MDF-Det: Motion-Aware Decoupling and Scene Filtering for Wide Area Small Moving Target Detection
Kangqiushi Li, Xiaoran Zhang, Zheng Zhang, Huaxin Xiao, Yu Liu · 2026
Read MDF-Det: Motion-Aware Decoupling and Scene Filtering for Wide Area Small Moving Target Detection by Kangqiushi Li, Xiaoran Zhang, Zheng Zhang, Huaxin Xiao, Yu Liu (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-13611703.txt.
Description
Kangqiushi Li and co-authors present in 2026 a detector for tiny moving targets in wide area air views. The targets are faint, often crowd close, and sit in clutter that spawns false alarms, all at low frame rates.
Their system works in stages. First it blends motion cues with frame change cues to lift faint targets out of the background. Next it splits merged blobs in dense groups with a fine heat map. Last it uses scene sense, such as where cars can go, to cut false alarms. Tests on a public wide area set beat past methods by a clear margin.
Catalog record
| CREATOR | Kangqiushi Li, Xiaoran Zhang, Zheng Zhang, Huaxin Xiao, Yu Liu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 62 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |