Automatic Target Classification Using Multiple Sidescan Sonar Images of Different Orientations

Abstract

In this report, the target classification performance of a multiple view side scan sonar is investigated. The classification statistics are estimated using model based automatic classifiers. The guidelines to the design of efficient classification algorithms are defined. The shadow is retained as the basic information for target classification. 'The input feature vector of the automatic classifier is the cross section(or height profile) of the target estimated from its shadow.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Sep 01, 1997
Accession Number
AD1120709

Entities

People

  • Antonio Guerrero
  • B. Stage
  • B. Zerr

Tags

Communities of Interest

  • Autonomy
  • Energy and Power Technologies
  • Ground and Sea Platforms
  • Materials and Manufacturing Processes
  • Sensors
  • Weapons Technologies

DTIC Thesaurus Topics

  • Artificial Intelligence Software
  • Automata Theory
  • Autonomous Underwater Vehicles
  • Collision Avoidance
  • Computer Languages
  • Computer Vision
  • Computers
  • Databases
  • Detection
  • Detectors
  • False Alarms
  • Image Processing
  • Information Science
  • Network Science
  • Neural Networks
  • Pattern Recognition
  • Self Organizing Systems
  • Supervised Machine Learning
  • Target Classification
  • Target Recognition
  • Two Dimensional
  • Warning Systems

Readers

  • Acoustical Oceanography.
  • Computer Vision.