SARCDNet-an enhanced deep learning network for change detection from bi-temporal SAR images
Vibha Damodara Kevala, Vishal Mukundan, Sravya Nedungatt, Shilpa Suresh, Shyam Lal · 2025
Read SARCDNet-an enhanced deep learning network for change detection from bi-temporal SAR images by Vibha Damodara Kevala, Vishal Mukundan, Sravya Nedungatt, Shilpa Suresh, Shyam Lal (2025) 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/pmc-12804961.txt.
Description
Vibha Damodara Kevala and co-authors present SARCDNet, a deep network that spots surface change between two radar images. Radar sees through cloud and night, which makes it prized for flood watches, disaster response, and city growth checks. Its speckle noise, though, muddies fine change calls.
Their 2025 paper builds the network around an adaptive fusion block. Global filtering in the frequency domain draws out the broad strokes, while channel attention boosts the features that matter. The design stays light on compute while it damps speckle. Tests on public data sets, including a Yellow River set, show stronger accuracy than prior methods. The authors pitch the tool for steady earth watch from orbit.
Catalog record
| CREATOR | Vibha Damodara Kevala, Vishal Mukundan, Sravya Nedungatt, Shilpa Suresh, Shyam Lal |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 33 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |