Using Neural Networks to Correlate Satellite Imagery and Ground-Truth Data

Abstract

Current approaches to evaluating the condition of natural resources on Army training and testing lands are statistically based and attempt to generate rational mathematical formulae that characterize the relationship between satellite imagery and ground-truth data. Even in the hands of a well trained image processing expert, the application of standard image processing tools can yield varying results. Army land managers need an alternate approach for correlating satellite imagery to ground-truth measurements. This approach can be found in the application of neural networks. This report presents the research results of using neural networks as a computational tool to correlate ground-truth data with satellite imagery tor Hohenfels, Germany, and to turn the imagery into maps of the installation. Satellite imagery, Neural networks, Land Condition Trend Analysis (LCTA), Geographic Resource Analysis Support System (GRASS)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 1994
Accession Number
ADA285486

Entities

People

  • James D. Westervelt
  • Xiping Wu

Organizations

  • Construction Engineering Research Laboratory

Tags

Communities of Interest

  • Space

DTIC Thesaurus Topics

  • Algorithms
  • Army Training
  • Artificial Intelligence Software
  • Civil Engineering
  • Cognitive Science
  • Computing System Architectures
  • Correlators
  • Economic Forecasting
  • Engineering
  • Information Systems
  • Measurement
  • Natural Resources
  • Network Architecture
  • Neural Networks
  • Remote Sensing
  • Satellite Imaging
  • Self Organizing Systems

Readers

  • Computer Vision.
  • Neural Network Machine Learning.
  • Wetland-Land-Environmental Management.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks
  • Space
  • Space - Satellites