Advertisement

Journal of Mathematical Imaging and Vision

, Volume 2, Issue 4, pp 327–350 | Cite as

Shape from texture for smooth curved surfaces in perspective projection

  • Jonas Gårding
Article

Abstract

Projective distortion of surface texture observed in a perspective image can provide direct information about the shape of the underlying surface. Previous theories have generally concerned planar surfaces; this paper presents a systematic analysis of first- and second-order texture distortion cues for the case of a smooth, curved surface. In particular, several kinds of texture gradients are analyzed and are related to surface orientation and surface curvature. The local estimates obtained from these cues can be integrated to obtain a global surface shape, and it is shown that the two surfaces resulting from the well-known tilt ambiguity in the local foreshortening cue typically have qualitatively different shapes. As an example of a practical application of the analysis, a shape-from-texture algorithm based on local orientation-selective filtering is described, and some experimental results are shown.

Key words

shape from texture texture gradients perspective projection curved surfaces monocular cues 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    J. Gibson, The Perception of the Visual World, Houghton Mifflin: Boston, 1950.Google Scholar
  2. 2.
    J. Aloimonos, “Shape from texture”, Biol. Cybernet., vol. 58, pp. 345–360, 1988.Google Scholar
  3. 3.
    R. Bajcsy and L. Lieberman, “Texture gradients as a depth cue”, Comput. Graph. Image Process., vol. 5, pp. 52–67, 1976.Google Scholar
  4. 4.
    A. Blake and C. Marions, “Shape from texture: the homogeneity hypothesis”, in Proc. IEEE 3rd Int. Conf. on Computer Vision, Osaka, Japan, IEEE Computer Society Press, pp. 350–353, 1990.Google Scholar
  5. 5.
    D. Blostein and N. Ahuja, “Shape from texture: integrating texture element extraction and surface estimation”, IEEE Trans. Patt. Anal. Mach. Intell., vol. 11, pp. 1233–1251, 1989.Google Scholar
  6. 6.
    J. Gårding, “Shape from texture and contour by weak isotropy”, J. Artificial Intell., in press.Google Scholar
  7. 7.
    K. Kanatani and T.C. Chou, “Shape from texture: general principle”, J. Artificial Intell., vol. 38, pp. 1–48, 1989.Google Scholar
  8. 8.
    A.P. Pentland, “Shading into texture”, J. Artificial Intell., vol. 29, pp. 147–170, 1986.Google Scholar
  9. 9.
    A.P. Witkin, “Recovering surface shape and orientation from texture”, J. Artificial Intell., vol. 17, pp. 17–45, 1981.Google Scholar
  10. 10.
    D. Buckley, J.P. Frisby, and E. Spivey, “Stereo and texture cue combination in ground planes: an investigation using the table stereometer”, Perception, vol. 20, pp. 91, 1991.Google Scholar
  11. 11.
    J.E. Cutting and R.T. Millard, “Three gradients and the perception of flat and curved surfaces”, J. Exp. Psychol. [Gen.], vol. 113, pp. 198–216, 1984.Google Scholar
  12. 12.
    J.T. Todd and R.A. Akerstrom, “Perception of threedimensional form from patterns of optical texture”, J. Psychol. [Human Percept.], vol. 13, pp. 242–255, 1987.Google Scholar
  13. 13.
    J. Gibson, The Ecological Approach to Visual Perception, Houghton Mifflin: Boston, 1979.Google Scholar
  14. 14.
    J.J. Koenderink, Solid Shape, MIT Press: Cambridge, MA, 1990.Google Scholar
  15. 15.
    B. O'Neill, Elementary Differential Geometry, Academic Press: Orlando, FL, 1966.Google Scholar
  16. 16.
    K.A. Stevens, “The information content of texture gradients”, Biol. Cybernet., vol. 42, pp. 95–105, 1981.Google Scholar
  17. 17.
    J. Gårding, “Shape from surface markings”, Ph.D. thesis, Department of Numerical Analysis and Computing Science, Royal Institute of Technology, Stockholm, 1991.Google Scholar
  18. 18.
    A.C. Bovik, M. Clark, and W.S. Geisler, “Multichannel texture analysis using localized spatial filters”, IEEE Trans. Patt. Anal. Mach. Intell., vol. 12, pp. 55–73, 1990.Google Scholar
  19. 19.
    M.R. Turner, “Texture discrimination by Gabor function”, Biol. Cybernet., vol. 55, pp. 71–82, 1986.Google Scholar
  20. 20.
    J. Jones and L. Palmer, “An evaluation of the twodimensional Gabor filter model of simple receptive fields in cat striate cortex”, J. Neurophysiol., vol. 58, pp. 1233–1258, 1987.Google Scholar
  21. 21.
    P. Kube, “Using frequency-and orientation-tuned channels to determine surface slant”, in Proc. 8th Ann. Conf. of the Cognitive Science Society, Amherst, MA, 1986, pp. 235–244, Lawrence Erlbaum Associates.Google Scholar
  22. 22.
    M.R. Turner, G.L. Gerstein, and R. Bajcsy, “Underestimation of visual texture slant by human observers: a model”, Biol. Cybernet., vol. 65, pp. 215–226, 1991.Google Scholar
  23. 23.
    L.G. Brown and H. Shvaytser, “Surface orientation from projective foreshortening of isotropic texture autocorrelation”, IEEE Trans. Patt. Anal. Mach. Intell., vol. 12, pp. 584–588, 1990.Google Scholar

Copyright information

© Kluwer Academic Publishers 1992

Authors and Affiliations

  • Jonas Gårding
    • 1
  1. 1.Computational Vision and Active Perception Laboratory (CVAP), Department of Numerical Analysis and Computing ScienceRoyal Institute of TechnologyStockholmSweden

Personalised recommendations