Demonstrating the Automated Change Detection and Classification (ACDC) System during the Gulf of Mexico FY05 Naval Exercise (GOMEX-05)

Abstract

This report presents test results from a demonstration of the Automated Change Detection and Classification (ACDC) system, developed by the Naval Research Laboratory (NRL) in support of sidescan sonar analysts at the Naval Oceanographic Office. NRL compared the computer-aided change detection capabilities of ACDC with traditional, manual methods of change detection during a naval mine warfare exercise in 2004. Two versions of ACDC (ACDC "Lite" and "Medium") were tested to determine how well the system could aid analysts in detecting changes between newly collected sidescan sonar imagery and historical imagery. ACDC Lite enabled analysts to perform change detection significantly faster than manual methods (3.36 min. vs 2 hr) with identical results. ACDC Medium improved analysts' performance by matching one additional contact during change detection, in as little as 12.6 minutes. Follow-on work is suggested for further improving ACDC performance in support of mine countermeasures.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 01, 2005
Accession Number
ADA432930

Entities

Organizations

  • United States Naval Research Laboratory

Tags

Communities of Interest

  • Human Systems
  • Materials and Manufacturing Processes
  • Sensors

DTIC Thesaurus Topics

  • Algorithms
  • Application Software
  • Change Detection
  • Classification
  • Computers
  • Detection
  • Geographic Regions
  • Graphical User Interface
  • Html
  • Markup Languages
  • Military Research
  • Naval Operations
  • Naval Warfare
  • Operating Systems
  • Parallel Computing
  • Parallel Processing
  • Warfare

Readers

  • Coastal Oceanography
  • Military Logistics and Supply Chain Management
  • Sensor Fusion and Tracking Systems.