Image Enhancement and Automated Target Recognition Techniques for Underwater Electro-Optic Imagery

Abstract

The main objective of this project is to develop a complete, flexible, and extensible modular automated target recognition (MATR) system for computer aided detection and classification (CAD/CAC) of target objects from within cluttered and possibly noisy image data. The MATR system framework is designed to be applicable to a wide range of situations, each with its own challenges, and so is organized in such a way that the constituent algorithms are interchangeable and can be selected based on their individual suitability to the particular task within the specific application. The ATR system designer can select combinations of algorithms, many of which are being developed at Metron, to produce a variety of systems, each tailored to specific needs. While the development of the system is still ongoing, results for mine countermeasures (MCM) applications using electro-optical (EO) image data have been encouraging. A brief description of the system framework, some of the novel algorithms, and preliminary test results are provided in this interim report.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 30, 2007
Accession Number
ADA546856

Entities

People

  • Cetin Savkli
  • Joseph Shirron
  • Thomas Giddings

Tags

Communities of Interest

  • Materials and Manufacturing Processes
  • Sensors

DTIC Thesaurus Topics

  • Automated Target Recognition
  • Classification
  • Computer Vision
  • Data Sets
  • Detection
  • Detectors
  • Feature Extraction
  • Identification
  • Image Processing
  • Machine Learning
  • Neural Networks
  • Noise
  • Recognition
  • Target Recognition

Fields of Study

  • Engineering

Readers

  • Sensor Fusion and Tracking Systems.
  • Software Engineering
  • Software Engineering.