Conditional Estimation of Vector Patterns in Remote Sensing and GIS

Abstract

Oriented patterns, such as those produced by vector propagation, raster pattern accretion, or deformation of geometric features, are common in image processing and GIS. Our approach to classifying such patterns is to decompose them into two parts: (1) the flow field, describing the direction of anisotropy; and (2) the residual pattern obtained by describing the image in a coordinate system built from the flow field. We develop a method for the local estimation of anisotropy and a method for combining the estimates to construct a flow coordinate system.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 01, 1998
Accession Number
ADA354138

Entities

People

  • J. M. F. Masuch

Organizations

  • University of Amsterdam

Tags

Communities of Interest

  • Space

DTIC Thesaurus Topics

  • Anisotropy
  • Anomaly Detection
  • Artificial Intelligence
  • Buildings And Structures
  • Change Detection
  • Computations
  • Contracts
  • Coordinate Systems
  • Detection
  • Flow Fields
  • Frequency
  • Image Processing
  • Materials
  • Orientation (Direction)
  • Pattern Recognition
  • Power Spectra
  • Remote Sensing

Fields of Study

  • Computer science

Readers

  • Acoustical Oceanography.
  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Theoretical Analysis.