Models for motion perception

MODELS FOR MOTION PERCEPTION David 1. Heeger Ruzena Bajcsy (advisor) As observers move through the environment or shift their direction of gaze, the world moves past them. In addition, there may be objects that are moving differently from the static background, either rigid-body motions or nonrigid (e.g., turbulent) ones. This dissertation discusses several models for motion perception. The models rely on first measuring motion energy, a multiresolution representation of motion infonnation extracted from image sequences. The image flow model combines the outputs of a set of spatiotempora! motion-energy filters to estimate image velocity, consonant with current views regarding the neurophysiology and psychophysics of motion perception. A parallel implementation computes a distributed representation of image velocity that encodes both a velocity estimate and the uncertainty in that estimate. In addition, a numerical measure of image-flow uncertainty is derived. The egomoticn model poses the detection of moving objects and the recovery of depth from motion as sensor fusion problems that necessitate combining infollllation from different sensors in the presence of noise and uncertainty. Image sequences are segmented by finding image regions corresponding to entire objects that are moving differently from the stationary background. The turbulent flow model utilizes a fractal-based model of turbulence, and estimates the fractal scaling parameter of fractal image sequences from the outputs of motion-energy filters. Some preliminary results demonstrate the model's potential for discriminating image regions based on fractal scaling.

[1]  Walter L. Smith Probability and Statistics , 1959, Nature.

[2]  Donald D. Hoffman,et al.  Parts of recognition , 1984, Cognition.

[3]  Benoit B. Mandelbrot,et al.  Fractal Geometry of Nature , 1984 .

[4]  Allen M. Waxman,et al.  Surface Structure and Three-Dimensional Motion from Image Flow Kinematics , 1985 .

[5]  R. Paul Robot manipulators : mathematics, programming, and control : the computer control of robot manipulators , 1981 .

[6]  Green Bf Figure coherence in the kinetic depth effect. , 1961 .

[7]  B. Green Figure coherence in the kinetic depth effect. , 1961, Journal of experimental psychology.

[8]  Edward H. Adelson,et al.  Orthogonal Pyramid Transforms For Image Coding. , 1987, Other Conferences.

[9]  Gregory D. Hager,et al.  Information and multi-sensor coordination , 1986, UAI.

[10]  Dana H. Ballard,et al.  ACTIVE NAVIGATION: TRACKING AN ENVIRONMENTAL POINT CONSIDERED BENEFICIAL. , 1986 .

[11]  J. Hay,et al.  Optical motions and space perception: an extension of Gibson's analysis. , 1966, Psychological review.

[12]  P. Sander Decision and estimation theory , 1980 .

[13]  D. Regan,et al.  Looming detectors in the human visual pathway , 1978, Vision Research.

[14]  M. Feigenbaum Universal behavior in nonlinear systems , 1983 .

[15]  J. Roach,et al.  Determining the movement of objects from a sequence of images , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  I. G. BONNER CLAPPISON Editor , 1960, The Electric Power Engineering Handbook - Five Volume Set.

[17]  G. Johansson Visual motion perception. , 1975, Scientific American.

[18]  E. Gibson,et al.  The development of perception , 1983 .

[19]  D Regan,et al.  Visually guided locomotion: psychophysical evidence for a neural mechanism sensitive to flow patterns. , 1979, Science.

[20]  Alex Pentland,et al.  Fractal-Based Description of Natural Scenes , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  S. McKee,et al.  Precise velocity discrimination despite random variations in temporal frequency and contrast , 1986, Vision Research.

[22]  D'arcy W. Thompson,et al.  On Growth and Form , 1917, Nature.

[23]  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.

[24]  Steven W. Zucker,et al.  Trace Inference, Curvature Consistency, and Curve Detection , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Norman I. Badler,et al.  Temporal scene analysis: conceptual descriptions of object movements. , 1975 .

[26]  Ellen C. Hildreth,et al.  Computations Underlying the Measurement of Visual Motion , 1984, Artif. Intell..

