FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression

arXiv:2403.16677v1 Announce Type: new
Abstract: Nanosatellite constellations equipped with sensors capturing large geographic regions provide unprecedented opportunities for Earth observation. As constellation sizes increase, network contention poses a downlink bottleneck. Orbital Edge Computing (OEC) leverages limited onboard compute resources to reduce transfer costs by processing the raw captures at the source. However, current solutions have limited practicability due to reliance on crude filtering methods or over-prioritizing particular downstream tasks.
This work presents FOOL, an OEC-native and task-agnostic feature compression method …

abstract arxiv compression compute computing constellation costs cs.cv cs.dc cs.lg cs.ni earth earth observation edge edge computing eess.iv feature network observation opportunities processing raw reduce resources satellite sensors transfer type