Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
April 3, 2026IET Radar Sonar & NavigationOpen Access

Characterisation and Classification of Resident Space Objects Using Radar Networks

View Full Paper
Ask AI
Bookmark
Share

Authors

MRManjunath Thindlu RudrappaFraunhofer Institute for High Frequency Physics and Radar TechniquesMAM. AlbrechtFraunhofer Institute for High Frequency Physics and Radar TechniquesPKPeter KnottFraunhofer Institute for High Frequency Physics and Radar Techniques

Discussion

Loading...

Member takes

Implication

Simulation framework generates radar images to classify space objects, indicating advancements in radar technology.

Key Points

  • The aim is to improve the classification of resident space objects using radar imagery and deep learning.
  • Developed a simulation framework for generating radar images from CAD models of space objects.
  • Created a database of 42 space objects with both radar images and point cloud data.
  • Trained deep learning models on datasets under varying signal-to-noise ratio conditions.
  • Compared performance of point cloud architectures with image-based neural networks.
  • PointNet, DGCNN, and Point Transformer architectures outperformed standard models at low SNR levels.
  • Image-based networks adapted better to noise-corrupted images during training.
  • Noise-augmented training improved robustness for both image and point cloud architectures.

Cite This Study

Rudrappa et al. (2026) studied this question.

synapsesocial.com/papers/69cf5d775a333a821460b2e4https://doi.org/10.1049/rsn2.70140
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Deep learning‐based space debris detection for space situational awareness: A feasibility study applied to the radar processing2024 · 37 citations
  2. 2Deep Residual Learning for Image Recognition2016 · 229,327 citations
  3. 3ImageNet: A large-scale hierarchical image database2009 · 63,509 citations
  4. 4Few‐shot learning for satellite characterisation from synthetic inverse synthetic aperture radar images2024 · 6 citations
  5. 5Range-Doppler-Time Tensor Processing for Deep-Space Satellite Characterization Using Narrowband Radar2024 · 5 citations