On The Three Diumensionality of Motion Correspondence

Motion correspondence has long been regarded by psychophysicists as being performed with respect to ~wo dimensional distances only. This is despite the fact that obtaining correspondence of 3D objects from 2D positions is It mathematically ill posed problem. In this work, we reinterpret e.xLant psychophysical experiments that seemingly support the claim about two dimensionality of correspondence, and discuss avai.lable evidence from neuroanatomy and psychophysics which seems to indicate that correspondence problem is solved by a tnree dimensional process. Brief remarks about the significance of this analysis for computer vision are also made.

[1]  Petersik Jt.  The two-process distinction in apparent motion. , 1989 .

[2]  Ishwar K. Sethi,et al.  Finding Trajectories of Feature Points in a Monocular Image Sequence , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  J T Todd,et al.  The visual perception of smoothly curved surfaces from minimal apparent motion sequences , 1991, Perception & psychophysics.

[4]  Zygmunt Pizlo,et al.  Is vision metric? Comment on Lappin and Love (1992) , 1994, Perception & psychophysics.

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

[6]  I M Smith,et al.  The Effect of Two-Dimensional and Three-Dimensional Distance on Apparent Motion , 1983, Perception.

[7]  J T Petersik.  The two-process distinction in apparent motion. , 1989, Psychological bulletin.

[8]  Chia-Hoang Lee,et al.  Using elastic nets for correspondence in range data , 1993, IEEE International Conference on Neural Networks.

[9]  J. Todd,et al.  Ordinal structure in the visual perception and cognition of smoothly curved surfaces. , 1989, Psychological review.

[10]  John Primrose.  Geometry of visual space , 1951 .

[11]  T. D. Williams,et al.  Depth from camera motion in a real world scene , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Takeo Kanade,et al.  Integrated sensor and range-finding analog signal processor , 1991 .

[13]  Anupam Joshi,et al.  Correspondence problem in image sequence analysis , 1993, Pattern Recognit..

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

[15]  E. Johnston.  Systematic distortions of shape from stereopsis , 1991, Vision Research.

[16]  D Marr,et al.  Cooperative computation of stereo disparity. , 1976, Science.

[17]  D. Hubel,et al.  Segregation of form, color, movement, and depth: anatomy, physiology, and perception. , 1988, Science.

[18]  Steven W. Zucker,et al.  The Local Structure of Image Discontinuities in One Dimension , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  D. C. Van Essen,et al.  Concurrent processing streams in monkey visual cortex , 1988, Trends in Neurosciences.

[20]  S. Ullman.  The Interpretation of Visual Motion , 1979 .

[21]  J T Todd,et al.  The perception of 3-dimensional affine structure from minimal apparent motion sequences , 1990, Perception & psychophysics.

[22]  Anupam Joshi,et al.  On the problem of correspondence in range data and some inelastic uses for elastic nets , 1995, IEEE Trans. Neural Networks.

[23]  A. A. Smith.  The geometry of visual space. , 1959, Psychological review.

[24]  G G Haydu,et al.  Perception of Apparent Motion. , 1960, Science.

[25]  S Ullman,et al.  Two Dimensionality of the Correspondence Process in Apparent Motion , 1978, Perception.