Object Recognition by Alignment Using Invariant Projections of Planar Surfaces

Abstract

In order to recognize an object in an image, we must determine the best transformation from object model to the image. In this paper, we show that for features from coplanar surfaces which undergo linear transformations in space, there exist projections invariant to the surface motions up to rotations in the image field. To use this property, we propose a new alignment approach to object recognition based on centroid alignment of corresponding feature groups. This method uses only a single pair of 2D model and data. Experimental results show the robustness of the proposed method against perturbations of feature positions. Object recognition, Invariant properties, Recognition by alignment.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1994
Accession Number
ADA279841

Entities

People

  • Eric Grimson
  • Kenji Nagao

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Air Platforms

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Classification
  • Clustering
  • Computer Vision
  • Coordinate Systems
  • Covariance
  • Eigenvalues
  • Errors
  • Feature Extraction
  • Massachusetts
  • Military Research
  • Numbers
  • Object Recognition
  • Perturbations
  • Probability
  • Recognition

Fields of Study

  • Computer science

Readers

  • Computer Vision.

Technology Areas

  • Space
  • Space - Space Objects
  • Space - Spacecraft Maneuvers