Perceptual Organization for Scene Segmentation and Description

A data-driven system for segmenting scenes into objects and their components is presented. This segmentation system generates hierarchies of features that correspond to structural elements such as boundaries and surfaces of objects. The technique is based on perceptual organization, implemented as a mechanism for exploiting geometrical regularities in the shapes of objects as projected on images. Edges are recursively grouped on geometrical relationships into a description hierarchy ranging from edges to the visible surfaces of objects. These edge groupings, which are termed collated features, are abstract descriptors encoding structural information. The geometrical relationships employed are quasi-invariant over 2-D projections and are common to structures of most objects. Thus, collations have a high likelihood of corresponding to parts of objects. Collations serve as intermediate and high-level features for various visual processes. Applications of collations to stereo correspondence, object-level segmentation, and shape description are illustrated. >

[1]  J. Hochberg,et al.  A quantitative approach to figural "goodness". , 1953, Journal of experimental psychology.

[2]  F. Attneave.  Some informational aspects of visual perception. , 1954, Psychological review.

[3]  W. R. Garner,et al.  Goodness of pattern and pattern uncertainty. , 1963 .

[4]  E. Leeuwenberg.  A perceptual coding language for visual and auditory patterns. , 1971, The American journal of psychology.

[5]  H. Blum.  Biological shape and visual science (part I) , 1973 .

[6]  W. R. Garner.  The Processing of Information and Structure , 1974 .

[7]  Thomas O. Binford,et al.  Computer Description of Curved Objects , 1973, IEEE Transactions on Computers.

[8]  Ramakant Nevatia.  Computer Analysis of Scenes of 3-Dimensional Curved Objects , 1976 .

[9]  Ramakant Nevatia,et al.  Description and Recognition of Curved Objects , 1977, Artif. Intell..

[10]  R. Kelly,et al.  The Gestalt Photomapping System , 1977 .

[11]  D. Katz.  Gestalt Psychology: Its Nature and Significance , 1979 .

[12]  K. Laws.  Textured Image Segmentation , 1980 .

[13]  Takeo Kanade,et al.  Recovery of the Three-Dimensional Shape of an Object from a Single View , 1981, Artif. Intell..

[14]  Jerome A. Feldman,et al.  Connectionist Models and Their Properties , 1982, Cogn. Sci..

[15]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[16]  A. Treisman.  Perceptual grouping and attention in visual search for features and for objects. , 1982, Journal of experimental psychology. Human perception and performance.

[17]  Scott Kirkpatrick,et al.  Optimization by Simmulated Annealing , 1983, Sci..

[18]  M. Brady.  Criteria for Representations of Shape , 1983 .

[19]  Steven W. Zucker,et al.  On the Foundations of Relaxation Labeling Processes , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Thomas O. Binford,et al.  Perceptual Organization as a Basis for Visual Recognition , 1983, AAAI.

[21]  S. Zucker.  Computational and Psychophysical Experiments in Grouping: Early Orientation Selection , 1983 .

[22]  Geoffrey E. Hinton,et al.  Massively Parallel Architectures for AI: NETL, Thistle, and Boltzmann Machines , 1983, AAAI.

[23]  Andrew P. Witkin,et al.  Scale-Space Filtering , 1983, IJCAI.

[24]  Geoffrey E. Hinton,et al.  Parallel visual computation , 1983, Nature.

[25]  Narendra Ahuja,et al.  PERCEPTUAL SEGMENTATION OF NONHOMOGENEOUS DOT PATTERNS. , 1983 .

[26]  S. Palmer.  The Psychology of Perceptual Organization: A Transformational Approach , 1983 .

[27]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[28]  Takeo Kanade,et al.  Mapping Image Properties into Shape Constraints: Skewed Symmetry, Affine-Transformable Patterns, and the Shape-from-Texture Paradigm , 1983 .

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

[30]  Rodney A. Brooks,et al.  Model-Based Three-Dimensional Interpretations of Two-Dimensional Images , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[32]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[33]  M. Brady,et al.  Smoothed Local Symmetries and Their Implementation , 1984 .

[34]  Andrew P. Witkin,et al.  Scale-space filtering: A new approach to multi-scale description , 1984, ICASSP.

[35]  Lee R. Nackman,et al.  Three-Dimensional Shape Description Using the Symmetric Axis Transform I: Theory , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  Jonathan H Connell,et al.  Learning Shape Descriptions: Generating and Generalizing Models of Visual Objects , 1985 .

[37]  Ramakant Nevatia,et al.  Segment-based stereo matching , 1985, Comput. Vis. Graph. Image Process..

[38]  J. Hopfield,et al.  Computing with neural circuits: a model. , 1986, Science.

[39]  Azriel Rosenfeld,et al.  Axial representations of shape , 1986, Computer Vision Graphics and Image Processing.

[40]  Robert C. Bolles,et al.  Perceptual Organization and Curve Partitioning , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[41]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[42]  Allen Brookes,et al.  Detecting structure by symbolic constructions on tokens , 1987, Comput. Vis. Graph. Image Process..

[43]  Geoffrey E. Hinton,et al.  Connectionist Architectures for Artificial Intelligence , 1990, Computer.

[44]  Ramakant Nevatia,et al.  Using Symmetries For Analysis Of Shape From Contour , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[45]  Long Quan,et al.  Generating the initial hypothesis using perspective invariants for a 2D image and 3D model matching , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[46]  Ruud M. Bolle,et al.  Visual recognition using concurrent and layered parameter networks , 1989, Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[47]  Ramakant Nevatia,et al.  Using Perceptual Organization to Extract 3-D Structures , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[48]  R. Mohan.  Application of neural constraint satisfaction networks to vision , 1989, International 1989 Joint Conference on Neural Networks.

[49]  Gerard Medioni,et al.  Multi-scale contour matching in a motion sequence , 1989 .

[50]  Gerard Medioni,et al.  USC image understanding research: 1988–89 , 1989 .

[51]  R. Nevatia,et al.  Perceptual organization for computer vision , 1989 .

[52]  Ramakant Nevatia,et al.  Segmentation and description based on perceptual organization , 1989, Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[53]  Richard S. Weiss,et al.  Perceptual Grouping Of Curved Lines , 1989, Other Conferences.

[54]  Edward M. Riseman,et al.  Token-based extraction of straight lines , 1989, IEEE Trans. Syst. Man Cybern..

[55]  T. Fan.  Describing and Recognizing 3-D Objects Using Surface Properties , 1989, Springer Series in Perception Engineering.

[56]  W. Eric L. Grimson,et al.  The Combinatorics of Heuristic Search Termination for Object Recognition in Cluttered Environments , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[57]  W. Eric L. Grimson.  The Combinatorics of Heuristic Search Termination for Object Recognition in Cluttered Environments , 1991, IEEE Trans. Pattern Anal. Mach. Intell..