Accession Number : ADA160602


Title :   Computing Visible-Surface Representations,


Corporate Author : MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB


Personal Author(s) : Terzopoulos,D


Full Text : http://www.dtic.mil/dtic/tr/fulltext/u2/a160602.pdf


Report Date : Mar 1985


Pagination or Media Count : 64


Abstract : The computational framework offered in this paper addresses, in a unified way, certain visual information processing tasks involved in the representation of visible surfaces. Particular emphasis is placed on utilizing highly parallel, cooperative processing to integrate surface shape information over multiple visual sources, to fuse it across a multiplicity of spatial resolutions, and to maintain the global consistency of the resulting distributed shape representations. The issues are first investigated in terms of a surface reconstruction model rooted in mathematical physics. This formal analysis is augmented by an empirical study of the resulting algorithms, which feature multiresolution iterative processing within hierarchical surface shape representations. The approach is guided by current knowledge of how humans perceive visible surfaces, while applications in machine vision provide a testbed for the algorithms. Keywords: vision; finite elemeent analysis; discontinuities; variational principles; splines.


Descriptors :   *COMPUTATIONS , *SURFACES , *VISUAL PERCEPTION , ALGORITHMS , HUMANS , FINITE ELEMENT ANALYSIS , SHAPE , PARALLEL PROCESSING , CONSISTENCY , PHYSICS , MATHEMATICS , VISION , DISCONTINUITIES , INFORMATION PROCESSING , VARIATIONAL PRINCIPLES , VISUAL SIGNALS , SPLINES


Subject Categories : Theoretical Mathematics
      Cybernetics


Distribution Statement : APPROVED FOR PUBLIC RELEASE