Object Representation Using Appearance-Based Parts and Relations

Abstract

The recognition of general three-dimensional objects in cluttered scenes remains a challenging problem. In particular, the design of a good representation that is suitable for modeling large numbers of generic objects, and is also robust to occlusion, has been a stumbling block to achieving success. In this paper, we propose a representation using appearance-based parts and relations to overcome these problems. Appearance-based parts and relations are defined in terms of closed regions and unions of these regions, respectively. The regions are segmented using the MDL principle; their appearance is obtained from collections of images and compactly represented by parametric manifolds in the two eigenspaces spanned by the parts and the relations. Qualitative and quantitative experiments illustrating the potential of the representation for successful object recognition in the presence of clutter and occlusion are presented.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1999
Accession Number
ADA458670

Entities

People

  • Chien-yuan Huang
  • Octavia Camps
  • Tapas Kanungo

Organizations

  • Pennsylvania State University

Tags

Communities of Interest

  • C4I

DTIC Thesaurus Topics

  • Abstracts
  • Computer Vision
  • False Alarms
  • Formal Languages
  • Image Processing
  • Image Recognition
  • Information Operations
  • Language
  • Object Recognition
  • Recognition
  • Three Dimensional
  • Universities
  • Vascular System Injuries
  • Warning Systems

Readers

  • Computer Vision.
  • Graph Algorithms and Convex Optimization.