Optimal seamline detection for SAR image mosaicking guided by superpixel segmentation and region merging
Dong Yan, Feixiang Zeng, Bairu Chen, Rui Huang, Yi She · 2026
Read Optimal seamline detection for SAR image mosaicking guided by superpixel segmentation and region merging by Dong Yan, Feixiang Zeng, Bairu Chen, Rui Huang, Yi She (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/plos-pone-0348842.txt.
Description
Dong Yan and co-workers devise a smarter way to choose stitch lines when joining radar satellite images into one big map. Mismatched brightness and slight shifts between scenes can leave ugly seams. Their 2026 method first groups pixels into tidy super-regions. These regions stay consistent across overlapping images. Neighbors then merge by texture and edge evidence. Finally, the method picks the cheapest clean path through a network of candidate seams.
Tests on real radar scenes checked each step of the pipeline. Compared with two classic methods, the new route preserved whole objects and hugged their boundaries better. Cleaner mosaics matter for flood mapping, land monitoring, and any wide-area work built on radar imagery.
Catalog record
| CREATOR | Dong Yan, Feixiang Zeng, Bairu Chen, Rui Huang, Yi She |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 57558 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |