Computational Experiments with a Feature Based Stereo Algorithm

Computational models of the human stereo system can provide insight into general information processing constraints that apply to any stereo system, either artificial or biological. In 1977 Marr and Poggio proposed one such computational model, which was characterized as matching certain feature points in difference-of-Gaussian filtered images and using the information obtained by matching coarser resolution representations to restrict the search space for matching finer resolution representations. An implementation of the algorithm and its testing on a range of images was reported in 1980. Since then a number of psychophysical experiments have suggested possible refinements to the model and modifications to the algorithm. As well, recent computational experiments applying the algorithm to a variety of natural images, especially aerial photographs, have led to a number of modifications. In this paper, we present a version of the Marr-Poggio-Grimson algorithm that embodies these modifications, and we illustrate its performance on a series of natural images.

[1]  H J Howard,et al.  A Test for the Judgment of Distance. , 1919, Transactions of the American Ophthalmological Society.

[2]  L. S. Woodburne.  The effect of a constant visual angle upon the binocular discrimination of depth differences , 1934 .

[3]  R. N. Berry.  Quantitative relations among vernier, real depth, and stereoscopic depth acuities. , 1948, Journal of experimental psychology.

[4]  B. Julesz.  Binocular depth perception of computer-generated patterns , 1960 .

[5]  J. Pokorny.  Foundations of Cyclopean Perception , 1972 .

[6]  Hans P. Morevec.  Towards automatic visual obstacle avoidance , 1977, IJCAI 1977.

[7]  Hans P. Moravec.  Towards Automatic Visual Obstacle Avoidance , 1977, IJCAI.

[8]  Tomaso Poggio,et al.  A Theory of Human Stereo Vision , 1977 .

[9]  David Marr,et al.  Representing Visual Information , 1977 .

[10]  Christopher W. Tyler,et al.  Spatial Limitations Of Human Stereoscopic Vision , 1977, Optics & Photonics.

[11]  T. Poggio,et al.  A computational theory of human stereo vision , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[12]  J. Bergen,et al.  A four mechanism model for threshold spatial vision , 1979, Vision Research.

[13]  Ellen C. Hildreth,et al.  Implementation Of A Theory Of Edge Detection , 1980 .

[14]  William B. Thompson,et al.  TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE , 2009 .

[15]  Tomaso Poggio,et al.  Some Comments on a Recent Theory of Stereopsis , 1980 .

[16]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[17]  Hans P. Moravec.  Obstacle avoidance and navigation in the real world by a seeing robot rover , 1980 .

[18]  D. Marr,et al.  An Information Processing Approach to Understanding the Visual Cortex , 1980 .

[19]  T. O. Binford,et al.  Geometric Constraints In Stereo Vision , 1980, Optics & Photonics.

[20]  John Frisby,et al.  The role of spatial frequency tuned channels in vergence control , 1980, Vision Research.

[21]  D. Marr,et al.  Smallest channel in early human vision. , 1980, Journal of the Optical Society of America.

[22]  J. Mayhew,et al.  Vergence Eye Movements Made in Response to Spatial-Frequency-Filtered Random-Dot Stereograms , 1981, Perception.

[23]  Thomas O. Binford,et al.  Depth from Edge and Intensity Based Stereo , 1981, IJCAI.

[24]  G. Brink,et al.  Diplopia thresholds and the initiation of vergence eye-movements , 1981, Vision Research.

[25]  John E. W. Mayhew,et al.  Psychophysical and Computational Studies Towards a Theory of Human Stereopsis , 1981, Artif. Intell..

[26]  G. Brink,et al.  What is the diplopia threshold? , 1981, Perception & psychophysics.

[27]  Thomas O. Binford,et al.  Intensity Discontinuity Location to SubPixel Precision , 1981, IJCAI.

[28]  H. K. Nishihara,et al.  Towards A Real Time Implementation Of The Marr And Poggio Stereo Matcher , 1981, Other Conferences.

[29]  Eric L. W. Grimson,et al.  From Images to Surfaces: A Computational Study of the Human Early Visual System , 1981 .

[30]  W E Grimson,et al.  A computer implementation of a theory of human stereo vision. , 1981, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[31]  J Mayhew,et al.  The Interpretation of Stereo-Disparity Information: The Computation of Surface Orientation and Depth , 1982, Perception.

[32]  H. C. Longuet-Higgins.  The Role of the Vertical Dimension in Stereoscopic Vision , 1982, Perception.

[33]  Demetri Terzopoulos.  Multi-Level Reconstruction of Visual Surfaces: Variational Principles and Finite Element Representations , 1982 .

[34]  J. E. W. Mayhew,et al.  A computational model of binocular depth perception , 1982, Nature.

[35]  W E Grimson,et al.  A computational theory of visual surface interpolation. , 1982, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[36]  K. Prazdny.  Computing Convergence Angle From Random Dot Stereograms , 1983, IJCAI.

[37]  W. Eric L. Grimson.  Surface consistency constraints in vision , 1983, Comput. Vis. Graph. Image Process..

[38]  J. Canny.  Finding Edges and Lines in Images , 1983 .

[39]  Michael Kass,et al.  A Computational Framework for the Visual Correspondence Problem , 1983, IJCAI.

[40]  W. Eric L. Grimson,et al.  An implementation of a computational theory of visual surface interpolation , 1983, Comput. Vis. Graph. Image Process..

[41]  H. Wilson.  Psychophysical Evidence for Spatial Channels , 1983 .

[42]  Demetri Terzopoulos,et al.  Multiresolution computation of visible-surface representations , 1984 .

[43]  Takeo Kanade,et al.  Stereo by Intra- and Inter-Scanline Search Using Dynamic Programming , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.