PhD student, LISTIC, USMB
Contact
E-mail : antoine.bralet@univ-smb.fr || Telephone: +33(0) 4 50 09 65 91 || Web page: https: //ant89ne.github.io/
Office : A210 || Postal address: LISTIC - 5 chemin de Bellevue - Annecy-le-Vieux - CS 80439 - 74944 ANNECY CEDEX
Thesis
Theme: AFuTé
Subject: Multimodal Deep Learning for the analysis of spatio-temporal dynamics from remote sensing images / Apprentissage multimodal profond et analyse des dynamiques spatio-temporelles par imagerie de télédétection
Résumé: The aim of our research is to detect landslides on satellite images using deep learning methods. The study distinguishes between sudden landslides caused by intense rainfall and slow, destructive, long-term landslides. Several methods have been implemented: radar-to-optical modality translation for cloud-independent detection, task combination to make translation more relevant, multimodal detection with missing modalities, InSAR dataset creation and neural network explicability are some of the topics covered in this thesis.
The topic of the researches target sliding areas detections from remote sensing images by using deep learning approaches. Both sudden and slow moving phenomena are of interest in the thesis requiring the implementation of several deep learning techniques. Among them, the major contributions lie in radar-optical modality translation for weather robust detections, leveraging land-cover classification to increase translation reliability, apply multimodal slide detections algorithms within a missing modality context, create a new InSAR dataset or introduce explainability within the networks.
- Deep Learning of Radiometrical and Geometrical Sar Distorsions for Image Modality translations, Bralet, A., Atto, A. M., Chanussot, J., & Trouvé, E. (2022, October). In 2022 IEEE International Conference on Image Processing (ICIP) (pp. 1766-1770). IEEE.
- Impact de la stratégie de décodage sur la traduction de modalité radar-optique d'images de télédétection, Bralet, A., Atto, A., Chanussot, J., & Trouvé, E., number 2023-1309, pages p. 929-932, Grenoble. GRETSI - Research Group in Signal and Image Processing
Additional work :
- ISSLIDE: InSAR dataset for Slow SLIding area DEtection with machine learning, Bralet, A., Trouvé, E., Chanussot, J., & Atto, A. M., September 22, 2023, IEEE Dataport, doi: https://dx.doi.org/10.21227/dhxt-5g91.
- Towards a multi-Modal, multi-Temporal and multi-Phenomena dataset for natural phenomena observation through deep learning, Bralet, A., Atto, A. M., Chanussot, J., & Trouvé, E. First proposed in 2022 Mesure de la Déformation par Imagerie Satellitaire (MDIS).
Supervisor: Abdourrahmane ATTO (LISTIC)
Co-supervisor: Emmanuel TROUVÉ (LISTIC) - Jocelyn CHANUSSOT (GIPSA-Lab)
Start of thesis: 01/10/2021
This thesis is funded by the IATOAURA Project of the Auvergne Rhône-Alpes region.