Gilles Roussel

• University of the Littoral Opal Coast

Insects, particularly butterflies, play a crucial role in maintaining ecosystems. Therefore, better management is needed, which involves identifying the different species. This work aims to classify four important butterfly species using raw images from a spatio-spectral camera. This camera generates images in 192 spectral layers, posing a signific...

Miniaturized CMOS hyperspectral cameras utilizing Fabry-Perot Interferometers (FPIs) have emerged as a low-cost solution providing fast-acquisition miniaturized sensors well-suited for both in-field analysis and remote sensing. However, FPIs generate harmonics around each wavelength of interest, hindering the accuracy and reliability of spectral in...

This paper presents novel unmixing and demosaicing methods for snapshot spectral imaging (SSI) systems utilizing Fabry-Perot filters. Unlike conventional approaches that perform unmixing after image restoration or demosaicing, our proposed methods leverage Fabry-Perot filter deconvolution and extend the “pure pixel” framework to the SSI sensor patc...

In this paper we propose a novel framework that successfully combines random projection or compression to weighted Nonnegative Matrix Factorization (NMF). Indeed a large body of NMF research has focused on the unweighted case—i.e., a complete data matrix to factorize—with a few extensions to handle incomplete data. Also most of these works are typi...

This paper addresses spectral analysis, detection and classification of active fires and seeing the invisible through smoke and thin clouds. The idea is realizable by using an intelligent hybridization of machine/deep learning models and using multi-sensor images (aerial, satellite). The applicability is tested using the hyperspectral images (Visib...

Des caméras hyperspectrales compactes à acquisition spatio-spectrale ont été proposées ces dernières années. Leur miniaturisation et leur conception engendrent des désalignements géométriques pour lesquels le fabricant ne propose pas de solution. Dans nos précédents travaux, nous avons conçu une approche basée sur les collections d'homographies pou...

Dans cet article, nous proposons une nouvelle méthode de démélange pour les systèmes d'imagerie spectrale « snapshot » (SSI) utilisant des filtres de Fabry-Perot. Ces caméras ne fournissent qu'une partie du contenu spectral observé et la stratégie classique consiste à réaliser le démélange après la restauration de l'image (ou dématriçage). Dans cet...

Dans cet article, nous étudions la fusion spatio-temporelle d'une série temporelle d'images multi-spectrales avec une série temporelle d'images hyper-spectrales. Nous proposons pour cela une nouvelle approche fondée sur un réseau antagoniste génératif (GAN). Notre contribution principale réside dans le fait que le GAN prend en entrée des images sat...

This work focuses on filling the knowledge gap associated with the contribution of natural and anthropogenic marine emissions to PM10 concentrations in northern France. For this purpose, a 1-year measurement and sampling campaign for PM10 has been conducted at a French coastal site situated at the Strait of Dover. The characterization of PM10 sampl...

This study aimed to evaluate the oxidative potential (OP) of PM2.5 collected for almost a year in an urban area of the East Mediterranean. Two acellular assays, based on ascorbic acid (AA) and dithiothreitol (DTT) depletion, were used to measure the OP. The results showed that the mean volume normalized OP-AAv value was 0.64 ± 0.29 nmol·min-1·m-3 a...

This work is focused on filling the lack of knowledge associated with natural and anthropogenic marine emissions on PM10 concentrations in Northern France. For this purpose, a one-year measurement and sampling campaign for PM10 has been performed at a French coastal site situated in front of the Straits of Dover. The characterization of PM10 sample...