PFA - Product Feature extraction and Analysis

The aim of this project was to demonstrate that feature extraction and analysis of EO data makes it possible to exploit the large volumes of various types of satellite data more efficiently, and through this to foster the scientific analysis of mission wide data sets. This project addressed emerging methods and tools for data product features and information extraction, in view of possible implementations for enriching data description and easing the use of archived data.

Due to the recent developments of imaging satellite sensors, huge quantities of EO data have been acquired. Accordingly, millions of single-date as well as time-series of scenes provided by optical, radar and other sensors have been collected and stored on the EO data archives. To properly exploit the huge amount of EO data, the project was aim at implementing two main parts:

  • a feature extraction part aiming at effectively derive sets of features from different kinds of EO data, i.e., SAR, optical and also time series of SAR and optical images, and
  • a scenarios part aiming at exploiting the features obtained in the first part in the context of information extraction scenarios from the EO data analysis.