Name
Title | ||
|---|---|---|
ART neural networks for remote sensing: vegetation classification from Landsat TM and terrain data |
Abstract | ||
|---|---|---|
A new methodology for automatic mapping from Landsat thematic mapper (TM) and terrain data, based on the fuzzy ARTMAP neural network, is developed. System capabilities are tested on a challenging remote sensing classification problem, using spectral and terrain features for vegetation classification in the Cleveland National Forest. After training at the pixel level, system performance is tested at the stand level, using sites not seen during training. Results are compared to those of maximum likelihood classifiers, as well as back propagation neural networks and K nearest neighbor algorithms. ARTMAP dynamics are fast, stable, and scalable, overcoming common limitations of back propagation. Best results are obtained using a hybrid system based on a convex combination of fuzzy ARTMAP and maximum likelihood predictions. A prototype remote sensing example introduces each aspect of data processing and fuzzy ARTMAP classification. The example shows how the network automatically constructs a minimal number of recognition categories to meet accuracy criteria. A voting strategy improves prediction and assigns confidence estimates by training the system several times on different orderings of an input set |
Year | DOI | Venue |
|---|---|---|
1997 | 10.1109/36.563271 | Geoscience and Remote Sensing, IEEE Transactions |
Keywords | Field | DocType |
terrain mapping,geophysical techniques,method,remote sensing,geophysics computing,fuzzy artmap,land surface,signal processing,cleveland national forest,forestry,woodland,maximum likelihood estimation,maximum likelihood prediction,art neural nets,training,optical imaging,feedforward neural net,multidimensional signal processing,backpropagation,back propagation,feedforward neural nets,multispectral remote sensing,voting strategy,image classification,art neural network,automatic mapping,usa,geophysical signal processing,neural net,ir imaging,landsat tm,vegetation mapping,optical information processing,thematic mapper,k nearest neighbor algorithm,forest,maximum likelihood classifier,fuzzy neural nets,geophysical measurement technique,neural networks,system testing,maximum likelihood,system performance,data processing,convex combination,hybrid system,satellites,neural network,k nearest neighbor | Data mining,Thematic Mapper,Terrain,Fuzzy logic,Remote sensing,Multispectral pattern recognition,Vegetation classification,Artificial neural network,Contextual image classification,Backpropagation,Mathematics | Journal |
Volume | Issue | ISSN |
35 | 2 | 0196-2892 |
ISBN | Citations | PageRank |
0-7803-3068-4 | 35 | 4.34 |
References | Authors | |
13 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Gail A. Carpenter | 1 | 2909 | 760.83 |
| Gjaja, M.N. | 2 | 35 | 4.34 |
| Sucharita Gopal | 3 | 119 | 24.02 |
| C. E. Woodcock | 4 | 166 | 41.71 |