[27]  D. Burr,et al.  Contrast sensitivity at high velocities , 1982, Vision Research.

[28]  T. Poggio,et al.  Visual hyperacuity: spatiotemporal interpolation in human vision , 1981, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[29]  Hugh Durrant-Whyte,et al.  Integration, coordination, and control of multi-sensor robot systems , 1987 .

[30]  M. Wertheimer Laws of organization in perceptual forms. , 1938 .

[31]  S. L. Eerm,et al.  Fractal properties of rain, and a fractal model , 1985 .

[32]  Yiannis Aloimonos,et al.  Active vision , 2004, International Journal of Computer Vision.

[33]  Daryl T. Lawton,et al.  Processing translational motion sequences , 1983, Comput. Vis. Graph. Image Process..

[34]  A. Witkin,et al.  On the Role of Structure in Vision , 1983 .

[35]  Allen M. Waxman,et al.  Dynamic Stereo: Passive Ranging to Moving Objects from Relative Image Flows , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  Amar Mitiche,et al.  On Kineopsis and Computation of Structure and Motion , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  E. Adelson,et al.  Phenomenal coherence of moving visual patterns , 1982, Nature.

[38]  Donald D. Hoffman,et al.  Inferring the relative three-dimensional positions of two moving points. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[39]  Jake K. Aggarwal,et al.  Segmentation through the detection of changes due to motion , 1979 .

[40]  A. Bandopadhay,et al.  Constraints on the Computation of Rigid Motion Parameters from Retinal Displacements. , 1985 .

[41]  R. Voss Random Fractal Forgeries , 1985 .

[42]  Minas E. Spetsakis,et al.  Closed Form Solution to the Structure from Motion Problem from Line Correspondences , 1987, AAAI.

[43]  D. H. Kelly Motion and vision. II. Stabilized spatio-temporal threshold surface. , 1979, Journal of the Optical Society of America.

[44]  J. O'Rourke,et al.  Model-based image analysis of human motion using constraint propagation , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[45]  Jan J. Koenderink,et al.  Local structure of movement parallax of the plane , 1976 .

[46]  Irving Biederman,et al.  Human image understanding: Recent research and a theory , 1985, Comput. Vis. Graph. Image Process..

[47]  Ruzena Bajcsy,et al.  Object Recognition Using Vision and Touch , 1985, IJCAI.

[48]  J. Daugman Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[49]  Steven W. Zucker,et al.  From orientation selection to optical flow , 1987, Comput. Vis. Graph. Image Process..

[50]  David W. Murray,et al.  Scene Segmentation from Visual Motion Using Global Optimization , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[51]  Shaun Lovejoy,et al.  Scale Invariance, Symmetries, Fractals, and Stochastic Simulations of Atmospheric Phenomena , 1986 .

[52]  D Regan,et al.  Visual responses to vorticity and the neural analysis of optic flow. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[53]  Philip S. Brown,et al.  The Variance Spectrum of Tropospheric Winds over Eastern Europe , 1979 .

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

[55]  Alex Pentland,et al.  Perceptual Organization and the Representation of Natural Form , 1986, Artif. Intell..

[56]  Aaron F. Bobick,et al.  Classifying Objects from Visual Information , 1986 .

[57]  A. Pentland Perceptual organization and the representation of natural form , 1987 .

[58]  Andrew B. Watson,et al.  A look at motion in the frequency domain , 1983 .

[59]  H. Barrow,et al.  RECOVERING INTRINSIC SCENE CHARACTERISTICS FROM IMAGES , 1978 .

[60]  David Heeger,et al.  Depth and Flow From Motion Energy , 1986, AAAI.

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

[62]  M. Subbarad,et al.  Interpretation of Visual Motion: A Computational Study , 1988 .

[63]  Harry Wechsler,et al.  Derivation of optical flow using a spatiotemporal-Frequency approach , 1987, Comput. Vis. Graph. Image Process..

