A 3-D Object Recognition System Using Aspect Graphs

Abstract

This report describes a prototype 3-D object recognition system composed of three major sections; 1) an object representation module, 2) a feature extraction and matching module, and 3) a recognition control strategy module. The object representation module uses an implementation of a newly developed algorithm for the construction of perspective projection aspect graphs of convex polyhedra. The feature extraction and matching module implements a new method of using Fourier Descriptors to characterize the complete 2-D projection of an object. The recognition control strategy module uses the aspect graph object representation to control the application of a constrained optimization algorithm. The system is implemented in C on a SUN workstation, and some simple recognition experiments have been carried out to demonstrate the validity of the overall concept. The limitations of the system suggest several important avenues for future research. Keywords: Three dimensional, Two dimensional.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 1988
Accession Number
ADA198472

Entities

People

  • David Eggert
  • John Stewman
  • Kevin Bowyer
  • Louise Stark

Organizations

  • University of South Florida

Tags

Communities of Interest

  • Air Platforms
  • Autonomy
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Artificial Intelligence
  • Classification
  • Computer Science
  • Computer Vision
  • Computers
  • Engineering
  • Feature Extraction
  • Identification
  • Object Recognition
  • Optimization
  • Pattern Recognition
  • Recognition
  • Three Dimensional
  • Two Dimensional
  • Universities

Readers

  • Computer Science.
  • Computer Vision.

Technology Areas

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