Thesis of Nicolas Thuylie

Visual tracking with spiking neural networks and its application to aerosol event tracking

The thesis project has two interdependent objectives. The first is the creation of new datasets, which are a top priority for the scientific community in order to compare neuromorphic learning approaches. The second objective is to develop a neuromorphic learning approach for the classification of spatio-temporal image sequences available in large quantities and without terrain truth or with very limited terrain truth. The data are aerosols, collected from earth observation satellites. The results of the thesis will contribute to make a large amount of atmospheric data accessible, even exploitable by the scientific community.

Jury

M. Chaabane DJERABA Professeur des universités Université de Lille Directeur de thèse, Mme Sylvie CHAMBON Professeure des universités Toulouse INP Rapporteure, M. Sergio DAVIES Senior lecturer Manchester Metropolitan University Rapporteur, M. Jean MARTINET Professeur des universités Université Côte d’Azur Examinateur, M. Daniel SORIA Senior Lecturer University of Kent Examinateur, Mme Ioanna GIORGI Lecturer University of Kent Co-directrice de thèse, M. Pierre TIRILLY Maître de conférences Université de Lille Co-encadrant de thèse, Mme Rokia MIASSAOUI Professeure University of Quebec en Outaouais (UQO) Examinatrice, M. Jérôme RIEDI Université de Lille Invité.

Thesis of the team FOX defended on 31/03/2026