Fog-Adaptive-YOLO: A lightweight model for insulator defect detection
Xiaoyuan Jin, Yuzhen Zhao, Wangyu Shen, Zhun Guo, Jianjing Gao, Baoxi Yuan, Xiyuan Zhu · 2026
Read Fog-Adaptive-YOLO: A lightweight model for insulator defect detection by Xiaoyuan Jin, Yuzhen Zhao, Wangyu Shen, Zhun Guo, Jianjing Gao, Baoxi Yuan, Xiyuan Zhu (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-0351054.txt.
Description
Xiaoyuan Jin and colleagues built a light vision model that spots faults on power line insulators even in fog. Fog blurs small cracks and dirt marks, and drone photos add busy backgrounds. Their model cleans fog noise, lifts faint fault marks, and blends detail at several scales while staying small enough for field gear.
On a fog data set the team built, accuracy reached a solid mark with under three million settings to tune. Scores held up on two public fog sets and on a clear weather road scene set as well. Light weight matters here: a model that runs on a drone can flag faults during flight instead of after landing, cutting inspection time for power crews.
Catalog record
| CREATOR | Xiaoyuan Jin, Yuzhen Zhao, Wangyu Shen, Zhun Guo, Jianjing Gao, Baoxi Yuan, Xiyuan Zhu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 70874 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |