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

Abstract

The long-term goal of this project is to provide a flexible, accurate and extensible automated target recognition (ATR) system for use with a variety of imaging and non-imaging sensors. Such an ATR system, once it achieves a high level of performance, can relieve human operators from the tedious business of pouring over vast quantities of mostly mundane data, calling the operator in only when the computer assessment involves an unacceptable level of ambiguity. The ATR system will provide most leading edge algorithms for detection, segmentation, and classification while incorporating many novel algorithms that we are developing at Metron. To address one of the most critical challenges in ATR technology, the system will also provide powerful feature extraction routines designed for specific applications of current interest.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2006
Accession Number
ADA521885

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

Readers

  • Sensor Fusion and Tracking Systems.
  • Systems Analysis and Design

Technology Areas

  • AI & ML