Learning Grouping Strategies for 2D and 3D Object Recognition

Abstract

The Schema Learning System (SLS) automatically assembles task specific object recognition programs from existing IU algorithms. SLS brings together two emerging technologies; image understanding and machine learning, to automatically build customized procedures for recognizing and extracting specific object classes in constrained contexts. This paper describes the representations and algorithms underlying SLS, and presents an example of SLS learning to recognize rooftops in aerial images of Ft. Hood. This task is the first of several tasks from the ARPA/ORD sponsored RADIUS project that SLS is intended to learn without human interaction. In later experiments, SLS will be tasked to automatically construct 3D models of buildings and other objects of interest from overlapping aerial images.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1996
Accession Number
ADA332936

Entities

People

  • Bruce A. Draper

Organizations

  • University of Massachusetts Amherst

Tags

Communities of Interest

  • Air Platforms
  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Aerial Photographs
  • Algorithms
  • Artificial Intelligence
  • Automata Theory
  • Cameras
  • Computer Programming
  • Computer Science
  • Computer Vision
  • Computers
  • Control Systems Engineering
  • Detectors
  • Images
  • Intelligent Systems
  • Neural Networks
  • Object Recognition
  • Recognition
  • Reinforcement Learning

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Solar Photovoltaics and Thermoelectric Devices.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks