IFD-YOLO: A Lightweight Infrared Sensor-Based Detector for Small UAV Targets
Fu Li, Xuehan Lv, Ming Zhao, Wangyu Wu, Erik Blasch, Yufeng Zheng · 2025
Read IFD-YOLO: A Lightweight Infrared Sensor-Based Detector for Small UAV Targets by Fu Li, Xuehan Lv, Ming Zhao, Wangyu Wu, Erik Blasch, Yufeng Zheng (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-12736559.txt.
Description
Fu Li and co-authors present IFD-YOLO, a light detector that spots small drones in infrared images. Their twenty twenty-five article deals with a hard sensing task: targets are tiny, the signal is weak against noise, and the drone carrying the sensor has little computing power to spare.
Built on a nano YOLO model, the design adds three parts. A RepViT backbone sharpens feature extraction at both wide and fine scales. A dynamic ghost module fuses features at low cost. A new loss function tightens box placement for small targets. On two data sets it beat the base model on accuracy while using about a quarter fewer parameters and a fifth less compute.
Catalog record
| CREATOR | Fu Li, Xuehan Lv, Ming Zhao, Wangyu Wu, Erik Blasch, Yufeng Zheng |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 80 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |