This Article 
 Bibliographic References 
 Add to: 
Local Surface Shape Estimation of 3-D Textured Surfaces using Gaussian Markov Random Fields and Stereo Windows
October 1993 (vol. 15 no. 10)
pp. 1091-1098

The problem of extracting the local shape information of a 3-D texture surface from a single 2-D image by tracking the perceived systematic deformations the texture undergoes by virtue of being present on a 3-D surface and by virtue of being imaged is examined. The surfaces of interest are planar and developable surfaces. The textured objects are viewed as originating by laying a rubber planar sheet with a homogeneous parent texture on it onto the objects. The homogeneous planar parent texture is modeled by a stationary Gaussian Markov random field (GMRF). A probability distribution function for the texture data obtained by projecting the planar parent texture under a linear camera model is derived, which is an explicit function of the parent GMRF parameters, the surface shape parameters. and the camera geometry. The surface shape parameter estimation is posed as a maximum likelihood estimation problem. A stereo-windows concept is introduced to obtain a unique and consistent parent texture from the image data that, under appropriate transformations, yields the observed texture in the image. The theory is substantiated by experiments on synthesized as well as real images of textured surfaces.

[1] B. K. P. Horn,Robot Vision. Cambridge, MA: M.I.T. Press, 1986.
[2] D. Marr, "Representing visual information--A computational approach," inComputer Vision Systems, A. R. Hanson and E. M. Riseman, Eds. New York: Academic, 1978.
[3] B. K. P. Horn, "Obtaining shape from shading information," inPsychology of Computer Vision, P. H. Winston, Ed. New York: McGraw-Hill, 1975, ch. 4.
[4] B. K. P. Horn and R. W. Sjoberg, "Calculating the reflectance map,"Applied Opt., vol. 18, June 1979.
[5] D. Marr, "Analysis of occluding contour," inProc. Royal Soc. Lon. B, vol. 197, 1977.
[6] K. A. Stevens, "The visual interpretation of visual contours,"Artificial Intell., vol. 17, Aug. 1981.
[7] J. J. Gibson,The Perception of the Visual World. Boston: Houghton Mifflin, 1950.
[8] R. Bajcsy and L. Lieberman, "Texture gradients as a depth cue,"Comput. Graphics Image Processing, vol. 5, 1976.
[9] Y. C. Jau and R. T. Chinn, "Shape from texture using the Wigner distribution,"Comput. Vision Graphics Image Processing, vol. 52, no. 2, Nov. 1990.
[10] A. P. Witkin, "Recovering surface shape and orientation from texture,"Artificial Intell., vol. 17, 1981.
[11] L. S. Davis, L. Lanos, and S. M. Dunn, "Efficient recovery of shape from texture,"IEEE Trans. Pattern Anal. Machine Intell., vol. 5, no. 5, 1983.
[12] K. Kanatani, "Detection of surface orientation and motion from texture by a stereological technique,"Artificial Intell., vol. 23, pp. 213-237, 1984.
[13] K. Ikeuchi, "Shape from regular patterns,"Artificial Intell., vol. 22, 1984.
[14] J. R. Kender, "Shape from texture," Ph.D. dissertation, Carnegie-Mellon Univ., Pittsburgh, PA, Rep. CMU-CS-81-102, Nov. 1980.
[15] Y. Ohta, K. Maenobu, and T. Sakai, "Obtaining surface orientation from texels under perspective projection," inProc. Int. Joint Conf. Artificial Intell., 1980.
[16] D. Blostein, and N. Ahuja, "Shape from texture: Integrating textureelement extraction and surface estimation,"IEEE Trans. Pattern Anal. Machine Intell., vol. 11, no. 12, 1989.
[17] D. Brzakovic, "Computer based 3-D description from texture," Ph.D. dissertation, Dept. of Elect. Eng., Univ. of Florida, 1984.
[18] L. G. Brown and H. Shvaytser, "Surface orientation from projective foreshortening of isotropic texture autocorrelation,"IEEE Trans. Pattern Anal. Machine Intell., vol. 12, no. 6, 1990.
[19] Y. Choe and R. Kashyap, "3-D Shape from a shaded and textured surface image,"IEEE Trans. Pattern Anal. Machine Intell., vol. 13, no. 9, 1991.
[20] R. Chellappa and R. Kashyap, "Texture synthesis using 2-D noncausal autoregressive models,"IEEE Trans. Acoust. Speech Signal Processing, vol. ASSP-33, Feb. 1985.
[21] F. S. Cohen,Markov Random Fields for Image Modelling and Analysis, U. Desai, Ed. New York: Kluwer Academic, Sept. 1986.
[22] F. S. Cohen and D. B. Cooper, "Simple parallel hierarchical and relaxation algorithms for segmenting noncausal Markovian fields,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-9, pp. 195-219, March 1987.
[23] F. S. Cohen and M. S. Patel, "Modeling and synthesis of images of 3-D textured surfaces,"CVGIP: Graphical Models Image Processing, vol. 53, no. 6, Nov. 1991.
[24] F. S. Cohen and M. S. Patel, "Shape from texture using Gaussian Markov random fields," inTheory and Applications of Markov Random Fields for Image Processing, R. Chellappa and A. K. Jain, Eds. New York: Academic, 1993.
[25] J. Woods, "Two-dimensional discrete Markov random fields,"IEEE Trans. Inform. Theory,vol. IT-18, pp. 232-240, 1972.
[26] J. Besag, "Spatial interaction and the statistical analysis of lattice systems,"J. Royal Stat. Soc., Series B, vol. 36, 1974.
[27] J. Besag and P. Moran, "On the estimation and testing of spatial interaction in Gaussian lattices,"Biometrika, vol. 62, 1975.
[28] R. Kashyap and R. Chellapa, "Estimation and choice of neighbors in spatial interaction models of images,"IEEE Trans. Inform. Theory, vol. IT-29, pp. 60-72, Jan. 1983.
[29] F. S. Cohen, Z. Fan, and M. S. Patel, "Classification of rotated and scaled textured images using Gaussian Markov random field models,"IEEE Trans. Pattern Anal. Machine Intell., Feb. 1991.
[30] P. J. Besl and R. C. Jain, "Intrinsic and extrinsic surface characteristics," inProc. Int. Conf. Comput. Vision Patt. Recogn., 1985.
[31] R. D. Rimey and F. S. Cohen, "A maximum likelihood approach for segmenting range data,"IEEE Trans. Robotics Automat., Apr. 1988.
[32] A. Rosenfeld and A. Kak,Digital Picture Processing, New York: Academic, 1976.
[33] P. Brodatz,Textures. New York: Dover.
[34] M. S. Patel, "Shape extraction of 3-D textured scenes from image data," Ph.D. Dissertation, Drexel Univ. Elect. Comput. Eng. Dept., Aug. 1991.
[35] J. Aloimonos, "Shape from texture,"Biol. Cybern., vol. 58, pp. 345-360, 1988.
[36] W. Larimore, "Statistical inference on stationary random fields,"Proc. IEEE, vol. 65, no. 6, June 1977.
[37] M. S. Patel and F. S. Cohen, "Shape from texture using Markov random field models and stereo-windows,"CVPR, 1992.

Index Terms:
local surface shape estimation; MLE; planar surfaces; 3-D textured surfaces; Gaussian Markov random fields; stereo windows; single 2-D image; perceived systematic deformations; developable surfaces; stationary Gaussian Markov random field; probability distribution function; camera geometry; surface shape parameter estimation; maximum likelihood estimation problem; Markov processes; maximum likelihood estimation; stereo image processing
M.A.S. Patel, F.S. Cohen, "Local Surface Shape Estimation of 3-D Textured Surfaces using Gaussian Markov Random Fields and Stereo Windows," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 10, pp. 1091-1098, Oct. 1993, doi:10.1109/34.254067
Usage of this product signifies your acceptance of the Terms of Use.