Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 26, 2026SensorsOpen Access

CD-TrGNN: A Complex-Domain Transformer–Graph Neural Network for ISAR Space Target Attitude Estimation

View Full Paper
Ask AI
Bookmark
Share

Authors

YHYonghua HeJWJiahao WangAPAoxiang Pan

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates enhanced attitude estimation in space surveillance, indicating improved situational awareness.

Key Points

  • The aim is to enhance space target attitude estimation using a novel method that overcomes existing limitations.
  • Introduced a complex-domain Transformer module to capture long-range dependencies in ISAR images.
  • Employed a graph convolution module with learnable adjacency matrices to model satellite structural relationships.
  • Performed experiments on a custom ISAR complex image dataset to validate the approach.
  • Achieved a three-axis mean absolute error of 1.70°.
  • Maintained an error of 2.81° at a 5 dB signal-to-noise ratio.
  • Demonstrated accuracy below 2° for two different satellite structures.

Cite This Study

He et al. (2026) studied this question.

synapsesocial.com/papers/6a65a825d3aea3239cd789e6https://doi.org/10.3390/s26154705
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. 1Few-shot Classification for ISAR Images of Space Targets by Complexvalued Patch Graph Transformer2024 · 13 citations
  2. 2HMG-Former: a hierarchical meta-graph transformer framework for robust multi-class SAR target recognition2026
  3. 3CCDN-DETR: A Detection Transformer Based on Constrained Contrast Denoising for Multi-Class Synthetic Aperture Radar Object Detection2024 · 6 citations
  4. 4RaTDet: A Marine Radar Transformer Network for End-to-End Target Detection2026
  5. 5Transformer Network-Aided Relative Pose Estimation for Non-cooperative Spacecraft Using Vision Sensor2024 · 4 citations