A stereo model using LoG and Gabor filtering
- PMID: 8817768
- DOI: 10.1163/156856896x00024
A stereo model using LoG and Gabor filtering
Abstract
This paper presents a computational model for stereopsis. Laplacian of Gaussian filters are used to extract spatial features and a set of one-octave Gabor filters is used to extract orientation information from a scene. A mapping from a 3D space onto two 2D image planes is derived using a Gaussian sphere model. The determinant of the Jacobian of the mapping is derived and matching is performed using zero-crossings associated with their orientation information. Relaxation labelling is used as a co-operative process for solving the correspondence problem.
Similar articles
-
Spatial frequency tuned channels: implications for structure and function from psychophysical and computational studies of stereopsis.Philos Trans R Soc Lond B Biol Sci. 1980 Jul 8;290(1038):95-116. doi: 10.1098/rstb.1980.0085. Philos Trans R Soc Lond B Biol Sci. 1980. PMID: 6106245
-
Transparency and the uniqueness constraint in human and computer stereo vision.Nature. 1990 Oct 11;347(6293):553-6. doi: 10.1038/347553a0. Nature. 1990. PMID: 2215681
-
Perception of 3D surface orientation from skew symmetry.Vision Res. 2001 Nov;41(24):3163-83. doi: 10.1016/s0042-6989(01)00187-0. Vision Res. 2001. PMID: 11711141
-
Fechner, information, and shape perception.Atten Percept Psychophys. 2011 Nov;73(8):2353-78. doi: 10.3758/s13414-011-0197-4. Atten Percept Psychophys. 2011. PMID: 21879419 Review.
-
Pairwise comparison technique: a simple solution for depth reconstruction.J Opt Soc Am A. 1993 Jun;10(6):1129-35. doi: 10.1364/josaa.10.001129. J Opt Soc Am A. 1993. PMID: 8320583 Review.