Shortcuts in shape classification from two images

Abstract Exact structure from motion is an ill-posed computation and therefore is sensitive to noise. It is shown here that a qualitative shape feature, the classification of surfaces into convex, concave, cylindrical, planar, and hyperbolic regions, can be computed directly from motion disparities, without the computation of an exact depth map. It is also shown that humans can judge the curvature sense of three points undergoing apparent motion from two, three, and four views with success rate significantly above chance.

[1]  Ellen C. Hildreth,et al.  The perceptual buildup of three-dimensional structure from motion , 1989, Perception & psychophysics.

[2]  Andrew Blake,et al.  Robust Estimation of Surface Curvature from Deformation of Apparent Contours , 1990, ECCV.

[3]  Tomaso Poggio,et al.  Computational vision and regularization theory , 1985, Nature.

[4]  Andrea J. van Doorn,et al.  Invariant Properties of the Motion Parallax Field due to the Movement of Rigid Bodies Relative to an Observer , 1975 .

[5]  J S Lappin,et al.  Accurate visual measurement of three-dimensional moving patterns. , 1983, Science.

[6]  Thomas S. Huang,et al.  Uniqueness and Estimation of Three-Dimensional Motion Parameters of Rigid Objects with Curved Surfaces , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  T Poggio,et al.  Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks , 1990, Science.

[8]  Gilad Adiv,et al.  Determining Three-Dimensional Motion and Structure from Optical Flow Generated by Several Moving Objects , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  T. Poggio,et al.  A network that learns to recognize three-dimensional objects , 1990, Nature.

[10]  S Ullman,et al.  Maximizing Rigidity: The Incremental Recovery of 3-D Structure from Rigid and Nonrigid Motion , 1984, Perception.

[11]  Shimon Ullman,et al.  Computational Studies in the Interpretation of Structure and Motion: Summary and Extension , 1983 .

[12]  Daphna Weinshall,et al.  Direct computation of qualitative 3D shape and motion invariants , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[13]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[14]  James T. Todd,et al.  Ordinal structure in the visual perception and cognition of smoothly curved surfaces. , 1989 .

[15]  Daphna Weinshall.  Direct Computation of Qualitative 3-D Shape and Motion Invariants , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  H. C. Longuet-Higgins,et al.  The interpretation of a moving retinal image , 1980, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[17]  Daphna Weinshall,et al.  Qualitative Depth from Stereo, with Applications , 1990, Comput. Vis. Graph. Image Process..

[18]  Donald Michie,et al.  Machine Intelligence 7 , 1975 .

[19]  Claes von Hofsten,et al.  Visual perception of motion in depth: Application of a vector model to three-dot motion patterns , 1973 .

[20]  Dana H. Ballard,et al.  Animate Vision , 1991, Artif. Intell..

[21]  Yiannis Aloimonos,et al.  Purposive and qualitative active vision , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.