Hierarchical Multisensor Image Understanding.

Abstract

This report describes the research results on Honeywell's Hierarchical Multisensor Image Understanding program. Honeywell is developing a unified framework for the different hierarchical levels of image processing such as segmentation, detection, classification, and identification of outdoor scenes and across different sensor modalities such as millimeter wave, infrared, and visible. Current activities on the project are reviewed under the following headings: (1) A Survey of Multisource Information Fusion Systems; (2) The Role of Structure in Human and Machine Perception; (3) A Knowledge Based Image Segmentation System; (4) The Use of Optical Flow as a Depth Cue in Scene Analysis and (5) Belief Maintenance for A Fuzzy Reasoning System. Keywords include: Image processing; Image understanding; Artificial intelligence; and Scene analysis.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 1985
Accession Number
ADA160324

Entities

People

  • J. Budenske
  • M. Bazakos
  • R. K. Aggarwal
  • S. Mader
  • Yong Ha Kim

Organizations

  • Honeywell International, Inc.

Tags

Communities of Interest

  • Materials and Manufacturing Processes
  • Sensors

DTIC Thesaurus Topics

  • Air Force
  • Artificial Intelligence
  • Artificial Intelligence Software
  • Automata Theory
  • Bayes Theorem
  • Cognitive Science
  • Computational Science
  • Computer Languages
  • Computer Vision
  • Computers
  • Detection
  • Fuzzy Logic
  • Geometric Forms
  • Image Processing
  • Machine Perception
  • Three Dimensional
  • Two Dimensional

Readers

  • Geospatial Intelligence and Artificial Intelligence Analytics
  • Image Processing and Computer Vision.
  • Sensor Fusion and Tracking Systems.

Technology Areas

  • 5G
  • AI & ML