Dynamic Feature Elimination-Based Visual–Inertial Navigation Algorithm
Jiawei Yu, Hongde Dai, Juan Li, Xin Li, Xueying Liu · 2025
Read Dynamic Feature Elimination-Based Visual–Inertial Navigation Algorithm by Jiawei Yu, Hongde Dai, Juan Li, Xin Li, Xueying Liu (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-12787790.txt.
Description
Jiawei Yu, Hongde Dai, Juan Li, Xin Li, and Xueying Liu improve camera-based navigation for moving scenes in a paper from 2025. Visual-inertial systems estimate motion from cameras plus motion sensors. Passing people and vehicles corrupt their feature points. The new algorithm rebuilds the feature extractor to fuse fine texture with deep meaning. A tracking module then spots moving objects in real time and deletes their points.
Only static background features reach the pose solver. On a standard driving data set, trajectory accuracy improved by about fifteen percent over the base system. Each frame processed in roughly twenty-four milliseconds. The authors target robots and vehicles in busy environments.
Catalog record
| CREATOR | Jiawei Yu, Hongde Dai, Juan Li, Xin Li, Xueying Liu |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 45 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |