Few‐shot learning for satellite characterisation from synthetic inverse synthetic aperture radar images
Abstract Space situational awareness systems primarily focus on detecting and tracking space objects, providing crucial positional data. However, understanding the complex space domain requires characterising satellites, often involving estimation of bus and solar panel sizes. While inverse syntheti...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-04-01
|
| Series: | IET Radar, Sonar & Navigation |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/rsn2.12516 |
| _version_ | 1797203115063115776 |
|---|---|
| author | Friso G. Heslinga Faruk Uysal Sabina B. vanRooij Sven Berberich Miguel Caro Cuenca |
| author_facet | Friso G. Heslinga Faruk Uysal Sabina B. vanRooij Sven Berberich Miguel Caro Cuenca |
| author_sort | Friso G. Heslinga |
| collection | DOAJ |
| description | Abstract Space situational awareness systems primarily focus on detecting and tracking space objects, providing crucial positional data. However, understanding the complex space domain requires characterising satellites, often involving estimation of bus and solar panel sizes. While inverse synthetic aperture radar allows satellite visualisation, developing deep learning models for substructure segmentation in inverse synthetic aperture radar images is challenging due to the high costs and hardware requirements. The authors present a framework addressing the scarcity of inverse synthetic aperture radar data through synthetic training data. The authors approach utilises a few‐shot domain adaptation technique, leveraging thousands of rapidly simulated low‐fidelity inverse synthetic aperture radar images and a small set of inverse synthetic aperture radar images from the target domain. The authors validate their framework by simulating a real‐case scenario, fine‐tuning a deep learning‐based segmentation model using four inverse synthetic aperture radar images generated through the backprojection algorithm from simulated raw radar data (simulated at the analogue‐to‐digital converter level) as the target domain. The authors results demonstrate the effectiveness of the proposed framework, significantly improving inverse synthetic aperture radar image segmentation across diverse domains. This enhancement enables accurate characterisation of satellite bus and solar panel sizes as well as their orientation, even when the images are sourced from different domains. |
| first_indexed | 2024-04-24T08:14:12Z |
| format | Article |
| id | doaj.art-a75f5ff91e1e49dfb24728cf845e2e1a |
| institution | Directory Open Access Journal |
| issn | 1751-8784 1751-8792 |
| language | English |
| last_indexed | 2024-04-24T08:14:12Z |
| publishDate | 2024-04-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Radar, Sonar & Navigation |
| spelling | doaj.art-a75f5ff91e1e49dfb24728cf845e2e1a2024-04-17T04:32:47ZengWileyIET Radar, Sonar & Navigation1751-87841751-87922024-04-0118464965610.1049/rsn2.12516Few‐shot learning for satellite characterisation from synthetic inverse synthetic aperture radar imagesFriso G. Heslinga0Faruk Uysal1Sabina B. vanRooij2Sven Berberich3Miguel Caro Cuenca4TNO ‐ Defence, Safety & Security the Hague the NetherlandsTNO ‐ Defence, Safety & Security the Hague the NetherlandsTNO ‐ Defence, Safety & Security the Hague the NetherlandsTNO ‐ Defence, Safety & Security the Hague the NetherlandsTNO ‐ Defence, Safety & Security the Hague the NetherlandsAbstract Space situational awareness systems primarily focus on detecting and tracking space objects, providing crucial positional data. However, understanding the complex space domain requires characterising satellites, often involving estimation of bus and solar panel sizes. While inverse synthetic aperture radar allows satellite visualisation, developing deep learning models for substructure segmentation in inverse synthetic aperture radar images is challenging due to the high costs and hardware requirements. The authors present a framework addressing the scarcity of inverse synthetic aperture radar data through synthetic training data. The authors approach utilises a few‐shot domain adaptation technique, leveraging thousands of rapidly simulated low‐fidelity inverse synthetic aperture radar images and a small set of inverse synthetic aperture radar images from the target domain. The authors validate their framework by simulating a real‐case scenario, fine‐tuning a deep learning‐based segmentation model using four inverse synthetic aperture radar images generated through the backprojection algorithm from simulated raw radar data (simulated at the analogue‐to‐digital converter level) as the target domain. The authors results demonstrate the effectiveness of the proposed framework, significantly improving inverse synthetic aperture radar image segmentation across diverse domains. This enhancement enables accurate characterisation of satellite bus and solar panel sizes as well as their orientation, even when the images are sourced from different domains.https://doi.org/10.1049/rsn2.12516artificial intelligenceimage segmentationinverse synthetic aperture radar (ISAR)satellite tracking |
| spellingShingle | Friso G. Heslinga Faruk Uysal Sabina B. vanRooij Sven Berberich Miguel Caro Cuenca Few‐shot learning for satellite characterisation from synthetic inverse synthetic aperture radar images IET Radar, Sonar & Navigation artificial intelligence image segmentation inverse synthetic aperture radar (ISAR) satellite tracking |
| title | Few‐shot learning for satellite characterisation from synthetic inverse synthetic aperture radar images |
| title_full | Few‐shot learning for satellite characterisation from synthetic inverse synthetic aperture radar images |
| title_fullStr | Few‐shot learning for satellite characterisation from synthetic inverse synthetic aperture radar images |
| title_full_unstemmed | Few‐shot learning for satellite characterisation from synthetic inverse synthetic aperture radar images |
| title_short | Few‐shot learning for satellite characterisation from synthetic inverse synthetic aperture radar images |
| title_sort | few shot learning for satellite characterisation from synthetic inverse synthetic aperture radar images |
| topic | artificial intelligence image segmentation inverse synthetic aperture radar (ISAR) satellite tracking |
| url | https://doi.org/10.1049/rsn2.12516 |
| work_keys_str_mv | AT frisogheslinga fewshotlearningforsatellitecharacterisationfromsyntheticinversesyntheticapertureradarimages AT farukuysal fewshotlearningforsatellitecharacterisationfromsyntheticinversesyntheticapertureradarimages AT sabinabvanrooij fewshotlearningforsatellitecharacterisationfromsyntheticinversesyntheticapertureradarimages AT svenberberich fewshotlearningforsatellitecharacterisationfromsyntheticinversesyntheticapertureradarimages AT miguelcarocuenca fewshotlearningforsatellitecharacterisationfromsyntheticinversesyntheticapertureradarimages |