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: