Deep learning for SAR image processing

Описание: This webinar is the part of the webinar series organised by the ISPRS WG III/3 (Active Microwave Remote Sensing) with the technical support of the ISPRS Student Consortium (ISPRS SC).It is organised on the second Wednesday of every months.

Date: 9 April, 2025 Time: 12:00 - 13:00 (GMT+0)
Title: Deep learning for SAR image processing
Speaker: Florence Tupin, Télécom Paris
Moderator: Michael Schmitt

Abstract: In the first part of this talk we will review some recent deep learning based methods for speckle reduction. Then we will focus on a new self-supervised approach called MuChaPro (Multi-Channel Projections) leveraging on single channel despeckling to handle multi-channel data.

Speaker's Bio: Florence Tupin(Senior Member, IEEE) received the engineering degree and the Ph.D. degree in signal and image processing from Ecole Nationale Superieure des Telecommunications (ENST), Paris, France, in 1994 and 1997, respectively, and the Habilitation a Diriger des Recherches degree from the University of Rennes, Rennes, France, in 2007. From 1997 to 1998, she was with SAGEM, Paris, France, where she worked on fingerprint recognition. She is currently a Professor of image and signal processing with LTCI, Telecom Paris, Paris, France. From 2014 to 2020, she was the Head of the Image, Modeling, Analysis, GEometry,and Synthesis Team of LTCI, and since 2020 she has been deputy director of LTCI. She is currently Head of the Image, Data, Signal departement of Telecom Paris. She has coauthored more than 200 papers. Her research interests include image processing and analysis, especially for remote sensing and synthetic aperture radar imaging applications, and earth observation.
More details: https://sc.isprs.org/resources/webinars/