Thales Track: In space image processing using AI embedded on System On Module: example of OPS-SAT cloud segmentation

Thales Track: In space image processing using AI embedded on System On Module: example of OPS-SAT cloud segmentation

The IRT Saint-Expury in Sophia-Antipolis CIAR (Reactive and Autonomous Image Chain) project has leaded to the OPS-SAT use case. This OPS-SAT experiment demonstrates the capability to perform on board image inferences by Artificial Neural Networks in close real time. Currently used to identify clouds in order to select the useful images for on-board, the CIAR Neural Networks can be trained also to detect wild fires and give the alert to ground in near real time, adding value on board.