Abstract
Spectral analysis provides a powerful means of estimating the perspective pose of texture planes. Unfortunately, one of the problems that restricts the utility of the method is the need to set the size of the spectral window. For texture planes viewed under extreme perspective distortion, the spectral frequency density may vary rapidly across the image plane. If the size of the window is mismatched to the underlying texture distribution, then the estimated frequency spectrum may become severely defocussed. This in turn limits the accuracy of perspective pose estimation. The aim in this paper is to describe an adaptive method for setting the size of the spectral window. We provide an analysis which shows that there is a window size that minimises the degree of defocusing. The minimum is located through an analysis of the spectral covariance matrix. We experiment with the new method on both synthetic and real world imagery. This demonstrates that the method provides accurate pose angle estimates, even when the slant angle is large. We also provide a comparison of the accuracy of perspective pose estimation that results both from our adaptive scale method and with one of fixed scale.
Supported by CAPES-BRAZIL under grant: BEX1549/95-2
Chapter PDF
Similar content being viewed by others
Keywords
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.
References
David Marr. Vision: A computational investigation into the human representation and processing of visual information. Freeman, 1982.
J. J. Gibson. The perception of the visual world. Houghton Miffin, Boston, 1950.
K.A. Stevens. On gradients and texture“gradients”. Journal of Experimental Psychology:general, 113(2):217–220, 1984.
K. Ikeuchi. Shape from regular patterns. Artificial Intelligence, 22:49–75, 1984.
John Aloimonos and M.J. Swain. Shape from texture. Biological Cybernetics, 58(5):345–360, 1988.
K. Kanatani and T. Chou. Shape from texture: General principle. Artificial Intelligence, 38:1–48, 1989.
R. Bajcsy and L. Lieberman. Texture gradient as a depth cue. Computer Graphics and Image Processing, 5:52–67, 1976.
John Krumm and Steve A. Shafer. Texture segmentation and shape in the same image. In IEEE International Conference on Computer Vision, pages 121–127, 1995.
B.J. Super and A.C. Bovik. Planar surface orientation from texture spatial frequencies. Pattern Recognition, 28(5):729–743, 1995.
Michael J. Black and Ruth Rosenholtz. Robust estimation of multiple surfaces shapes from occluded textures. In IEEE International Symposium on Computer Vision, pages 485–490, 1995.
J. Malik and R. Rosenholtz. A differential method for computing local shape-from-texture for planar and curved surfaces. In IEEE Conference on Vision and Pattern Recognition, pages 267–273, 1993.
Jonas Garding and Tony Lindeberg. Direct computation of shape cues using scale-adapted spatial derivatives operators. International Journal of Computer Vision, 17(2):163–191, 1994.
J.V. Stone and S.D. Isard. Adaptive scale filtering: A general method for obtaining shape from texture. IEEE Trans. on Pattern Analysis and Machine Intelligence, 17(7):713–718, 1995.
K.A. Stevens. Slant-tilt: the visual encoding of surface orientation. Biological Cybernetics, 46:183–195, 1983.
W.G. Carrara, R.S. Goodman, and R.M. Majewski. Spotlight synthetic aperture radar: signal processing algorithms. Artech House, USA, 1995.
Gabor D. Theory of communication. Journal of the Inst. Elect. Eng., 93:429–457, 1946.
S.M. Kay. Modern Spectral Estimation:Theory and Application. Prentice Hall, 1988.
E. Ribeiro and E.R. Hancock. 3-d planar orientation from texture: estimating vanishing point from local spectral analysis. In IX British machine Vision Conference, pages 326–335, Sep. 1998.
Phil Brodatz. Textures: A Photographic Album for Artists and Designers. Dover, New York, 1966.
E. Ribeiro and E.R. Hancock. Estimating the 3d orientation from texture planes using local spectral analysis. Image and Vision Computing, 18(8):619–631, 2000.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ribeiro, E., Hancock, E.R. (2000). Adapting Spectral Scale for Shape from Texture. In: Computer Vision - ECCV 2000. ECCV 2000. Lecture Notes in Computer Science, vol 1842. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45054-8_28
Download citation
DOI: https://doi.org/10.1007/3-540-45054-8_28
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67685-0
Online ISBN: 978-3-540-45054-2
eBook Packages: Springer Book Archive