FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912356552933376 |
|---|---|
| author | Furutanpey, Alireza Zhang, Qiyang Raith, Philipp Pfandzelter, Tobias Wang, Shangguang Dustdar, Schahram |
| author_facet | Furutanpey, Alireza Zhang, Qiyang Raith, Philipp Pfandzelter, Tobias Wang, Shangguang Dustdar, Schahram |
| contents | 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 that preserves prediction performance. FOOL partitions high-resolution satellite imagery to maximize throughput. Further, it embeds context and leverages inter-tile dependencies to lower transfer costs with negligible overhead. While FOOL is a feature compressor, it can recover images with competitive scores on quality measures at lower bitrates. We extensively evaluate transfer cost reduction by including the peculiarity of intermittently available network connections in low earth orbit. Lastly, we test the feasibility of our system for standardized nanosatellite form factors. We demonstrate that FOOL permits downlinking over 100x the data volume without relying on prior information on the downstream tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_16677 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression Furutanpey, Alireza Zhang, Qiyang Raith, Philipp Pfandzelter, Tobias Wang, Shangguang Dustdar, Schahram Machine Learning Computer Vision and Pattern Recognition Distributed, Parallel, and Cluster Computing Networking and Internet Architecture Image and Video Processing 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 that preserves prediction performance. FOOL partitions high-resolution satellite imagery to maximize throughput. Further, it embeds context and leverages inter-tile dependencies to lower transfer costs with negligible overhead. While FOOL is a feature compressor, it can recover images with competitive scores on quality measures at lower bitrates. We extensively evaluate transfer cost reduction by including the peculiarity of intermittently available network connections in low earth orbit. Lastly, we test the feasibility of our system for standardized nanosatellite form factors. We demonstrate that FOOL permits downlinking over 100x the data volume without relying on prior information on the downstream tasks. |
| title | FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression |
| topic | Machine Learning Computer Vision and Pattern Recognition Distributed, Parallel, and Cluster Computing Networking and Internet Architecture Image and Video Processing |
| url | https://arxiv.org/abs/2403.16677 |