Classification Accuracy
——a—— MANN 18D
LÍ — MANN 19D
Ue MANN 21D
Twenty-four land cover categories
Figure 3. Comparison of classification accuracy of three data
combination MANNS on twenty-four land cover categories.
categories could be
the computation in
related land cover
distinguished. However,
MANN is intensive.
ACKNOWLEDGMENT
The research upon which this paper is
based was supported in part by the Storrs
Agricultural Experiment Station of the
University of Connecticut under the project
Improved land cover mapping through
innovative computer-assisted processing of
satellite digital remote sensing data--Phase II.
One date of the Landsat TM data was provided
through the ASPRS KOSAT Award for
Application of Digital Landsat TM Data.
REFERENCES
Benediktsson, J., P. Swain, and O. Ersoy, 1990.
Neural Network Approaches Versus Statistical
Methods in Classification of Multisource Remote
Sensing Data. IEEE Trans. on Geoscience and
Remote Sensing, 28:540-552.
Bischof, H., W. Schneider, and A. Pi, 1992.
Multispectral Classification of Landsat-Images
Using Neural Networks. IEEE Trans. on
Geoscience and Remote Sensing, 30: 482-490.
Chen, K.S., Y.C. Tzeng, CF. Chen, and W.L.
Kao, 1995. Land-Cover Classification of
Multispectral Imagery Using a Dynamic Learning
Neural Network. Photogrammetric Engineering
and Remote Sensing, 61(4):403-408
Civco, D.L., 1993. Artificial neural networks for
land-cover classification and mapping,
International Journal | of | Geographical
Information Systems, 7(2):173-186.
Civco, D.L., and Y. Wang, 1994. Multispectral,
multitemporal, ^ multisource ^ spatial ^ data
98
classificati
Proceedin
Conventio
pp.123-13
Foody, G.
1995. Cla:
an Artifici
Training I
Engineeri
61(4):391.
Hara, Y,,
and J.A.
Networks
Transactio
Sensing, 3
Hecht-Nie
Backprop:
Internatioi
pp.1-593-€
Heermann.
Classificati
Data Us
Network.
Remote Se
Hepner, C
Bryant,
Classificati
Comparisc
Classificati
and Remoi
Hrycej: T..
Networks:
network cl
Jacobs, R
G.E. Hint:
experts, Ni
Liu, Z.K..
Remote ly
Neural N
Remote Se