Aa. Abuelgasim et al., CLASSIFICATION OF ASAS MULTIANGLE AND MULTISPECTRAL MEASUREMENTS USING ARTIFICIAL NEURAL NETWORKS, Remote sensing of environment, 57(2), 1996, pp. 79-87
Because the anisotropy of the Earth's surface reflectance is strongly
influenced by vegetation cover, multidirectional remotely sensed data
can be highly effective in discriminating among Land cover classes. Th
is article explores the use of multiangle and multispectral data from
the Advanced Solid-State Array Spectroradiometer (ASAS) in land cover
mapping using artificial neural networks. A multilayer feed-forward ne
ural network is trained to identify five land cover classes in Voyageu
rs National Park, Minnesota. Multiangle data achieve 89% of accuracy w
hen applied to a single band (774-790 nm), 7-directional imagery and 8
8% accuracy when applied to multispectral nadir data. Analysis of erro
r using the confusion matrix indicates that the higher classification
accuracy is obtained primarily for three classes: deciduous forest, we
tlands, and water. The results suggest that 1) directional radiance me
asurements contain much useful information for discrimination among la
nd cover classes, 2) the incorporation of more than one spectral multi
angle band improves the overall classification accuracy compared to a
single multiangle band, and 3) neural networks can successfully learn
class discriminations from directional radiance data and/or multidomai
n data.