A low illumination target detection method based on a dynamic gradient gain allocation strategy
Zhiqiang Li, Jian Xiang, Jiawen Duan · 2024
Read A low illumination target detection method based on a dynamic gradient gain allocation strategy by Zhiqiang Li, Jian Xiang, Jiawen Duan (2024) 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-11585611.txt.
Description
Li, Xiang, and Duan built this detection method in twenty twenty-four for finding objects in near-dark images. Standard detectors miss targets or fire falsely when light is low. Their model, DimNet, reworks several parts of a baseline detector at once. The aim is sharper features and cleaner boxes under poor light.
A new neck design mixes fine spatial detail with high-level meaning. A fusion module blends channel, spatial, local, and global cues together. The detection head was rebuilt and slimmed by sharing parameters. A fresh loss function focuses on target centers and downweights poor guesses. On a public dark-image dataset, DimNet beat both its baseline and the prior best method by clear margins.
Catalog record
| CREATOR | Zhiqiang Li, Jian Xiang, Jiawen Duan |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 73 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |