Deep Learning for Environment Monitoring
Nov. 10 2021, 9h30-12h30 CET, VIRTUAL EVENT
Combined advances in deep learning and Earth Observation technology have ushered in a new era of remote sensing. We are now able to efficiently oversee agricultural and forest lands at an unprecedented scale, and start to address pressing ecological challenges.
For this LaSTIG seminar, three international researchers will present their work on the subject, as well as three students from our lab:
- Charlotte Pelletier, IRISA, Univ. Bretagne Sud: « Deep Learning for the Analysis of Remote Sensing Time Series »
- Prof. Jan Dirk Wegner, EcoVision, ETH Zurich: « Towards High Carbon Stock Maps at Global Scale »
- Vivien Sainte Fare Garnot, IGN-LaSTIG-Univ. Gustave Eiffel: « Panoptic Segmentation of Satellite Images »
- Marc Russwurm, Computational Science and Earth Observation Laboratory, EPFL: « Data-Driven Vegetation Modeling and Tackling Representation Shift with Few-Shot Meta-Learning Methods »
- Ekaterina Kalinicheva, IGN, INRAE: « Weakly Supervized Vegetation Stratum Analysis from Aerial LiDAR »
- Felix Quinton, IGN-LaSTIG-Univ. Gustave Eiffel: « Modeling Crop Rotations with Deep Learning »
The first four talks will be 25min + 10min question; the last two talks will be 15min + 5min.
To get the zoom link, please register . For questions, you can contact me at:
loic.landrieu AT ign.fr .