An Iterative Hough Procedure for Three-Dimensional Object Recognition

Abstract

This paper is concerned with the problem of recognizing a rigid three-dimensional object in an image by matching a structural model of the object with information extracted from the image. Two important issues involved in developing such a recognition method are the choice of representation of the modeling primitives and abstractions, and the development of analysis operators that can detect instances of projections of these model entities in the image. A system is described which uses generalized Hough transforms to iteratively match a model consisting of straight edges against a set of line segments extracted from an image of that model taken from an unknown viewing position. The match is represented by a five-parameter transformation of the model onto the image. Straight line segments in the image are matched by finding the parameters of a viewing transformation of a three-dimensional model consisting of line segments. Assuming the scale of the object is known, there are three orientation and two translation parameters to be estimated. Initially a sparse, regular subset of parameters and transformations is evaluated for goodness-of-fit; then the procedure is repeated by successively subdividing the parameter space near current best estimates of peaks.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 1983
Accession Number
ADA157168

Entities

People

  • D. Harwood
  • L. S. Davis
  • T. M. Silberberg

Organizations

  • University of Maryland

Tags

Communities of Interest

  • Air Platforms

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Computer Science
  • Computer Vision
  • Coordinate Systems
  • Hash Tables
  • Image Registration
  • Images
  • Intervals
  • Iterations
  • Low Resolution
  • Object Recognition
  • Orientation (Direction)
  • Pattern Recognition
  • Recognition
  • Three Dimensional
  • Two Dimensional

Readers

  • Computational Modeling and Simulation
  • Computer Vision.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms
  • Space
  • Space - Space Objects