Complex-Domain Semantic Segmentation of Spacecraft Directly from ISAR Echoes
Aoxiang Pan, Yonghua He, Yonggang Li, Jiahao Wang, Ruitao Shen, Weigang Zhu · 2026
Read Complex-Domain Semantic Segmentation of Spacecraft Directly from ISAR Echoes by Aoxiang Pan, Yonghua He, Yonggang Li, Jiahao Wang, Ruitao Shen, Weigang Zhu (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13364143.txt.
Description
Aoxiang Pan and colleagues present a 2026 study on labeling spacecraft parts directly from radar echoes, skipping the usual step of forming a radar image first. In the classic pipeline, making the image discards echo phase and scatter detail that could guide the labeling, and hand-marking pixels is costly. Their One-Stop Segmentation design works in the complex signal domain and adds an automatic labeling module that builds masks from the echoes' own scattering traits.
A matching network then learns from those labels to segment new echoes end to end. The authors report lower application cost through the shorter chain and machine-made labels, with spacecraft structure priors steering focus to bodies and edges. The frame targets on-orbit inspection and servicing.
Catalog record
| CREATOR | Aoxiang Pan, Yonghua He, Yonggang Li, Jiahao Wang, Ruitao Shen, Weigang Zhu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 73951 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |