Underwater Robot Object Detection Algorithm Based on YOLOv11
Yongqing Shi, Wei Chen, Duo Wan, Lu Han · 2026
Read Underwater Robot Object Detection Algorithm Based on YOLOv11 by Yongqing Shi, Wei Chen, Duo Wan, Lu Han (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/pmc-13259184.txt.
Description
Yongqing Shi and co-authors teach a detection network to see through murky water. Underwater robots struggle because scattering, color loss, and uneven light blur every target. Their 2026 system upgrades the YOLOv11 detector with three purpose-built changes for degraded scenes.
Reconstruction convolutions trim redundant detail so real shapes stand out, while shuffle attention spotlights fine textures. A reworked scoring rule steadies the boxes drawn around objects. On robotic detection trials, the tuned model beat the stock version's accuracy by several points, reaching the high eighties. It stayed fast enough for live use, which matters when a robot must react in real time.
Catalog record
| CREATOR | Yongqing Shi, Wei Chen, Duo Wan, Lu Han |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 50 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |