Discrete wavelet analysis was assessed for its utility in aiding discrimination of three pine species (Pinus spp.) using airborne hyperspectral data (AVIRIS). Two different sets of Haar wavelet features were compared to each other and to calibrated radiance, as follows: (1) all combinations of detail and final level approximation coefficients and (2) wavelet energy features rather than individual coefficients. We applied stepwise discriminant techniques to reduce data dimensionality, followed by discriminant techniques to determine separability. Leave-one-out cross validation was used to measure the classification accuracy. The most accurate (74.2%) classification used all combinations of detail and approximation coefficients, followed by the original radiance (66.7%) and wavelet energy features (55.1%). These results indicate that application of the discrete wavelet transform can improve species discrimination within the Pinus genus.
Bibliographical noteFunding Information:
We are grateful to Dr J.A.N. van Aardt, Rochester Institute of Technology, for sharing field data collected for another study. The comments from one of our anonymous reviewers were thorough and extremely helpful. This work was funded by the Graduate School at Virginia Tech through a PhD 2010 fellowship (A. Banskota, Geospatial and Environmental Analysis Program, College of Natural Resources and Environment).