Deep Learning simplification for on-board processing


The main objective of the project is to define a workflow easing the integration and reduction of complex deep neural networks (DNN) models on Soc FPGA platforms.


Image processing on-board (HR & VHR & Hyper)

This workflow will be demonstrated on a deep learning (DL) image processing pipeline on board devoted to feature extraction.

This pipeline will be as generic as possible, keeping in mind common on board hardware resources (spatialized or not), to change the performed recognition tasks (clouds, floods, planes, ships or more generic objects identification).

The main challenge of this activity is to define the most suitable combination of methods for DL networks simplification (pruning, compression) being generic enough to be applied to networks or aggregate of networks with different types of architectures. For example:

As a summary, the main objectives of the project are:
Reduce DNN free parameters to fit in existing devices suitable for cubesats platforms, with minimal performances loss & high throughput
Propose and bench generic methodologies for DNN simplification
some applications
to identify ships, planes or vehicules for sites monitoring
in agriculture, to analyse cultures and soil evolution
forest fire
to identify and fight forest fires
to identify evolution of glaciers and movement of drifting icebergs
for any other application
This work is funded by a contract in the framework of the EO SCIENCE FOR SOCIETY PERMANENTLY OPEN CALL FOR PROPOSALS EOEP-5 BLOCK 4 issued by the European Space Agency.
  • Contractor:
  • Agenium Space
  • 1 avenue de l'Europe, Bâtiment 1
  • 31400 Toulouse