Efficient Generation of Synthetic Terrain Imagery for Automatic Target Recognition

Abstract

We have developed an integrated framework for the efficient synthesis of realistic images of three dimensional terrain with man-made objects and natural clutter. We have shown how many phenomenological aspects of the placement of road networks, tree clusters, populated areas, buildings, etc., can be captured in a computationally-efficient pseudorandom image-generation framework. We generate the underlying terrain with a fast Fourier based procedure. This procedure is seeded with a pseudorandom sequence, so a small number of parameters can characterize a distinctive class of terrain. Within each class, arbitrarily many scenes can be synthesized. We have used procedural definitions for objects; targets or clutter are represented by different models depending on range. For example, at a great distance trees may look like simple cones. But, as the viewpoint nears a tree, finer details will become visible. Procedural definitions also eliminate the need to explicitly store boundary representations for every object placed in the scene. A single procedural definition for an object, such as a tree, can be used at render time by a Z-buffer algorithm to create as many instances as are necessary, with each instance being unique since it uses a unique pseudorandom seed.... Automatic target recognition, Image synthesis, Computer modeling, Z-buffer.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 23, 1992
Accession Number
ADA260705

Entities

People

  • A. C. Kak
  • Huicong Kang
  • L. L. Grewe
  • R. L. Cromwell
  • S. G. Blask

Organizations

  • Purdue University

Tags

Communities of Interest

  • Energy and Power Technologies
  • Human Systems

DTIC Thesaurus Topics

  • Bodies Of Water
  • Boundaries
  • Classification
  • Computer Graphics
  • Computers
  • Frequency
  • Frequency Domain
  • Graphics
  • Military Research
  • New York
  • Ocean Waves
  • Oceans
  • Recognition
  • Target Recognition
  • Terrain
  • Three Dimensional
  • United States

Fields of Study

  • Computer science

Readers

  • Computer Vision.