Ponce and M. Brady, 1987. Towards a surface primal sketch. In Three-dimensional vision (Kanade ed.).Google Scholar
  60. J. M. S. Prewitt, 1970 (). Object enhancement and extraction. In Picture Processing and Psychopictorics, pages 75-149,.Google Scholar
  61. G. M. Provan, 1987. The complexity of Truth Maintenance Sytems and their application to vision. PhD thesis, Oxford University.Google Scholar
  62. G. L. Scott, 1987. The alternative snake - and other animals. In Proc. Alvey Vis. Conf., Cambridge, UK.Google Scholar
  63. Jun Shen and Serge Castan, 1986. An optimal linear operator for edge detection. In Proc. CVPR, pages 109-114, Miami, Fla.Google Scholar
  64. Libor A. Spacek, 1987. Edge detection and motion detection. Image and Vision Computing, 4:43–56.Google Scholar
  65. D. Terzopoulos, 1983. The role of constraints and discontinuities in visible-surface reconstruction. In Proc. 7th Int. J. Conf. Artif. Intell., pages 1073-1077, Karlsruhe.Google Scholar
  66. V. Torre and T. Poggio, 1986. On edge detection. IEEE Trans. Pattern Anal. Machine Intell., PAMI-8:147–163.CrossRefGoogle Scholar
  67. Shimon Ullman, 1979. The Interpretation of Visual Motion. MIT Press, Cambridge, Ma.Google Scholar
  68. R.J. Watt and M.J. Morgan, 1983. The Recognition and Representation of Edge Blur: Evidence for Spatial Primitives in Human Vision. Vision Res., 23(12): 1465–1477.CrossRefGoogle Scholar
  69. H.R. Wilson and J.R. Bergen, 1979. A four mechanism model for spatial vision. Vision Research, 19:19–32.CrossRefGoogle Scholar
  70. Richard A. Young, 1986 (). Simulation of human retinal function with the gaussian derivative model. In Proc. CVPR, pages 564-569, Miami, Fla.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1988

Authors and Affiliations

  • Michael Brady
    • 1
  1. 1.Robotics Research Group, Department of Engineering ScienceUniversity of OxfordOxfordUK

Personalised recommendations