ON THE RELATIVE PREDICTIVE VALUE OF THE NEW SPECTRAL BANDS IN THE WORLDVIEW-2 SENSOR

被引：37

作者：

Marchisio, G. ^{[1
]}

Pacifici, F. ^{[1
]}

Padwick, C. ^{[1
]}

机构：

[1] DigitalGlobe, Res & Dev, Longmont, CO 80503 USA

来源：

2010 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM | 2010年

关键词：

WorldView-2; multispectral; land cover classification; machine learning; spectral predictors;

D O I：

10.1109/IGARSS.2010.5649771

中图分类号：

P [天文学、地球科学];

学科分类号：

07 ;

摘要：

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.

引用

页码：2723 / 2726

页数：4