Segmentation of Satellite Imagery Using Hierarchical Thresholding and Neural Networks

Abstract

A significant task in the automated interpretation of cloud features on satellite imagery is the segmentation of the image into separate cloud features to be identified. A new technique, Hierarchical Threshold Segmentation (HTS) is presented. In HTS, region boundaries are defined over a range of grayshade thresholds. The hierarchy of the spatial relationships between colocated regions from different thresholds is represented in tree form. This tree is pruned, using a neural network, such that the regions of appropriate sizes and shapes are isolated. These various regions from the pruned trees are then collected to form the final segmentation of the entire image.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 1991
Accession Number
ADA247915

Entities

People

  • James E. Peak

Tags

Communities of Interest

  • Space

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Artificial Satellites
  • Atmospheric Sciences
  • Boundaries
  • Change Detection
  • Classification
  • Computer Programs
  • Computer Science
  • Computer Vision
  • Data Sets
  • Detection
  • Hierarchies
  • Image Segmentation
  • Military Research
  • Neural Networks
  • Pattern Recognition
  • Satellite Imaging

Fields of Study

  • Computer science

Readers

  • Atmospheric Science/Meteorology
  • Computer Programming and Software Development.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • Space