Automated Classification of Basic-Level Terrain Features in Digital Elevation Models

Abstract

This study addresses a two-class problem in automatic terrain classification. the basic-level terrain feature selected for initial delineation is a mount - an aggregation of elevated features including hills, mountains, and ranges. All remaining areas are classified collectively as non-mount. A method was developed to partition digital elevation models (DEMs) into mount and non- mount areas automatically. Then, the developed method is compared to those results obtained by a manual classification of synthetic stereo images produced from the same digital elevation data. The results of this work suggest that it may be possible to replicate the manual identification of mounts in certain physiographic regions. However, the general utility of the mount/nonmount classification approach appears to be limited by the nature of the regional terrain and by the quality of available digital data. Terrain Analysis, Automated Terrain Classification, Terrain Reasoning, Geomorphology, Geomorphometry, Digital Elevation Data

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 1992
Accession Number
ADA256932

Entities

People

  • Linda H. Graff

Organizations

  • Army Geospatial Center

Tags

Communities of Interest

  • Air Platforms
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Cartography
  • Digital Data
  • Drainage Basins
  • Engineering
  • Geographic Information Systems
  • Geographic Regions
  • Geography
  • Geological Surveys
  • Identification
  • Image Processing
  • Images
  • Landforms
  • Physical Geography
  • Remote Sensing
  • Topographic Maps
  • Topography
  • United States

Readers

  • Computer Vision.