Seafloor Characterization Using Texture

Abstract

Texture analysis is performed on multibeam sonar imagery. A set of fourteen texture features is computed using co-occurrence matrices to form the feature space. The dimensionality of the feature space is reduced by extracting the principal components from the original feature space. Classification of the image is performed on the principal components using K-Means algorithm. Results indicate that seafloor bottom types can be characterized by analyzing the texture of the bathymetric sonar images. Hydrography, Bathymetry, Optical properties, Remote sensing, Reverberation.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1993
Accession Number
ADA275399

Entities

People

  • Andrew B. Martinez
  • Brian S. Bourgeois
  • Herb Barad
  • Suresh Subramaniam

Organizations

  • United States Naval Research Laboratory

Tags

Communities of Interest

  • Air Platforms
  • Energy and Power Technologies
  • Materials and Manufacturing Processes
  • Space

DTIC Thesaurus Topics

  • Algorithms
  • Bathymetry
  • Classification
  • Clustering
  • Data Sets
  • Eigenvalues
  • Electrical Engineering
  • Feature Extraction
  • High Resolution
  • Information Science
  • Machine Learning
  • Pattern Recognition
  • Recognition
  • Remote Sensing
  • Sonar
  • Sonar Images
  • Statistics

Readers

  • Acoustical Oceanography.
  • Computer Vision.

Technology Areas

  • Space