The project
Research project aiming at the exploring and assessing potential of weak and semi-supervision methods to produce land cover maps through semantic segmentation.
Skills learned and/or deployed:
- Optical VHRRS image processing with object-based image analysis (OBIA)
- Machine learning (feature selection, hyperparameter optimization)
- Deep learning for semantic segmentation (Tensorflow, Keras)
- Python programming (scikit-learn, Tensorflow, Numpy, Pandas)
- Docker containerization and Singularity for HPC
- Grass Gis, Qgis
- Git, Github
- Unix