Unsupervised Spatial Feature and Change Detection in RS Imaging

Abstract

Main activities started: (1) a clearer modular rebuild of the basic methodology implemented by the system, involving a clear separation of the main methodological elements; (2) splitting off the new pixel by pixel classified image inspection mode in a non-volatile module, for separate operation; (3) selecting (sub)classes and regions in a classified image for further analysis; (4) experimentally start with spectral de-mixing, within (sub)classes, using RBF neural network technology; (5) almost completed a users friendly, menu based, users interface; and (6) migrated the system from Java JDK 1.16 to Java JDK 1.2.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 01, 1999
Accession Number
ADA364815

Entities

People

  • R. J. Mokken

Organizations

  • University of Amsterdam

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Abstracts
  • Accuracy
  • Blending
  • Change Detection
  • Classification
  • Contracts
  • Detection
  • Discriminant Analysis
  • European Union
  • Information Science
  • Inspection
  • Network Science
  • Neural Networks
  • Remote Sensing
  • Snow Cover
  • Splitting
  • Unsupervised Machine Learning

Fields of Study

  • Computer science
  • Physics

Readers

  • Database Systems and Applications
  • Image Processing and Computer Vision.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML