Review on Hardware Devices and Software Techniques Enabling Neural Network Inference Onboard Satellites
Guardado en:
| Publicado en: | Remote Sensing vol. 16, no. 21 (2024), p. 3957 |
|---|---|
| Autor principal: | |
| Otros Autores: | |
| Publicado: |
MDPI AG
|
| Materias: | |
| Acceso en línea: | Citation/Abstract Full Text + Graphics Full Text - PDF |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3126018520 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2072-4292 | ||
| 024 | 7 | |a 10.3390/rs16213957 |2 doi | |
| 035 | |a 3126018520 | ||
| 045 | 2 | |b d20240101 |b d20241231 | |
| 084 | |a 231556 |2 nlm | ||
| 100 | 1 | |a Lorenzo, Diana |u Independent Researcher, 56100 Pisa, Italy | |
| 245 | 1 | |a Review on Hardware Devices and Software Techniques Enabling Neural Network Inference Onboard Satellites | |
| 260 | |b MDPI AG |c 2024 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a Neural networks (NNs) have proven their ability to deal with many computer vision tasks, including image-based remote sensing such as the identification and segmentation of hyperspectral images captured by satellites. Often, NNs run on a ground system upon receiving the data from the satellite. On the one hand, this approach introduces a considerable latency due to the time needed to transmit the satellite-borne images to the ground station. On the other hand, it allows the employment of computationally intensive NNs to analyze the received data. Low-budget missions, e.g., CubeSat missions, have computation capability and power consumption requirements that may prevent the deployment of complex NNs onboard satellites. These factors represent a limitation for applications that may benefit from a low-latency response, e.g., wildfire detection, oil spill identification, etc. To address this problem, in the last few years, some missions have started adopting NN accelerators to reduce the power consumption and the inference time of NNs deployed onboard satellites. Additionally, the harsh space environment, including radiation, poses significant challenges to the reliability and longevity of onboard hardware. In this review, we will show which hardware accelerators, both from industry and academia, have been found suitable for onboard NN acceleration and the main software techniques aimed at reducing the computational requirements of NNs when addressing low-power scenarios. | |
| 653 | |a Oil spills | ||
| 653 | |a Software | ||
| 653 | |a Satellite communications | ||
| 653 | |a Hardware | ||
| 653 | |a Aerospace environments | ||
| 653 | |a Satellite imagery | ||
| 653 | |a Remote sensing | ||
| 653 | |a Cybersecurity | ||
| 653 | |a Data processing | ||
| 653 | |a Image processing | ||
| 653 | |a Computer vision | ||
| 653 | |a Digital signal processors | ||
| 653 | |a Power consumption | ||
| 653 | |a Fault tolerance | ||
| 653 | |a Workloads | ||
| 653 | |a Satellites | ||
| 653 | |a Radiation | ||
| 653 | |a Climate change | ||
| 653 | |a Accelerators | ||
| 653 | |a Field programmable gate arrays | ||
| 653 | |a Efficiency | ||
| 653 | |a Wildfires | ||
| 653 | |a Spacecraft recovery | ||
| 653 | |a Neural networks | ||
| 653 | |a Artificial intelligence | ||
| 653 | |a Image segmentation | ||
| 653 | |a Costs | ||
| 653 | |a Power | ||
| 653 | |a Onboard | ||
| 653 | |a Network latency | ||
| 653 | |a Inference | ||
| 653 | |a Missions | ||
| 653 | |a Power management | ||
| 653 | |a Design | ||
| 653 | |a Algorithms | ||
| 653 | |a Latency | ||
| 653 | |a Cubesat | ||
| 653 | |a Hyperspectral imaging | ||
| 700 | 1 | |a Dini, Pierpaolo |u Department of Information Engineering, University of Pisa, Via G. Caruso 16, 56100 Pisa, Italy; <email>pierpaolo.dini@ing.unipi.it</email> | |
| 773 | 0 | |t Remote Sensing |g vol. 16, no. 21 (2024), p. 3957 | |
| 786 | 0 | |d ProQuest |t Advanced Technologies & Aerospace Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3126018520/abstract/embedded/CH9WPLCLQHQD1J4S?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text + Graphics |u https://www.proquest.com/docview/3126018520/fulltextwithgraphics/embedded/CH9WPLCLQHQD1J4S?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3126018520/fulltextPDF/embedded/CH9WPLCLQHQD1J4S?source=fedsrch |