Consulter le flux RSS

Publications

Cette page présente les publications du Centre Borelli déposées sur le serveur HAL.

Affichage des publications 91 à 100 sur 1261 au total

Image Processing

Anomaly Detection for Hotspot Identification in Landsat Images

This paper presents a methodology for hotspot detection in multispectral images, utilizing the Reed-Xiaoli anomaly detection algorithm. By leveraging short-wave infrared data from Landsat, the Reed-Xiaoli algorithm identifies hotspots with…

Antoine Tadros, Charles Hessel, Rafael Grompone von Gioi, Florentin Poucin, Simon Lajouanie, Carlo De Franchis

2024 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2024) -

Image Processing

Hotspot Detection in Nighttime Landsat Data

We propose a statistically based method to detect hotspots in nighttime short-wave infrared Landsat data. The method assumes an independent and identical Gaussian distribution on the background data and looks for parts of the images with abnormally…

Charles Hessel, Antoine Tadros, Rafael Grompone von Gioi, Florentin Poucin, Simon Lajouanie, Carlo de Franchis

2024 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2024) -

Machine Learning

Gromov-Wasserstein-like Distances in the Gaussian Mixture Models Space

The Gromov-Wasserstein (GW) distance is frequently used in machine learning to compare distributions across distinct metric spaces. Despite its utility, it remains computationally intensive, especially for large-scale problems. Recently, a novel…

Antoine Salmona, Julie Delon, Agnès Desolneux

Transactions on Machine Learning Research Journal -

Neural and Evolutionary Computing

LEVERAGING EDGE DETECTION AND NEURAL NETWORKS FOR BETTER UAV LOCALIZATION

We propose a new method for the geolocalization of Unmaned Aerial Vehicles (UAV) in environments without Global Navigation Stallite Systems (GNSS). Current stateof-the-art methods use an offline-trained encoder to compute a vector representation …

Théo Di Piazza, Enric Meinhardt-Llopis, Gabriele Facciolo, Bénédicte Bascle, Corentin Abgrall, Jean-Clément Devaux

2024 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2024) -

Mathematics

On the Domain Generalization Capabilities of Interactive Segmentation Methods

Interactive image segmentation (IIS) methods are usually trained over segmentation datasets containing natural images. They are also usually evaluated over natural images. However, the most common use case is the annotation of new images from a…

Franco Marchesoni-Acland, Tanguy Magne, Fayçal Rekbi, Gabriele Facciolo

Image Processing On Line -