Dual-Hierarchy Graph Method for Object Indexing and Recognition

Abstract

UMD built an innovative general purpose, inherently robust system for object representation and recognition. The system is model-based and knowledge-based, unlike most of the current methods which rely on generic statistical inference. This knowledge is intrinsic to the objects themselves, based on geometric and semantic relations among objects. Therefor the system is insensitive to external interferences such as viewpoint changes (pose, scale etc.), illumination changes, occlusion, shadows, sensor noise etc. It also handles variability in the object itself, e.g. articulation or camouflage. All available models are represented in one graph consisting of two independent but interlocking hierarchies. One of these intrinsic hierarchies is a "Level of Abstraction (LOA) hierarchy, going up from specific to generic objects. The other is based on parts of the object.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 2014
Accession Number
ADA607067

Entities

People

  • Fan Yang
  • Isaac Weiss
  • Larry Davis

Organizations

  • University of Maryland

Tags

Communities of Interest

  • Autonomy
  • Energy and Power Technologies
  • Human Systems
  • Materials and Manufacturing Processes
  • Weapons Technologies

DTIC Thesaurus Topics

  • Air Force
  • Air Force Research Laboratories
  • Bayesian Networks
  • Computer Vision
  • Computers
  • Detection
  • Detectors
  • Identification
  • Image Processing
  • Information Science
  • Machine Learning
  • Object Recognition
  • Recognition
  • Statistical Inference
  • Supervised Machine Learning
  • Three Dimensional
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Computer Vision.

Technology Areas

  • AI & ML