Visual recognition using concurrent and layered parameter networks

A vision system to recognize 3-D objects is presented. A novel notion of generalized feature makes it possible to develop a homogeneous architecture to support recognition from simple partial features to complex feature assemblies and 3-D objects. Layered concurrent parameter transforms vote for feature hypotheses on the basis of image data and previously reconstructed features. Recognition networks, motivated by connectionist systems, collect votes, fuse evidence from various sources and ensure global consistency. In addition, they provide an integrated solution to the segmentation problem. The highly modular design allows fundamentally different types of features to interact in a coherent way, utilizing redundancies for more robust recognition. Within this paradigm, a system extracts planar patches, patches of quadrics of revolution, and the intersection curves of these surfaces (lines and conic sections in three-space) from a depth map. Reconstructed features index into a model database to form consistent object hypotheses. Experimental results detailing the recognition behavior or real depth maps are included.<<ETX>>

[1]  M. Docarmo.  Differential geometry of curves and surfaces , 1976 .

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

[3]  Herbert Freeman,et al.  Reconstruction of Curved-Surface Bodies from a Set of Imperfect Projections , 1977, IJCAI.

[4]  Thomas O. Binford,et al.  The Interpretation of Three-Dimensional Structure from Image Curves , 1981, IJCAI.

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

[6]  Thomas O. Binford,et al.  Survey of Model-Based Image Analysis Systems , 1982 .

[7]  K. S. Fu,et al.  Robot Vision For Machine Part Recognition , 1983, Optics & Photonics.

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

[9]  W. Grimson,et al.  Model-Based Recognition and Localization from Sparse Range or Tactile Data , 1984 .

[10]  Ramesh C. Jain,et al.  Three-dimensional object recognition , 1985, CSUR.

[11]  Daniel Sabbah.  Computing with connections in visual recognition of origami objects , 1985 .

[12]  Ruud M. Bolle,et al.  Extraction Of Surface Parameters From Depth Maps Viewing Planes And Quadrics Of Revolution , 1987, Other Conferences.

[13]  Gil J. Ettinger,et al.  Large hierarchical object recognition using libraries of parameterized model sub-parts , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[14]  Andrea Califano,et al.  Feature Recognition Using Correlated Information Contained in Multiple Neighborboods , 1988, AAAI.

[15]  Ruud M. Bolle,et al.  Generalized neighborhoods: a new approach to complex parameter feature extraction , 1989, Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition.