Annonce

Les commentaires sont clos.

Convergent Plug-and-Play algorithm for Deep Hyperspectral Unmixing

21 December 2023

Catégorie : Stagiaire

General description

Artificial intelligence (AI) and deep learning approaches have produced impressive results on many problems of computer vision and image processing. The field of remote sensing, which exploits satellite or aerial images for Earth observation, also benefits from the efficiency of these approaches. This has a strong social impact, as the applications of these methods tackle crucial issues such as environment monitoring (e.g. urban monitoring, deforestation, crop and agriculture monitoring).

 
Nevertheless, one of the issue with deep learning methods is their lack of interpretability. This is an important matter in remote sensing, since the images are ultimately used for strategic purposes (such are urban planning) where small errors can have a severe financial impact. To circumvent this issue, one can rely on the so-called plug-and-play methods, which combine neural networks and classical iterative optimization algorithms, the latter being highly interpretable. So far, these methods have not been extensively applied to hyperspectral imaging. The goal of this internship would be to study the use of plug-and-play methods for hyperspectral imaging, and to produce mathematical guarantees showing the reliability of the considered methods.
 
Candidate
 
The candidate must be a Master 2 student (or equivalent) with a strong knowledge of signal/image processing and mathematics (in particular, optimization). Basic machine learning knowledge is at least required. Ideally, the candidate will be familiar with the Python language (and in particular with Pytorch). Knowledge in hyperspectral imaging is a plus.
 
The candidate will acquire an expertise in remote sensing, deep learning, inverse problems and plug-and-play methods. Such skills are largely valuable, both in academia and in private companies, and are transferable to many other applications such as biomedical imaging, astrophysics, etc.
 
An extension of this subject to a PhD might be considered.
 
Contact
 
The internship (6 months) will take place in the IMAGES team (Télécom Paris) under the supervision of Christophe Kervazo and Arthur Leclaire.
 
Contact: christophe.kervazo@telecom-paris.fr; arthur.leclaire@telecom-paris.fr;
 
 
 
The full subhect can be found at: https://partage.imt.fr/index.php/s/SrTe3pT2nFQ6Bnk