This deliverable descrives the Data Mining tool components corresponding to the first version without any tuning for the use cases. For this first version, the EOLib system will be used and adapted for Copernicus data.
The Data Mining tool is basically composed of four main modules: data model generation, database management system, image search and semantic annotation, and multi-knowledge and query.
The first module transforms the original format of the EO products into smaller and more compact product representations that include image descriptors, metadata, image patches, etc.
The second module is used for storing all the generated information and allows querying and retrieval of the available data.
The third module (based on cascaded learning) is in charge of finding patterns of interest from the processed data at multi-resolution level and presenting the data to the user. Moreover, this module allows semantic annotation of the image content by using machine learning algorithms and human interaction.
The fourth module allows the user to search within the database for different knowledge/information (e.g., metadata, semantics, features, etc.) at multi-level.
Best viewed in Chrome or FireFox
This project has received funding from the European Union's Horizon 2020
research and innovation programmeunder grant agreement No 776193