TERRAIN CLASSIFICATION USING COLOR IMAGERY

Algorithms have been developed to permit classification of metal, soil, pavement, cultivated fields, and vegetation elements form standard color film imagery. The analyses are significant because the algorithms are independent of sensor and atmospheric conditions. The algorithms thus remove the necessity for a new training data set for each data collection mission. Terrain classification from the algorithms was accomplished to 97 percent accuracy using imagery at scales as small as 1:100,000 taken from altitudes in excess of 50,000 feet.

  • Availability:
  • Corporate Authors:

    American Society of Photogrammetry

    105 North Virginia Avenue
    Falls Church, VA  USA  22046
  • Authors:
    • Piech, K R
    • Gaucher, D W
    • Schott, J R
    • Smith, P G
  • Publication Date: 1977-4

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 00164067
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Nov 9 1977 12:00AM