Terrain Categorization Using a Background Spectral Library

Abstract

We describe development of a background spectral library for northeastern Virginia, USA, based on hyperspectral images and an extensive land cover database. The library consists of mean spectra and standard deviations measured in 14 areas of uniform land cover. Terrain categorizaton products include classification maps and fractional abundance maps determined by linear texture analysis. There is excellent qualitative agreement between the linear unmixing results and the known land covers.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 11, 2002
Accession Number
ADA439184

Entities

People

  • John Cipar
  • Peggy Grigsby
  • Ronald Lockwood
  • Thomas Cooley

Organizations

  • Air Force Research Laboratory

Tags

Communities of Interest

  • Air Platforms

DTIC Thesaurus Topics

  • Agreements
  • Air Force
  • Air Force Research Laboratories
  • Air Intelligence
  • Algorithms
  • Altitude
  • Classification
  • Databases
  • Hyperspectral Imagery
  • Information Science
  • Low Altitude
  • Military Research
  • Signal Processing
  • Spectra
  • Spectroscopy
  • Standards
  • Virginia

Readers

  • Computer Vision.
  • Image Processing and Computer Vision.
  • Technical Research and Report Writing.