Ass. Professor at Univ. Bretagne Sud (UBS), Vannes, France
Tel: [+33] (0)2 97 01 72 54
Address: Laboratoire IRISA, UMR CNRS 6074
BP 573, 56000 Vannes
Charlotte Pelletier is an associate professor in computer science at Univ. Bretagne Sud, Vannes, France. She conducts her research in Obelix team at the Institute for Research in IT and Random Systems (IRISA), Vannes, France. She is the coleader of the GeoData Science track within the Erasmus Mundus Joint Master Degree named Copernicus Master in Digital Earth. Her research focuses on machine learning, in particular time series analysis with applications in remote sensing.
From January 2018 to September 2019, she was a research fellow at the Faculty of Information Technology, Monash University, Melbourne, Australia. During her postdoctoral, supervised by Pr. Geoff Webb and Dr. François Petitjean, she proposed and developed accurate and scalable time series classification algorithms. The main application has been in remote sensing with the production of the first land cover map at 10 m spatial resolution over Victoria, Australia.
In December 2017, she completed her Ph.D. with the French Space Agency (CNES) and the French Mapping Agency (IGN), at CESBIO laboratory in Toulouse (France). She worked under the supervision of Pr. Gérard Dedieu (CNES) and Dr. Silvia Valero (Associate Professor at the University of Toulouse). Her Ph.D work aimed at improving the classification of new high resolution satellite image time series, such as the Sentinel-2 one. In particular, she analyzed the classifier robustness to the presence of mislabeled training data. She also explored the use of mislabeled data detection techniques, and she proposed new filtering approaches to deal with mislabeled data in the classification framework. This work has been awarded best PhD in Science by the Académie des Sciences of Toulouse in 2018.