Computer recognition of three-dimensional objects in a visual scene
Project MAC, Massachusetts Institute of Technology, 1968 - Computers - 287 pages
Methods are presented: (1) to partition or decompose a visual scene into the bodies forming it; (2) to position these bodies in three-dimensional space, by combining two scenes that make a stereoscopic pair; (3) to find the regions or zones of a visual scene that belong to its background; (4) to carry out the isolation of objects in (1) when the input has inaccuracies. Running computer programs implement the methods, and many examples illustrate their behavior. The input is a two-dimensional line-drawing of the scene, assumed to contain three-dimensional bodies possessing flat faces (polyhedra); some of them may be partially occluded. Suggestions are made for extending the work to curved objects. Some comparisons are made with human visual perception. The main conclusion is that it is possible to sseparate a picture or scene into the constituent objects exclusively in basis of monocular geometric properties (in basis of pure form); in fact, successful methods are shown. (Author).
What people are saying - Write a review
We haven't found any reviews in the usual places.
INTRODUCTION The q theslj u presented 10
Problems in analyzing a visual scene
13 other sections not shown
algorithm ambiguous analysis analyzed arrow assumption behavior bigger than 180 clean collinear concurrent lines cyclic permutation definition edges Example faces figure FORK ft ft genuine pair Guzman h-optical heuristic human identified illegal scenes inhibited Input Format Internal Format interpretation intervals join left scene LIMPIO line proposer LISP matching T's Memo metatheorem MINI missing mistakes MOMO monotonic function MULTI neighbor Nosabo nuclei o o o objects occluded body optical axes optical illusions parallel parallelepipeds partition Penrose Triangle picture possible preprocessor problem produce Project MAC property list reported right scene rules scene R3 segment SINGLEBODY solution strong links subroutines suggests suspicious regions Technology Square Theorem thesis three-dimensional space two-dimensional vertex vertices of type visual weak link