On the relative predictive value of the new spectral bands in the WorldWiew-2 sensor
暂无分享,去创建一个
We apply a comparative data mining framework to the multispectral classification of WorldView-2 (WV2) imagery. Our goal is two-fold. First, we want to identify land covers for which the combination of extended spectral coverage and high spatial resolution provide a distinctive advantage in classification accuracy. Second, we perform predictor analyses to determine which combinations of bands are more effective in resolving individual targets. This experimental approach provides a basis for building a spectral atlas that can offer guidance on the optimal combination of WV2 spectral bands for different application areas.
[1] Helmi Zulhaidi Mohd Shafri,et al. Hyperspectral Remote Sensing of Vegetation Using Red Edge Position Techniques , 2006 .
[2] Margaret E. Gardner,et al. THE SPECTRAL DIMENSION IN URBAN LAND COVER MAPPING FROM HIGH- RESOLUTION OPTICAL REMOTE SENSING DATA * , 2002 .
[3] Leo Breiman,et al. Random Forests , 2001, Machine Learning.
[4] Younès Bennani,et al. HVS : A Heuristic for Variable Selection in Multilayer Artificial Neural Network Classifier , 1997 .