Underwater multi-sensor information fusion for salient object detection
Yan Mou, Zhaolong Gao, Jinjiang Li · 2026
Read Underwater multi-sensor information fusion for salient object detection by Yan Mou, Zhaolong Gao, Jinjiang Li (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-0354804.txt.
Description
Yan Mou, Zhaolong Gao, and Jinjiang Li present in 2026 a vision system for picking out the main object in underwater scenes. The task supports tracking, editing, and recognition, but water muddies colour and depth readings. Their network fuses colour and depth data through attention steps that inject and embed features across both channel and space views.
By modelling how the two data types complete each other at wide and narrow scales, the system sharpens standout regions and quiets background noise. Layered fusion also lessens depth errors. Tests on several underwater sets beat leading methods, the authors report, showing the value of careful fusion.
Catalog record
| CREATOR | Yan Mou, Zhaolong Gao, Jinjiang Li |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36058 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |