LUF-net: A physically informed color calibration method for UAV RGB images based on exposure and irradiance information
Chufeng Wang, Bei Liu, Jingyang Zhang, Shichao Jin, Fengjie Yuan · 2026
Read LUF-net: A physically informed color calibration method for UAV RGB images based on exposure and irradiance information by Chufeng Wang, Bei Liu, Jingyang Zhang, Shichao Jin, Fengjie Yuan (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/PMC13452194.txt.
Description
Chufeng Wang and co-authors present in 2026 a light neural net that fixes color in drone farm photos using light and camera facts. Drone shots shift color with sky and exposure, which skews crop trait reads. Their net folds sun strength from a second sensor and camera exposure settings into the image fix, layer by layer.
Trials spanned three crops, four flight heights, and skies from dawn to bright sun. The model's color error fell below a set low mark and beat four rival fix methods. Cutting either input stream hurt the fix, which shows both carry weight. The authors say farm drones can hold true color without a ground target in each frame.
Catalog record
| CREATOR | Chufeng Wang, Bei Liu, Jingyang Zhang, Shichao Jin, Fengjie Yuan |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 35805 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |