Land cover mapping capability of multispectral thermal data: The TASI-600 case study

This study shows the land cover mapping accuracy retrievable by the TASI-600 thermal airborne multispectral sensor and describes some of the classification results tested on the thermal preprocessed data for a rural area. In the paper is provided an overview of the principal TASI-600 characteristics, i.e. 32 spectral bands in the 8.0-11.5 ?m spectral range, and land cover classification performances. A full assessment of the TASI-600 spectral bands has been also obtained by ranking them in order to understanding their role in land cover classification. Results accuracies have been validated using available ground truth. The study highlights that the new generation of multi/hyperspectral thermal sensors opens up interesting opportunities for accurate land cover classification.