Geometric Methods for ATR: Shape Analysis, Object/Image Metrics, Shape Reconstruction, and Shape Statistics

Abstract

This report summarizes the work done over the approximately three years of this project. Our general focus has been on the employment of advanced mathematical techniques from algebraic and differential geometry to solve various problems associated with object recognition. The principal framework has been the theory of object/image equations and object/image metrics which we have developed and exploited in multiple contexts and for multiple sensor types. This included not only issues of recognition and target identification, but problems related to 3D reconstruction, recovery of shape from motion, feature extraction, and statistical shape analysis.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 15, 2011
Accession Number
ADA563681

Entities

People

  • Amanda Johnson
  • Peter F. Stiller

Organizations

  • Texas A&M University

Tags

Communities of Interest

  • Air Platforms
  • Biomedical
  • Human Systems
  • Sensors

DTIC Thesaurus Topics

  • Air Force Research Laboratories
  • Algebraic Geometry
  • Algorithms
  • Computer Science
  • Computer Vision
  • Coordinate Systems
  • Detectors
  • Differential Geometry
  • Equations
  • Geometry
  • Identification
  • Mathematics
  • Object Recognition
  • Pattern Recognition
  • Recognition
  • Target Recognition
  • Three Dimensional

Fields of Study

  • Computer science

Readers

  • Calculus or Mathematical Analysis
  • Computer Vision.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms