Recovery of surface pose from texture orientation statistics under perspective projection

In a seminal paper, Witkin (1981) derived a model of surface slant and tilt recovery based on the statistics of the orientations of texture elements (texels) on a planar surface. This model made use of basic mathematical properties of probability distributions to formulate a posterior distribution on slant and tilt given a set of image orientations under orthographic projection. One problem with the Witkin model was that it produced a posterior distribution with multiple maxima, reflecting the inherent ambiguity in scene reconstruction under orthographic projection. In the present article, we extend Witkin’s method to incorporate the effects of perspective projection. An identical approach is used to that of Witkin; however, the model now reflects the effects of perspective projection on texel orientation. Performance of the new model is compared against that of Witkin’s model in a basic surface pose recovery task using both a maximum a posteriori (MAP) decision rule and a rule based on the expected value of the posterior distribution. The resultant posterior of the new model is shown to have only one maximum and thereby the ambiguity in scene interpretation is resolved. Furthermore, the model performs better than Witkin’s model using both MAP and expected value decision rules. The results are discussed in the context of human slant estimation.

[1]  Alan L. Yuille,et al.  An Extremum Principle for Shape from Contour , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  D. Sheinberg,et al.  Shape from texture: ideal observers and human psychophysics , 1996 .

[3]  H. Gruber,et al.  Perception of Slanted Surfaces , 1956 .

[4]  M. Landy,et al.  Bayesian Modelling of Visual Perception , 2002 .

[5]  Berthold K. P. Horn,et al.  Shape from shading , 1989 .

[6]  Jitendra Malik,et al.  Surface orientation from texture: Isotropy or homogeneity (or both)? , 1997, Vision Research.

[7]  Andrew Blake,et al.  Shape from Texture: Estimation, Isotropy and Moments , 1990, Artif. Intell..

[8]  E. Mingolla,et al.  Perception of solid shape from shading , 1989, Biological Cybernetics.

[9]  David C Knill,et al.  Mixture models and the probabilistic structure of depth cues , 2003, Vision Research.

[10]  Jitendra Malik,et al.  Computing Local Surface Orientation and Shape from Texture for Curved Surfaces , 1997, International Journal of Computer Vision.

[11]  J. Frisby,et al.  Does the human visual system implement an ideal observer theory of slant from texture? , 1996, Vision Research.

[12]  James V. Stone.  Shape from local and global analysis of texture , 1993 .

[13]  Andrea Li,et al.  Perception of three-dimensional shape from texture is based on patterns of oriented energy , 2000, Vision Research.

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

[15]  A. U.S.,et al.  Recovering Surface Shape and Orientation from Texture , 2002 .

[16]  David C. Knill,et al.  Surface orientation from texture: ideal observers, generic observers and the information content of texture cues , 1998, Vision Research.

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

[18]  Rajesh P. N. Rao,et al.  Probabilistic Models of the Brain: Perception and Neural Function , 2002 .

[19]  Jonas Gårding,et al.  Direct Estimation of Shape from Texture , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  J. Garding,et al.  Shape from texture and contour by weak isotropy , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[21]  Pascal Mamassian,et al.  Observer biases in the 3D interpretation of line drawings , 1998, Vision Research.

[22]  M. Hogervorst,et al.  The role of perspective effects and accelerations in perceived three-dimensional structure-from-motion. , 2000, Journal of experimental psychology. Human perception and performance.

[23]  James H. Elder,et al.  Texture properties affecting the accuracy of surface attitude judgements , 2006, Vision Research.

[24]  Tatsuto Takeuchi,et al.  Tilt dependency of slant aftereffect , 2000, Vision Research.

[25]  M. Braunstein.  Motion and texture as sources of slant information. , 1968, Journal of experimental psychology.

[26]  J. Koenderink,et al.  Surface perception in pictures , 1992, Perception & psychophysics.

[27]  R. A. Eagle,et al.  The role of perspective information in the recovery of 3D structure-from-motion , 1999, Vision Research.