Visual Learning from Multiple Views.

Abstract

An algorithm is presented in which a computer is visually shown a sequence of views of a solid planar object as the object is rotated in space. The computer automatically forms a three-dimensional description of the object. The description consists of a deterministic description of the object's surfaces and how they are interconnected to form the object, along with a measure of each surface's shape which is invariant to 3-dimensional rotation. From this self-learned model of the object, the object can be later recognized from any viewing angle. The basis of the algorithm is the ability of the program to determine in a specific visual view: What do I see now, that I have seen before. This is accomplished by generating two sets of mappings of one object description to another object description.

Document Details

Document Type
Technical Report
Publication Date
May 06, 1974
Accession Number
ADA006420

Entities

People

  • Clarence L. Coates
  • Stephen A. Underwood

Organizations

  • University of Texas at Austin

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Computers
  • Geometry
  • Learning
  • Mathematics
  • Physical Properties
  • Rotation
  • Sequences
  • Sizes (Dimensions)
  • Three Dimensional

Fields of Study

  • Computer science
  • Physics

Readers

  • Database Systems and Applications
  • Graph Algorithms and Convex Optimization.

Technology Areas

  • Space
  • Space - Space Objects