Autonomous method for selection or validation of training samples for large size hyperspectral images

Abstract

Providing unbiased ground truths for large size images is a complex task that is difficult to achieve in practice. The aim of our method is to easily produce reliable ground truths, from images covering large areas while respecting the physical nature of the observed data. The first step localizes all classes existing in a large size image without any a prior knowledge, as well as the samples that make them up. Next, the user selects classes from these unbiased detected classes, in order to build a true ground truth adapted to this application. No transformation is carried out on of characteristics (spectral features) of the hyperspectral image pixels measured objectively by the sensor. To prove the relevance of the learning sample selection method, we use three supervised classification methods requiring training samples. Two hyperspectral images are selected to illustrate the performance of the obtained training samples. The results of the proposed method are also compared to those available of some state of the art deep learning methods.