En savoir plus

Introduction :

Hyperspectral imaging (HSI), especially in proximal sensing, proves to be a relevant solution to describe and discriminate complex physiological phenomena involved in the diagnosis of phytopathologies.

However, most of the proposed methods for processing hyperspectral images, only consider the spectral aspect and consider the hyperspectral camera as a spectrometer that enables to acquire several points.This raises issues regarding the selection of samples to estimate a model.

In this approach, we propose a new method to process both spatial and spectral information contained in hyperspectral image.

Présentation :