A Hybrid Multi-Scale Phase-Correlation Framework for Subpixel Registration of Multi-Temporal Very-High-Resolution Remote Sensing Images
Laila Rasmy, Imane Sebari, Mohamed Ettarid · 2026
Read A Hybrid Multi-Scale Phase-Correlation Framework for Subpixel Registration of Multi-Temporal Very-High-Resolution Remote Sensing Images by Laila Rasmy, Imane Sebari, Mohamed Ettarid (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/PMC13514138.txt.
Description
Rasmy and colleagues proposed a hybrid method for aligning satellite images of the same place taken at different times, in a 2026 study. The method reaches accuracy finer than a single pixel. Precise registration underpins change detection and environmental monitoring, but images suffer local distortions from terrain and viewing angles, and phase correlation struggles with large shifts.
Rasmy built a detector called Fusion that merges two corner finders with line and edge detection for more repeatable landmarks. Points were then matched coarse-to-fine through a Gaussian pyramid, an image stack at shrinking scales, refining each shift with curve fitting. Tested on Pleiades and Sentinel-2 imagery, the framework kept alignment errors well under half a pixel. A two-dimensional fitting variant achieved the lowest error with the highest share of correct matches. The method stayed accurate under noise across resolutions, offering a registration pipeline for Earth observation.
Catalog record
| CREATOR | Laila Rasmy, Imane Sebari, Mohamed Ettarid |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 44 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |