Shape from texture using Markov random field models and stereo-windows

The problem of extracting the local shape information of a 3D textured surface from a single 2D image is addressed. The textured objects of interest are planar and developable surfaces that are viewed as originating by laying down 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). The probability density function of the projected planar parent texture 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.<<ETX>>

[1]  Ruzena Bajcsy,et al.  Texture gradient as a depth cue , 1976 .

[2]  Berthold K. P. Horn.  Obtaining shape from shading information , 1989 .

[3]  David B. Cooper,et al.  Simple Parallel Hierarchical and Relaxation Algorithms for Segmenting Noncausal Markovian Random Fields , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Katsushi Ikeuchi,et al.  Shape from Regular Patterns , 1984, Artif. Intell..

[5]  Kenichi Kanatani,et al.  Detection of Surface Orientation and Motion from Texture by a Stereological Technique , 1984, Artif. Intell..

[6]  Berthold K. P. Horn.  Robot vision , 1986, MIT electrical engineering and computer science series.

[7]  J. Aloimonos.  Shape from texture , 1988, Biological cybernetics.

[8]  Kent A. Stevens,et al.  The Visual Interpretation of Surface Contours , 1981, Artif. Intell..

[9]  John W. Woods,et al.  Two-dimensional discrete Markovian fields , 1972, IEEE Trans. Inf. Theory.

[10]  Toshiyuki Sakai,et al.  Obtaining Surface Orientation from Texels under Perspective Projection , 1981, IJCAI.

[11]  Roland T. Chin,et al.  Shape from texture using the Wigner distribution , 1990, Comput. Vis. Graph. Image Process..

[12]  Rama Chellappa,et al.  Estimation and choice of neighbors in spatial-interaction models of images , 1983, IEEE Trans. Inf. Theory.

[13]  J. Besag.  Spatial Interaction and the Statistical Analysis of Lattice Systems , 1974 .

[14]  Fernand S. Cohen,et al.  Markov random fields for image modelling and analysis , 1986 .

[15]  Rangasami L. Kashyap,et al.  3-D Shape from a Shaded and Textural Surface Image , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Y. J. Tejwani,et al.  Robot vision , 1989, IEEE International Symposium on Circuits and Systems,.

[17]  Lisa M. Brown,et al.  Surface Orientation from Projective Foreshortening of Isotropic Texture Autocorrelation , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Anup Basu,et al.  Texture, contour, shape, and motion , 1987, Pattern Recognit. Lett..

[19]  J. Besag,et al.  On the estimation and testing of spatial interaction in Gaussian lattice processes , 1975 .

[20]  R. Hetherington.  The Perception of the Visual World , 1952 .

[21]  Azriel Rosenfeld,et al.  Digital Picture Processing , 1976 .