| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 6349048 | International Journal of Applied Earth Observation and Geoinformation | 2013 | 9 Pages |
Abstract
⺠We mapped spatially heterogonous graminoid communities using high resolution aerial imagery. ⺠Appropriate texture window size is very important and can be estimated using semivariograms. ⺠NDVI, first and second order texture features significantly increased the detection accuracy. ⺠Support Vector Machine classifier outperformed the Maximum likelihood classifier.
Related Topics
Physical Sciences and Engineering
Earth and Planetary Sciences
Computers in Earth Sciences
Authors
Zoltan Szantoi, Francisco Escobedo, Amr Abd-Elrahman, Scot Smith, Leonard Pearlstine,