GAME-YOLO: Global Attention and Multi-Scale Enhancement for Low-Visibility UAV Detection with Sub-Pixel Localization
Ruohai Di, Hao Fan, Yuanzheng Ma, Jinqiang Wang, Ruoyu Qian · 2025
Read GAME-YOLO: Global Attention and Multi-Scale Enhancement for Low-Visibility UAV Detection with Sub-Pixel Localization by Ruohai Di, Hao Fan, Yuanzheng Ma, Jinqiang Wang, Ruoyu Qian (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-12731744.txt.
Description
Ruohai Di, Hao Fan, Yuanzheng Ma, Jinqiang Wang, and Ruoyu Qian published this study in 2025. It presents a camera system that spots small drones in poor viewing conditions, such as low light, haze, and blur. Small, slow, low-flying drones are hard to see, yet guards and airports need to find them fast.
Their system builds on a known detector and adds five upgrades. A front stage clears up the image, a wider attention step reads the whole scene, and a fusion step mixes detail at several scales. A special head pinpoints targets smaller than one pixel of shift. On a test set built for hard conditions, the system scored well above its base model and its closest rival. It also ran fast, at forty-eight frames per second, with a small model size.
Catalog record
| CREATOR | Ruohai Di, Hao Fan, Yuanzheng Ma, Jinqiang Wang, Ruoyu Qian |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 81 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |