Progress on Target and Terrain Recognition Research at Colorado State University.

Abstract

A target recognition capability is described which performs: color detection, target type and pose hypothesis generation, and target verification by 3D alignment of target models to range and optical imagery. The term coregistration' is introduced to describe target, range and optical sensor alignment. The following key verification components are described and demonstrated: target-model feature extraction, model-driven edge detection, range, optical and target coregistration, and coregistration space matching. As a precursor to future incorporation of terrain data, the ability to match terrain features to imagery from the UGV Demo C test site is demonstrated.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 16, 1995
Accession Number
ADA308667

Entities

People

  • Bruce A. Draper
  • J. R. Beveridge
  • Kris Siejko

Organizations

  • Colorado State University

Tags

Communities of Interest

  • Autonomy
  • Energy and Power Technologies
  • Materials and Manufacturing Processes
  • Sensors

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Change Detection
  • Computer Science
  • Computer Vision
  • Coordinate Systems
  • Detection
  • Detectors
  • Feature Extraction
  • Geometric Forms
  • Geometry
  • Optical Detectors
  • Optical Images
  • Pattern Recognition
  • Sensor Fusion
  • Target Recognition
  • Three Dimensional
  • Unmanned Ground Vehicles

Fields of Study

  • Physics

Readers

  • Computer Vision.

Technology Areas

  • AI & ML
  • Space
  • Space - Space Objects