Data Fusion v2

Deliverable: 
D2.8

This is an updated version of the D2.8 that contains the Data Fusion module for the CANDELA project. The synthetic aperture radar and multispectral data are fused at feature level or at semantic level. The first fusion is made by extracting the features of each type of data and then combining them in a new block inside the data model generation module of the data fusion system, while the second fusion is made by concatenating the semantic labels after the image search and semantic annotation module has been called.

Data Fusion v1

Deliverable: 
D2.7

This deliverable contains the Data Fusion 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 to Copernicus data.

Semantic Search v2

Deliverable: 
D2.6

This is an updated version of the D2.6 that describes the second version of the semantic search task. As already mentioned in the deliverable D2.5, the task covers a set of tools helping retrieve images through a semantic description of their content and search for data related to their content.

Deep Learning v2

Deliverable: 
D2.4

This deliverable describes the CANDELA change detection building blocks.

As already mentioned in the deliverable D2.3, two change detection building blocks are designed to work respectively on Sentinel-2 and on Sentinel-1 data. The two tools are really different and developed by different teams, which is why they will be described in two different sections.

Deep Learning v1

Deliverable: 
D2.3

This deliverable describes the first version of the change detection building block without any tuning for the use cases. For this first version, the change detection module will be adapted only for Sentinel-1 and Sentinel-2 data. Due to the difference between optical and SAR sensors, change detection chains proposed are different for both sensors. Each chain has been built with the purpose of being scalable and split into micro services for easy deployment.

Data Mining v2

Deliverable: 
D2.2

This is an updated version of the D2.2 that describes the work done on the Data Mining components during the second step of the CANDELA project, mainly the integration of the data model part on the CANDELA platform as back end, and the user interaction part on the local user machine as front end.

The Data Mining module is basically composed of four main sub-modules: data model generation for data mining (DMG-DM), database management system (DBMS), image search and semantic annotation (KDD), and multi-knowledge and query (QE).

Data Mining v1

Deliverable: 
D2.1

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.