[64]  Uriel Frisch,et al.  A simple dynamical model of intermittent fully developed turbulence , 1978, Journal of Fluid Mechanics.

[65]  Berthold K. P. Horn,et al.  Passive navigation , 1982, Computer Vision Graphics and Image Processing.

[66]  Alex Pentland,et al.  On the Imaging of Fractal Surfaces , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[67]  P. Stevens Patterns in Nature , 1974 .

[68]  D J Heeger,et al.  Model for the extraction of image flow. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[69]  Ramesh C. Jain,et al.  Direct Computation of the Focus of Expansion , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[70]  Philip E. Gill,et al.  Practical optimization , 1981 .

[71]  E. P. Krotkov,et al.  Exploratory visual sensing for determining spatial layout with an agile stereo camera system , 1987 .

[72]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[73]  Donald D. Hoffman Inferring local surface orientation from motion fields. , 1982, Journal of the Optical Society of America.

[74]  A. Pentland Recognition by Parts , 1987 .

[75]  Shahriar Negahdaripour,et al.  IEEE Transactions on Pattern Analysis and Machine Intelligence , 2004 .

[76]  S. Ullman Recent Computational Studies in the Interpretation of Structure from Motion , 1983 .

[77]  John K. Tsotsos,et al.  The Sensitivity of Motion and Structure Computations , 1987, AAAI.

[78]  Demetri Terzopoulos,et al.  Regularization of Inverse Visual Problems Involving Discontinuities , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[79]  Allen M. Waxman,et al.  Contour Evolution, Neighborhood Deformation, and Global Image Flow: Planar Surfaces in Motion , 1985 .

[80]  Peter J. Burt,et al.  Fast algorithms for estimating local image properties , 1982, Comput. Graph. Image Process..

[81]  J. Gibson The Ecological Approach to Visual Perception , 1979 .

[82]  John G. Proakis,et al.  Probability, random variables and stochastic processes , 1985, IEEE Trans. Acoust. Speech Signal Process..

[83]  E H Adelson,et al.  Spatiotemporal energy models for the perception of motion. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[84]  William B. Thompson,et al.  Disparity Analysis of Images , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[85]  R. Aris Vectors, Tensors and the Basic Equations of Fluid Mechanics , 1962 .

[86]  Berthold K. P. Horn,et al.  COMPUTATIONALLY-EFFICIENT METHODS FO R RECOVERING TRANSLATIONAL MOTIO N , 1987 .

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

[88]  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 .

[89]  Jake K. Aggarwal,et al.  Visually Interpreting the Motion of Objects in Space , 1981, Computer.

[90]  Allen M. Waxman,et al.  Binocular Image Flows: Steps Toward Stereo-Motion Fusion , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[91]  A. Waxman An image flow paradigm , 1987 .

[92]  A.H. Haddad,et al.  Applied optimal estimation , 1976, Proceedings of the IEEE.

[93]  J H Rieger,et al.  Processing differential image motion. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[94]  David G. Lowe,et al.  Three-Dimensional Object Recognition from Single Two-Dimensional Images , 1987, Artif. Intell..

[95]  S. McKee A local mechanism for differential velocity detection , 1981, Vision Research.

[96]  A J Ahumada,et al.  Model of human visual-motion sensing. , 1985, Journal of the Optical Society of America. A, Optics and image science.

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

[98]  J. van Santen,et al.  Elaborated Reichardt detectors. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[99]  A. Chorin Estimates of intermittency, spectra, and blow-up in developed turbulence , 1981 .

[100]  Dana H. Ballard,et al.  Rigid body motion from depth and optical flow , 1983, Comput. Vis. Graph. Image Process..

[101]  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.

[102]  Michael Leyton,et al.  Generative systems of analyzers , 1985, Comput. Vis. Graph. Image Process..

[103]  Valdis Berzins,et al.  Dynamic Occlusion Analysis in Optical Flow Fields , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[104]  Ralph Hartley,et al.  Segmentation of optical flow fields by pyramid linking , 1985, Pattern Recognit. Lett..