Share Email Print
cover

Proceedings Paper

Integrated land-cover mapping from satellite imagery using artificial neural networks
Author(s): Graeme G. Wilkinson; Ioannis Kanellopoulos; Z. K. Liu; S. Folving
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The automatic mapping of land cover from satellite imagery requires optimal classification and spatial generalization procedures. Here we describe the use of functional ink neural networks, based on a flat perceptron net with an augmented feature vector, to generate high accuracy classification products. These can then be trained more rapidly than multi-layer perceptrons. The network output is then used to fix land cover class area statistics which control a low-level generalization procedure based on a combined iterative majority filtering and reduced class growing procedure.

Paper Details

Date Published: 31 August 1993
PDF: 8 pages
Proc. SPIE 1941, Ground Sensing, (31 August 1993); doi: 10.1117/12.154705
Show Author Affiliations
Graeme G. Wilkinson, Institute for Remote Sensing Applications/Joint Research Ctr. (Italy)
Ioannis Kanellopoulos, Institute for Remote Sensing Applications/Joint Research Ctr. (Italy)
Z. K. Liu, Univ. of Science and Technology (China) (Italy)
S. Folving, Institute for Remote Sensing Applications/Joint Research Ctr. (Italy)


Published in SPIE Proceedings Vol. 1941:
Ground Sensing
Hatem N. Nasr, Editor(s)

© SPIE. Terms of Use
Back to Top