Optimizing the ground sample collection with cost-sensitive active learning for tree species classification using hyperspectral images

This study presents a cost-sensitive active learning method for optimizing the field surveys by a human expert in the classification of single tree species using hyperspectral images. The goal of the proposed method is to guide the human expert in the collection of labeled samples in order to maximize the ratio between the classification accuracy with respect to the travelling costs. Experiments carried out in the context of a real study on forest inventory show the effectiveness of the proposed method.