DustVeil: Label-Free Real-Time Detection of Airborne Coal-Mine Dust in Camera Streams via Physically-Grounded Multi-Cue Fusion and Knowledge Distillation
Ziming Huang, Yujia Wang, Kun Huang, Jianwei Yang, Zimo Fan, Xiaodong Sun, Tielin Zhao, Lei Ji, Tong Zhang, Fanglue Zhang · 2026
Read DustVeil: Label-Free Real-Time Detection of Airborne Coal-Mine Dust in Camera Streams via Physically-Grounded Multi-Cue Fusion and Knowledge Distillation by Ziming Huang, Yujia Wang, Kun Huang, Jianwei Yang, Zimo Fan, Xiaodong Sun, Tielin Zhao, Lei Ji, Tong Zhang, Fanglue Zhang (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-13568155.txt.
Description
Ziming Huang and co-authors present a vision system that spots coal dust plumes in mine camera feeds, in this 2026 paper. Underground scenes are dark, lights move with the machines, and dust looks much like lamp glare, shiny steel, or water spray. Human labels for training are scarce and costly down a mine. Their system, DustVeil, needs none, learning instead from physics-based cues.
A software teacher fuses three cues: a veiling measure against the background, local loss of texture, and a dark-channel signal. Gates screen out glare and color tricks, and the cues merge into a plume map with a mask. A fast student model then learns from the teacher's output for real-time use. Spotting dust as it rises helps mines control a hazard to lungs and safety alike.
Catalog record
| CREATOR | Ziming Huang, Yujia Wang, Kun Huang, Jianwei Yang, Zimo Fan, Xiaodong Sun, Tielin Zhao, Lei Ji, Tong Zhang, Fanglue Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 52 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |