Sidonie Lefèbvre

Évaluation des paramètres LIDAR pour les particules de suie d’origine aéronautique

Yoran Raynaud Diarra, Romain Ceolato, Andrés Bedoya, Sidonie Lefèbvre et autres

International audience

Estimating temperature and gas concentrations in propellant flames using metamodeling and global optimization

Claire Lavigne, Sidonie Lefèbvre, Christian Musso, Sylvain Rommeluère

We propose a methodology combining polynomial metamodeling and global optimization for estimating temperature and gas concentrations in propellant flames from moderate-resolution spectroradiometer measurements. We retrieve seven parameters: temperature, soot absorbance, concentrations of CO2 , H2O, CO, and HCl and the projected source …

fr (code pays fourni par la source)

Self-supervised learning for object detection in challenging settings: A survey

Alina Ciocarlan, Sidonie Lefèbvre, Sylvie Le Hégarat‐Mascle, Arnaud Woiselle

Self-supervised learning (SSL) has shown great promise in computer vision, enabling networks to learn meaningful representations from large unlabeled datasets. SSL methods fall into two main categories: instance discrimination and image modeling. While instance discrimination is fundamental to SSL, it was originally …

fr (code pays fourni par la source)

Self-supervised learning for object detection in challenging settings: A survey

Alina Ciocarlan, Sidonie Lefèbvre, Sylvie Le Hégarat‐Mascle, Arnaud Woiselle

Self-supervised learning (SSL) has shown great promise in computer vision, enabling networks to learn meaningful representations from large unlabeled datasets. SSL methods fall into two main categories: instance discrimination and image modeling. While instance discrimination is fundamental to SSL, it was originally …

fr (code pays fourni par la source)

An anomaly-aware detection head for frugal and robust Infrared Small Target Detection

Alina Ciocarlan, Sylvie Le Hégarat‐Mascle, Sidonie Lefèbvre

Infrared Small Target Detection (IRSTD) is a challenging task in defense applications, where complex backgrounds and tiny target sizes often result in numerous false alarms using conventional object detectors. To overcome this limitation, we propose an Anomaly-Aware version of You Only Look …

fr (code pays fourni par la source)

An anomaly-aware detection head for frugal and robust Infrared Small Target Detection

Alina Ciocârlan, Sylvie Le Hégarat‐Mascle, Sidonie Lefèbvre

Infrared Small Target Detection (IRSTD) is a challenging task in defense applications, where complex backgrounds and tiny target sizes often result in numerous false alarms using conventional object detectors. To overcome this limitation, we propose an Anomaly-Aware version of You Only Look …

fr (code pays fourni par la source)

Optimizing Permutation-Invariant Criterion with Law-Smooth Cross-Entropy Method: Application to Spectral Band Selection for Anomaly Detection

Frédéric Dambreville, Sidonie Lefèbvre

Une distance de style stochastique pour la synthèse de textures multispectrales

Sélim Ollivier, Yann Gousseau, Sidonie Lefèbvre

International audience

fr (code pays fourni par la source)

3D Radiative Transfer Modeling for Maize Traits Retrieval Across Different Growth Stages: Exploring the Complementarity of Sentinel-2 and CHIME

Romain Démoulin, Jean-Philippe Gastellu-Etchegorry, Sidonie Lefèbvre, Xavier Briottet et autres

International audience

Modeling 3D radiative transfer for maize traits retrieval: A growth stage-dependent study on hyperspectral sensitivity to field geometry, soil moisture, and leaf biochemistry

Romain Démoulin, Jean‐Philippe Gastellu‐Etchegorry, Sidonie Lefèbvre, Xavier Briottet et autres

This study integrates a dynamic plant growth model with a three-dimensional (3D) radiative transfer model (RTM) for maize traits retrieval using high spatial–spectral resolution airborne data. The research combines the Discrete Anisotropic Radiative Transfer (DART) model with the Dynamic L-System-based Architectural maize …

fr (code pays fourni par la source)

Kernel based sensitivity analysis applied to crop monitoring with hyperspectral remote sensing

Romain Démoulin, Sidonie Lefèbvre, Jean‐Philippe Gastellu‐Etchegorry, Zhijun Zhen et autres

International audience

fr (code pays fourni par la source)

Estimation of the Parameters of a Three-Dimensional Gust Model with a Wind Lidar

Christian Musso, Thibault Boulant, Matthieu Valla, Sidonie Lefèbvre et autres

Reducing fuel consumption for future airplanes is a critical issue. One solution is to design airplanes with a large wing aspect ratio to increase the lift. However, such wings are sensitive to loads induced by gusts. A technique consists of using adaptive …

fr (code pays fourni par la source)